Initial version that works with the lstein fork. The only things not working are: CPU mode, streaming updates (live and progress bar), Turbo Mode, and keeps the model in VRAM instead of RAM

Image item refactor

.gitignore

@@ -1,3 +1,5 @@
 __pycache__
+installer
+installer.tar
 dist
 .idea/*

Developer Console.cmd

@@ -1,15 +0,0 @@
-@echo off
-
-echo "Opening Stable Diffusion UI - Developer Console.." & echo.
-
-set SD_BASE_DIR=%cd%
-set MAMBA_ROOT_PREFIX=%SD_BASE_DIR%\env\mamba
-set INSTALL_ENV_DIR=%SD_BASE_DIR%\env\installer_env
-set PROJECT_ENV_DIR=%SD_BASE_DIR%\env\project_env
-
-call "%MAMBA_ROOT_PREFIX%\condabin\mamba_hook.bat"
-
-call micromamba activate "%INSTALL_ENV_DIR%"
-call micromamba activate "%PROJECT_ENV_DIR%"
-
-cmd /k

How to install and run.txt

@@ -0,0 +1,24 @@
+Congrats on downloading Stable Diffusion UI, version 2!
+
+If you haven't downloaded Stable Diffusion UI yet, please download from https://github.com/cmdr2/stable-diffusion-ui#installation
+
+After downloading, to install please follow these instructions:
+
+For Windows:
+- Please double-click the "Start Stable Diffusion UI.cmd" file inside the "stable-diffusion-ui" folder.
+
+For Linux:
+- Please open a terminal, and go to the "stable-diffusion-ui" directory. Then run ./start.sh
+
+That file will automatically install everything. After that it will start the Stable Diffusion interface in a web browser.
+
+To start the UI in the future, please run the same command mentioned above.
+
+
+If you have any problems, please:
+1. Try the troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/wiki/Troubleshooting
+2. Or, seek help from the community at https://discord.com/invite/u9yhsFmEkB
+3. Or, file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues
+
+Thanks
+cmdr2 (and contributors to the project)

README BEFORE YOU RUN THIS.txt

@@ -0,0 +1,8 @@
+Hi there,
+
+What you have downloaded is meant for the developers of this project, not for users.
+
+If you only want to use the Stable Diffusion UI, you've downloaded the wrong file.
+Please download and follow the instructions at https://github.com/cmdr2/stable-diffusion-ui#installation
+
+Thanks

README.md

@@ -8,7 +8,7 @@
 
 [![Discord Server](https://img.shields.io/discord/1014774730907209781?label=Discord)](https://discord.com/invite/u9yhsFmEkB) (for support, and development discussion) | [Troubleshooting guide for common problems](Troubleshooting.md)
 
-️‍🔥🎉 **New!** Use Custom Weights, Task Queue, Negative Prompt, Live Preview, More Samplers, In-Painting, Face Correction (GFPGAN) and Upscaling (RealESRGAN) have been added!
+️‍🔥🎉 **New!** Live Preview, More Samplers, In-Painting, Face Correction (GFPGAN) and Upscaling (RealESRGAN) have been added!
 
 This distribution currently uses Stable Diffusion 1.4. Once the model for 1.5 becomes publicly available, the model in this distribution will be updated.
 
@@ -17,9 +17,6 @@ This distribution currently uses Stable Diffusion 1.4. Once the model for 1.5 be
 - **Face Correction (GFPGAN) and Upscaling (RealESRGAN)**
 - **In-Painting**
 - **Live Preview**: See the image as the AI is drawing it
-- **Task Queue**: Queue up all your ideas, without waiting for the current task to finish
-- **Custom Weights**: Use your own `.ckpt` file, by placing it inside the `stable-diffusion` folder (rename it to `custom-model.ckpt`)
-- **Negative Prompt**: Specify aspects of the image to *remove*.
 - **Lots of Samplers:** ddim, plms, heun, euler, euler_a, dpm2, dpm2_a, lms
 - **Image Modifiers**: A library of *modifier tags* like *"Realistic"*, *"Pencil Sketch"*, *"ArtStation"* etc. Experiment with various styles quickly.
 - **New UI**: with cleaner design

Start Stable Diffusion UI.cmd

@@ -1,25 +0,0 @@
-@echo off
-
-echo. & echo "Stable Diffusion UI - v2.5" & echo.
-
-set PATH=C:\Windows\System32;%PATH%
-
-set SD_BASE_DIR=%cd%
-
-@rem Confirm or change the installation dir
-call installer\bootstrap\check-install-dir.bat
-
-@rem set the vars again, if the installer dir has changed
-set SD_BASE_DIR=%cd%
-
-echo Working in %SD_BASE_DIR%
-
-@rem Setup the packages required for the installer
-call installer\bootstrap\bootstrap.bat
-
-@rem Test the bootstrap
-call git --version
-call python --version
-
-@rem Download the rest of the installer and UI
-call installer\installer\start.bat

Troubleshooting.md

@@ -9,11 +9,6 @@ Additionally, a common reason for this error is that you're using an initial ima
 
 Also try generating smaller sized images.
 
-## basicsr module not found
-For Windows: Please download and extract basicsr from [here](https://github.com/cmdr2/stable-diffusion-ui/releases/download/v2.16/basicsr-win64.zip), and place the `basicsr` folder inside the `stable-diffusion-ui\stable-diffusion\env\lib\site-packages` folder. Then run the `Start Stable Diffusion UI.cmd` file again.
-
-For Linux: Please contact on the [discord server](https://discord.com/invite/u9yhsFmEkB).
-
 ## No ldm found, or antlr4 or any other missing module, or ClobberError: This transaction has incompatible packages due to a shared path
 On Windows, please ensure that you had placed the `stable-diffusion-ui` folder after unzipping to the root of C: or D: (or any drive). For e.g. `C:\stable-diffusion-ui`. **Note:** This has to be done **before** you start the installation process. If you have already installed (and are facing this error), please delete the installed folder, and start fresh by unzipping and placing the folder at the top of your drive.
 
@@ -49,27 +44,3 @@ After this, you can access the server at `http://localhost:1337` (where 1337 is
 Please ensure that you have an NVIDIA GPU and the latest [NVIDIA driver](http://www.nvidia.com/Download/index.aspx), and that you've installed [nvidia-container-toolkit](https://stackoverflow.com/a/58432877).
 
 Also, if you are using WSL (Windows), please ensure you have the latest WSL kernel by running `wsl --shutdown` and then `wsl --update`. (Thanks [AndrWeisR](https://github.com/AndrWeisR))
-
-# For support queries
-## Entering a conda environment in an existing installation
-This will give you an activated conda environment in the terminal, so you can run commands and force-install any packages, if required.
-
-Users don't need to have the Anaconda Prompt installed to do this anymore, since the installer bundles a portable version of conda inside it. Just follow these steps.
-
-**Windows:**
-1. Open the terminal: Press Win+R, type "cmd", and press "Run"
-2. Type `cd C:\stable-diffusion-ui` and press enter (or wherever you've installed it)
-3. Type `installer\Scripts\activate.bat` and press enter
-4. Type `cd stable-diffusion` and press enter
-5. Type `conda activate .\env` and press enter
-6. Type `python --version` and press enter. You should see 3.8.5.
-
-**Linux:**
-1. Open the terminal
-2. Type `cd /path/to/stable-diffusion-ui` and press enter
-3. Type `installer/bin/activate` and press enter
-4. Type `cd stable-diffusion` and press enter
-5. Type `conda activate ./env` and press enter
-6. Type `python --version` and press enter. You should see 3.8.5.
-
-This will give you an activated conda environment. To confirm, type `python --version` and press enter. You should see 3.8.5.

build.bat

@@ -0,0 +1,47 @@
+@echo off
+
+@echo "Hi there, what you are running is meant for the developers of this project, not for users." & echo.
+@echo "If you only want to use the Stable Diffusion UI, you've downloaded the wrong file."
+@echo "Please download and follow the instructions at https://github.com/cmdr2/stable-diffusion-ui#installation" & echo.
+@echo "If you are actually a developer of this project, please type Y and press enter" & echo.
+
+set /p answer=Are you a developer of this project (Y/N)?
+if /i "%answer:~,1%" NEQ "Y" exit /b
+
+@set PYTHONNOUSERSITE=1
+
+@mkdir dist\stable-diffusion-ui
+
+@echo "Downloading components for the installer.."
+
+@call conda env create --prefix installer -f environment.yaml
+@call conda activate .\installer
+
+@echo "Creating a distributable package.."
+
+@call conda install -c conda-forge -y conda-pack
+@call conda pack --n-threads -1 --prefix installer --format tar
+
+@cd dist\stable-diffusion-ui
+@mkdir installer
+
+@call tar -xf ..\..\installer.tar -C installer
+
+@mkdir scripts
+
+@copy ..\..\scripts\on_env_start.bat scripts\
+@copy "..\..\scripts\Start Stable Diffusion UI.cmd" .
+@copy ..\..\LICENSE .
+@copy "..\..\CreativeML Open RAIL-M License" .
+@copy "..\..\How to install and run.txt" .
+@echo. > scripts\install_status.txt
+
+@echo "Build ready. Zip the 'dist\stable-diffusion-ui' folder."
+
+@echo "Cleaning up.."
+
+@cd ..\..
+
+@rmdir /s /q installer
+
+@del installer.tar

build.sh

@@ -0,0 +1,55 @@
+#!/bin/bash
+
+printf "Hi there, what you are running is meant for the developers of this project, not for users.\n\n"
+printf "If you only want to use the Stable Diffusion UI, you've downloaded the wrong file.\n"
+printf "Please download and follow the instructions at https://github.com/cmdr2/stable-diffusion-ui#installation\n\n"
+printf "If you are actually a developer of this project, please type Y and press enter\n\n"
+
+read -p "Are you a developer of this project (Y/N) " yn
+case $yn in
+    [Yy]* ) ;;
+    * ) exit;;
+esac
+
+export PYTHONNOUSERSITE=1
+
+mkdir -p dist/stable-diffusion-ui
+
+echo "Downloading components for the installer.."
+
+source ~/miniconda3/etc/profile.d/conda.sh
+
+conda install -c conda-forge -y conda-pack
+
+conda env create --prefix installer -f environment.yaml
+conda activate ./installer
+
+echo "Creating a distributable package.."
+
+conda pack --n-threads -1 --prefix installer --format tar
+
+cd dist/stable-diffusion-ui
+mkdir installer
+
+tar -xf ../../installer.tar -C installer
+
+mkdir scripts
+
+cp ../../scripts/on_env_start.sh scripts/
+cp ../../scripts/start.sh .
+cp ../../LICENSE .
+cp "../../CreativeML Open RAIL-M License" .
+cp "../../How to install and run.txt" .
+echo "" > scripts/install_status.txt
+
+chmod u+x start.sh
+
+echo "Build ready. Zip the 'dist/stable-diffusion-ui' folder."
+
+echo "Cleaning up.."
+
+cd ../..
+
+rm -rf installer
+
+rm installer.tar

developer_console.sh

@@ -1,18 +0,0 @@
-#!/bin/bash
-
-if [ "$0" == "bash" ]; then
-  echo "Opening Stable Diffusion UI - Developer Console.."
-  echo ""
-
-  export SD_BASE_DIR=`pwd`
-  export MAMBA_ROOT_PREFIX="$SD_BASE_DIR/env/mamba"
-  export INSTALL_ENV_DIR="$SD_BASE_DIR/env/installer_env"
-  export PROJECT_ENV_DIR="$SD_BASE_DIR/env/project_env"
-
-  eval "$($MAMBA_ROOT_PREFIX/micromamba shell hook -s posix)"
-
-  micromamba activate "$INSTALL_ENV_DIR"
-  micromamba activate "$PROJECT_ENV_DIR"
-else
-  bash --init-file developer_console.sh
-fi

engine/runtime.py

@@ -1,658 +0,0 @@
-import json
-import os, re
-import traceback
-import torch
-import numpy as np
-from omegaconf import OmegaConf
-from PIL import Image, ImageOps
-from tqdm import tqdm, trange
-from itertools import islice
-from einops import rearrange
-import time
-from pytorch_lightning import seed_everything
-from torch import autocast
-from contextlib import nullcontext
-from einops import rearrange, repeat
-from ldm.util import instantiate_from_config
-from optimizedSD.optimUtils import split_weighted_subprompts
-from transformers import logging
-
-from gfpgan import GFPGANer
-from basicsr.archs.rrdbnet_arch import RRDBNet
-from realesrgan import RealESRGANer
-
-import uuid
-
-logging.set_verbosity_error()
-
-# consts
-config_yaml = "optimizedSD/v1-inference.yaml"
-filename_regex = re.compile('[^a-zA-Z0-9]')
-
-# api stuff
-from . import Request, Response, Image as ResponseImage
-import base64
-from io import BytesIO
-#from colorama import Fore
-
-# local
-stop_processing = False
-temp_images = {}
-
-ckpt_file = None
-gfpgan_file = None
-real_esrgan_file = None
-
-model = None
-modelCS = None
-modelFS = None
-model_gfpgan = None
-model_real_esrgan = None
-
-model_is_half = False
-model_fs_is_half = False
-device = None
-unet_bs = 1
-precision = 'autocast'
-sampler_plms = None
-sampler_ddim = None
-
-has_valid_gpu = False
-force_full_precision = False
-try:
-    gpu = torch.cuda.current_device()
-    gpu_name = torch.cuda.get_device_name(gpu)
-    print('GPU detected: ', gpu_name)
-
-    force_full_precision = ('nvidia' in gpu_name.lower() or 'geforce' in gpu_name.lower()) and (' 1660' in gpu_name or ' 1650' in gpu_name) # otherwise these NVIDIA cards create green images
-    if force_full_precision:
-        print('forcing full precision on NVIDIA 16xx cards, to avoid green images. GPU detected: ', gpu_name)
-
-    mem_free, mem_total = torch.cuda.mem_get_info(gpu)
-    mem_total /= float(10**9)
-    if mem_total < 3.0:
-        print("GPUs with less than 3 GB of VRAM are not compatible with Stable Diffusion")
-        raise Exception()
-
-    has_valid_gpu = True
-except:
-    print('WARNING: No compatible GPU found. Using the CPU, but this will be very slow!')
-    pass
-
-def load_model_ckpt(ckpt_to_use, device_to_use='cuda', turbo=False, unet_bs_to_use=1, precision_to_use='autocast', half_model_fs=False):
-    global ckpt_file, model, modelCS, modelFS, model_is_half, device, unet_bs, precision, model_fs_is_half
-
-    ckpt_file = ckpt_to_use
-    device = device_to_use if has_valid_gpu else 'cpu'
-    precision = precision_to_use if not force_full_precision else 'full'
-    unet_bs = unet_bs_to_use
-
-    if device == 'cpu':
-        precision = 'full'
-
-    sd = load_model_from_config(f"{ckpt_file}.ckpt")
-    li, lo = [], []
-    for key, value in sd.items():
-        sp = key.split(".")
-        if (sp[0]) == "model":
-            if "input_blocks" in sp:
-                li.append(key)
-            elif "middle_block" in sp:
-                li.append(key)
-            elif "time_embed" in sp:
-                li.append(key)
-            else:
-                lo.append(key)
-    for key in li:
-        sd["model1." + key[6:]] = sd.pop(key)
-    for key in lo:
-        sd["model2." + key[6:]] = sd.pop(key)
-
-    config = OmegaConf.load(f"{config_yaml}")
-
-    model = instantiate_from_config(config.modelUNet)
-    _, _ = model.load_state_dict(sd, strict=False)
-    model.eval()
-    model.cdevice = device
-    model.unet_bs = unet_bs
-    model.turbo = turbo
-
-    modelCS = instantiate_from_config(config.modelCondStage)
-    _, _ = modelCS.load_state_dict(sd, strict=False)
-    modelCS.eval()
-    modelCS.cond_stage_model.device = device
-
-    modelFS = instantiate_from_config(config.modelFirstStage)
-    _, _ = modelFS.load_state_dict(sd, strict=False)
-    modelFS.eval()
-    del sd
-
-    if device != "cpu" and precision == "autocast":
-        model.half()
-        modelCS.half()
-        model_is_half = True
-    else:
-        model_is_half = False
-
-    if half_model_fs:
-        modelFS.half()
-        model_fs_is_half = True
-    else:
-        model_fs_is_half = False
-
-    print('loaded ', ckpt_file, 'to', device, 'precision', precision)
-
-def load_model_gfpgan(gfpgan_to_use):
-    global gfpgan_file, model_gfpgan
-
-    if gfpgan_to_use is None:
-        return
-
-    gfpgan_file = gfpgan_to_use
-    model_path = gfpgan_to_use + ".pth"
-
-    if device == 'cpu':
-        model_gfpgan = GFPGANer(model_path=model_path, upscale=1, arch='clean', channel_multiplier=2, bg_upsampler=None, device=torch.device('cpu'))
-    else:
-        model_gfpgan = GFPGANer(model_path=model_path, upscale=1, arch='clean', channel_multiplier=2, bg_upsampler=None, device=torch.device('cuda'))
-
-    print('loaded ', gfpgan_to_use, 'to', device, 'precision', precision)
-
-def load_model_real_esrgan(real_esrgan_to_use):
-    global real_esrgan_file, model_real_esrgan
-
-    if real_esrgan_to_use is None:
-        return
-
-    real_esrgan_file = real_esrgan_to_use
-    model_path = real_esrgan_to_use + ".pth"
-
-    RealESRGAN_models = {
-        'RealESRGAN_x4plus': RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4),
-        'RealESRGAN_x4plus_anime_6B': RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=6, num_grow_ch=32, scale=4)
-    }
-
-    model_to_use = RealESRGAN_models[real_esrgan_to_use]
-
-    if device == 'cpu':
-        model_real_esrgan = RealESRGANer(scale=2, model_path=model_path, model=model_to_use, pre_pad=0, half=False) # cpu does not support half
-        model_real_esrgan.device = torch.device('cpu')
-        model_real_esrgan.model.to('cpu')
-    else:
-        model_real_esrgan = RealESRGANer(scale=2, model_path=model_path, model=model_to_use, pre_pad=0, half=model_is_half)
-
-    model_real_esrgan.model.name = real_esrgan_to_use
-
-    print('loaded ', real_esrgan_to_use, 'to', device, 'precision', precision)
-
-def mk_img(req: Request):
-    try:
-        yield from do_mk_img(req)
-    except Exception as e:
-        print(traceback.format_exc())
-
-        gc()
-
-        if device != "cpu":
-            modelFS.to("cpu")
-            modelCS.to("cpu")
-
-            model.model1.to("cpu")
-            model.model2.to("cpu")
-
-        gc()
-
-        yield json.dumps({
-            "status": 'failed',
-            "detail": str(e)
-        })
-
-def do_mk_img(req: Request):
-    global model, modelCS, modelFS, device
-    global model_gfpgan, model_real_esrgan
-    global stop_processing
-
-    stop_processing = False
-
-    res = Response()
-    res.request = req
-    res.images = []
-
-    temp_images.clear()
-
-    model.turbo = req.turbo
-    if req.use_cpu:
-        if device != 'cpu':
-            device = 'cpu'
-
-            if model_is_half:
-                del model, modelCS, modelFS
-                load_model_ckpt(ckpt_file, device)
-
-            load_model_gfpgan(gfpgan_file)
-            load_model_real_esrgan(real_esrgan_file)
-    else:
-        if has_valid_gpu:
-            prev_device = device
-            device = 'cuda'
-
-            if (precision == 'autocast' and (req.use_full_precision or not model_is_half)) or \
-                (precision == 'full' and not req.use_full_precision and not force_full_precision) or \
-                (req.init_image is None and model_fs_is_half) or \
-                (req.init_image is not None and not model_fs_is_half and not force_full_precision):
-
-                del model, modelCS, modelFS
-                load_model_ckpt(ckpt_file, device, req.turbo, unet_bs, ('full' if req.use_full_precision else 'autocast'), half_model_fs=(req.init_image is not None and not req.use_full_precision))
-
-                if prev_device != device:
-                    load_model_gfpgan(gfpgan_file)
-                    load_model_real_esrgan(real_esrgan_file)
-
-    if req.use_face_correction != gfpgan_file:
-        load_model_gfpgan(req.use_face_correction)
-
-    if req.use_upscale != real_esrgan_file:
-        load_model_real_esrgan(req.use_upscale)
-
-    model.cdevice = device
-    modelCS.cond_stage_model.device = device
-
-    opt_prompt = req.prompt
-    opt_seed = req.seed
-    opt_n_samples = req.num_outputs
-    opt_n_iter = 1
-    opt_scale = req.guidance_scale
-    opt_C = 4
-    opt_H = req.height
-    opt_W = req.width
-    opt_f = 8
-    opt_ddim_steps = req.num_inference_steps
-    opt_ddim_eta = 0.0
-    opt_strength = req.prompt_strength
-    opt_save_to_disk_path = req.save_to_disk_path
-    opt_init_img = req.init_image
-    opt_use_face_correction = req.use_face_correction
-    opt_use_upscale = req.use_upscale
-    opt_show_only_filtered = req.show_only_filtered_image
-    opt_format = 'png'
-    opt_sampler_name = req.sampler
-
-    print(req.to_string(), '\n    device', device)
-
-    print('\n\n    Using precision:', precision)
-
-    seed_everything(opt_seed)
-
-    batch_size = opt_n_samples
-    prompt = opt_prompt
-    assert prompt is not None
-    data = [batch_size * [prompt]]
-
-    if precision == "autocast" and device != "cpu":
-        precision_scope = autocast
-    else:
-        precision_scope = nullcontext
-
-    mask = None
-
-    if req.init_image is None:
-        handler = _txt2img
-
-        init_latent = None
-        t_enc = None
-    else:
-        handler = _img2img
-
-        init_image = load_img(req.init_image, opt_W, opt_H)
-        init_image = init_image.to(device)
-
-        if device != "cpu" and precision == "autocast":
-            init_image = init_image.half()
-
-        modelFS.to(device)
-
-        init_image = repeat(init_image, '1 ... -> b ...', b=batch_size)
-        init_latent = modelFS.get_first_stage_encoding(modelFS.encode_first_stage(init_image))  # move to latent space
-
-        if req.mask is not None:
-            mask = load_mask(req.mask, opt_W, opt_H, init_latent.shape[2], init_latent.shape[3], True).to(device)
-            mask = mask[0][0].unsqueeze(0).repeat(4, 1, 1).unsqueeze(0)
-            mask = repeat(mask, '1 ... -> b ...', b=batch_size)
-
-            if device != "cpu" and precision == "autocast":
-                mask = mask.half()
-
-        move_fs_to_cpu()
-
-        assert 0. <= opt_strength <= 1., 'can only work with strength in [0.0, 1.0]'
-        t_enc = int(opt_strength * opt_ddim_steps)
-        print(f"target t_enc is {t_enc} steps")
-
-    if opt_save_to_disk_path is not None:
-        session_out_path = os.path.join(opt_save_to_disk_path, req.session_id)
-        os.makedirs(session_out_path, exist_ok=True)
-    else:
-        session_out_path = None
-
-    seeds = ""
-    with torch.no_grad():
-        for n in trange(opt_n_iter, desc="Sampling"):
-            for prompts in tqdm(data, desc="data"):
-
-                with precision_scope("cuda"):
-                    modelCS.to(device)
-                    uc = None
-                    if opt_scale != 1.0:
-                        uc = modelCS.get_learned_conditioning(batch_size * [req.negative_prompt])
-                    if isinstance(prompts, tuple):
-                        prompts = list(prompts)
-
-                    subprompts, weights = split_weighted_subprompts(prompts[0])
-                    if len(subprompts) > 1:
-                        c = torch.zeros_like(uc)
-                        totalWeight = sum(weights)
-                        # normalize each "sub prompt" and add it
-                        for i in range(len(subprompts)):
-                            weight = weights[i]
-                            # if not skip_normalize:
-                            weight = weight / totalWeight
-                            c = torch.add(c, modelCS.get_learned_conditioning(subprompts[i]), alpha=weight)
-                    else:
-                        c = modelCS.get_learned_conditioning(prompts)
-
-                    modelFS.to(device)
-
-                    partial_x_samples = None
-                    def img_callback(x_samples, i):
-                        nonlocal partial_x_samples
-
-                        partial_x_samples = x_samples
-
-                        if req.stream_progress_updates:
-                            n_steps = opt_ddim_steps if req.init_image is None else t_enc
-                            progress = {"step": i, "total_steps": n_steps}
-
-                            if req.stream_image_progress and i % 5 == 0:
-                                partial_images = []
-
-                                for i in range(batch_size):
-                                    x_samples_ddim = modelFS.decode_first_stage(x_samples[i].unsqueeze(0))
-                                    x_sample = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
-                                    x_sample = 255.0 * rearrange(x_sample[0].cpu().numpy(), "c h w -> h w c")
-                                    x_sample = x_sample.astype(np.uint8)
-                                    img = Image.fromarray(x_sample)
-                                    buf = BytesIO()
-                                    img.save(buf, format='JPEG')
-                                    buf.seek(0)
-
-                                    del img, x_sample, x_samples_ddim
-                                    # don't delete x_samples, it is used in the code that called this callback
-
-                                    temp_images[str(req.session_id) + '/' + str(i)] = buf
-                                    partial_images.append({'path': f'/image/tmp/{req.session_id}/{i}'})
-
-                                progress['output'] = partial_images
-
-                            yield json.dumps(progress)
-
-                        if stop_processing:
-                            raise UserInitiatedStop("User requested that we stop processing")
-
-                    # run the handler
-                    try:
-                        if handler == _txt2img:
-                            x_samples = _txt2img(opt_W, opt_H, opt_n_samples, opt_ddim_steps, opt_scale, None, opt_C, opt_f, opt_ddim_eta, c, uc, opt_seed, img_callback, mask, opt_sampler_name)
-                        else:
-                            x_samples = _img2img(init_latent, t_enc, batch_size, opt_scale, c, uc, opt_ddim_steps, opt_ddim_eta, opt_seed, img_callback, mask)
-
-                        yield from x_samples
-
-                        x_samples = partial_x_samples
-                    except UserInitiatedStop:
-                        if partial_x_samples is None:
-                            continue
-
-                        x_samples = partial_x_samples
-
-                    print("saving images")
-                    for i in range(batch_size):
-
-                        x_samples_ddim = modelFS.decode_first_stage(x_samples[i].unsqueeze(0))
-                        x_sample = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
-                        x_sample = 255.0 * rearrange(x_sample[0].cpu().numpy(), "c h w -> h w c")
-                        x_sample = x_sample.astype(np.uint8)
-                        img = Image.fromarray(x_sample)
-
-                        has_filters =   (opt_use_face_correction is not None and opt_use_face_correction.startswith('GFPGAN')) or \
-                                        (opt_use_upscale is not None and opt_use_upscale.startswith('RealESRGAN'))
-
-                        return_orig_img = not has_filters or not opt_show_only_filtered
-
-                        if stop_processing:
-                            return_orig_img = True
-
-                        if opt_save_to_disk_path is not None:
-                            prompt_flattened = filename_regex.sub('_', prompts[0])
-                            prompt_flattened = prompt_flattened[:50]
-
-                            img_id = str(uuid.uuid4())[-8:]
-
-                            file_path = f"{prompt_flattened}_{img_id}"
-                            img_out_path = os.path.join(session_out_path, f"{file_path}.{opt_format}")
-                            meta_out_path = os.path.join(session_out_path, f"{file_path}.txt")
-
-                            if return_orig_img:
-                                save_image(img, img_out_path)
-
-                            save_metadata(meta_out_path, prompts, opt_seed, opt_W, opt_H, opt_ddim_steps, opt_scale, opt_strength, opt_use_face_correction, opt_use_upscale, opt_sampler_name, req.negative_prompt)
-
-                        if return_orig_img:
-                            img_data = img_to_base64_str(img)
-                            res_image_orig = ResponseImage(data=img_data, seed=opt_seed)
-                            res.images.append(res_image_orig)
-
-                            if opt_save_to_disk_path is not None:
-                                res_image_orig.path_abs = img_out_path
-
-                        del img
-
-                        if has_filters and not stop_processing:
-                            print('Applying filters..')
-
-                            gc()
-                            filters_applied = []
-
-                            if opt_use_face_correction:
-                                _, _, output = model_gfpgan.enhance(x_sample[:,:,::-1], has_aligned=False, only_center_face=False, paste_back=True)
-                                x_sample = output[:,:,::-1]
-                                filters_applied.append(opt_use_face_correction)
-
-                            if opt_use_upscale:
-                                output, _ = model_real_esrgan.enhance(x_sample[:,:,::-1])
-                                x_sample = output[:,:,::-1]
-                                filters_applied.append(opt_use_upscale)
-
-                            filtered_image = Image.fromarray(x_sample)
-
-                            filtered_img_data = img_to_base64_str(filtered_image)
-                            res_image_filtered = ResponseImage(data=filtered_img_data, seed=opt_seed)
-                            res.images.append(res_image_filtered)
-
-                            filters_applied = "_".join(filters_applied)
-
-                            if opt_save_to_disk_path is not None:
-                                filtered_img_out_path = os.path.join(session_out_path, f"{file_path}_{filters_applied}.{opt_format}")
-                                save_image(filtered_image, filtered_img_out_path)
-                                res_image_filtered.path_abs = filtered_img_out_path
-
-                            del filtered_image
-
-                        seeds += str(opt_seed) + ","
-                        opt_seed += 1
-
-                    move_fs_to_cpu()
-                    gc()
-                    del x_samples, x_samples_ddim, x_sample
-                    print("memory_final = ", torch.cuda.memory_allocated() / 1e6)
-
-    print('Task completed')
-
-    yield json.dumps(res.json())
-
-def save_image(img, img_out_path):
-    try:
-        img.save(img_out_path)
-    except:
-        print('could not save the file', traceback.format_exc())
-
-def save_metadata(meta_out_path, prompts, opt_seed, opt_W, opt_H, opt_ddim_steps, opt_scale, opt_prompt_strength, opt_correct_face, opt_upscale, sampler_name, negative_prompt):
-    metadata = f"{prompts[0]}\nWidth: {opt_W}\nHeight: {opt_H}\nSeed: {opt_seed}\nSteps: {opt_ddim_steps}\nGuidance Scale: {opt_scale}\nPrompt Strength: {opt_prompt_strength}\nUse Face Correction: {opt_correct_face}\nUse Upscaling: {opt_upscale}\nSampler: {sampler_name}\nNegative Prompt: {negative_prompt}"
-
-    try:
-        with open(meta_out_path, 'w') as f:
-            f.write(metadata)
-    except:
-        print('could not save the file', traceback.format_exc())
-
-def _txt2img(opt_W, opt_H, opt_n_samples, opt_ddim_steps, opt_scale, start_code, opt_C, opt_f, opt_ddim_eta, c, uc, opt_seed, img_callback, mask, sampler_name):
-    shape = [opt_n_samples, opt_C, opt_H // opt_f, opt_W // opt_f]
-
-    if device != "cpu":
-        mem = torch.cuda.memory_allocated() / 1e6
-        modelCS.to("cpu")
-        while torch.cuda.memory_allocated() / 1e6 >= mem:
-            time.sleep(1)
-
-    if sampler_name == 'ddim':
-        model.make_schedule(ddim_num_steps=opt_ddim_steps, ddim_eta=opt_ddim_eta, verbose=False)
-
-    samples_ddim = model.sample(
-        S=opt_ddim_steps,
-        conditioning=c,
-        seed=opt_seed,
-        shape=shape,
-        verbose=False,
-        unconditional_guidance_scale=opt_scale,
-        unconditional_conditioning=uc,
-        eta=opt_ddim_eta,
-        x_T=start_code,
-        img_callback=img_callback,
-        mask=mask,
-        sampler = sampler_name,
-    )
-
-    yield from samples_ddim
-
-def _img2img(init_latent, t_enc, batch_size, opt_scale, c, uc, opt_ddim_steps, opt_ddim_eta, opt_seed, img_callback, mask):
-    # encode (scaled latent)
-    z_enc = model.stochastic_encode(
-        init_latent,
-        torch.tensor([t_enc] * batch_size).to(device),
-        opt_seed,
-        opt_ddim_eta,
-        opt_ddim_steps,
-    )
-    x_T = None if mask is None else init_latent
-
-    # decode it
-    samples_ddim = model.sample(
-        t_enc,
-        c,
-        z_enc,
-        unconditional_guidance_scale=opt_scale,
-        unconditional_conditioning=uc,
-        img_callback=img_callback,
-        mask=mask,
-        x_T=x_T,
-        sampler = 'ddim'
-    )
-
-    yield from samples_ddim
-
-def move_fs_to_cpu():
-    if device != "cpu":
-        mem = torch.cuda.memory_allocated() / 1e6
-        modelFS.to("cpu")
-        while torch.cuda.memory_allocated() / 1e6 >= mem:
-            time.sleep(1)
-
-def gc():
-    if device == 'cpu':
-        return
-
-    torch.cuda.empty_cache()
-    torch.cuda.ipc_collect()
-
-# internal
-
-def chunk(it, size):
-    it = iter(it)
-    return iter(lambda: tuple(islice(it, size)), ())
-
-
-def load_model_from_config(ckpt, verbose=False):
-    print(f"Loading model from {ckpt}")
-    pl_sd = torch.load(ckpt, map_location="cpu")
-    if "global_step" in pl_sd:
-        print(f"Global Step: {pl_sd['global_step']}")
-    sd = pl_sd["state_dict"]
-    return sd
-
-# utils
-class UserInitiatedStop(Exception):
-    pass
-
-def load_img(img_str, w0, h0):
-    image = base64_str_to_img(img_str).convert("RGB")
-    w, h = image.size
-    print(f"loaded input image of size ({w}, {h}) from base64")
-    if h0 is not None and w0 is not None:
-        h, w = h0, w0
-
-    w, h = map(lambda x: x - x % 64, (w, h))  # resize to integer multiple of 64
-    image = image.resize((w, h), resample=Image.Resampling.LANCZOS)
-    image = np.array(image).astype(np.float32) / 255.0
-    image = image[None].transpose(0, 3, 1, 2)
-    image = torch.from_numpy(image)
-    return 2.*image - 1.
-
-def load_mask(mask_str, h0, w0, newH, newW, invert=False):
-    image = base64_str_to_img(mask_str).convert("RGB")
-    w, h = image.size
-    print(f"loaded input mask of size ({w}, {h})")
-
-    if invert:
-        print("inverted")
-        image = ImageOps.invert(image)
-        # where_0, where_1 = np.where(image == 0), np.where(image == 255)
-        # image[where_0], image[where_1] = 255, 0
-
-    if h0 is not None and w0 is not None:
-        h, w = h0, w0
-
-    w, h = map(lambda x: x - x % 64, (w, h))  # resize to integer multiple of 64
-
-    print(f"New mask size ({w}, {h})")
-    image = image.resize((newW, newH), resample=Image.Resampling.LANCZOS)
-    image = np.array(image)
-
-    image = image.astype(np.float32) / 255.0
-    image = image[None].transpose(0, 3, 1, 2)
-    image = torch.from_numpy(image)
-    return image
-
-# https://stackoverflow.com/a/61114178
-def img_to_base64_str(img):
-    buffered = BytesIO()
-    img.save(buffered, format="PNG")
-    buffered.seek(0)
-    img_byte = buffered.getvalue()
-    img_str = "data:image/png;base64," + base64.b64encode(img_byte).decode()
-    return img_str
-
-def base64_str_to_img(img_str):
-    img_str = img_str[len("data:image/png;base64,"):]
-    data = base64.b64decode(img_str)
-    buffered = BytesIO(data)
-    img = Image.open(buffered)
-    return img

engine/server.py

@@ -1,237 +0,0 @@
-import json
-import traceback
-
-import sys
-import os
-
-SCRIPT_DIR = os.getcwd()
-print('started in ', SCRIPT_DIR)
-
-SD_UI_DIR = os.getenv('SD_UI_PATH', None)
-sys.path.append(os.path.dirname(SD_UI_DIR))
-
-CONFIG_DIR = os.path.join(SD_UI_DIR, '..', 'scripts')
-
-OUTPUT_DIRNAME = "Stable Diffusion UI" # in the user's home folder
-
-from fastapi import FastAPI, HTTPException
-from fastapi.staticfiles import StaticFiles
-from starlette.responses import FileResponse, StreamingResponse
-from pydantic import BaseModel
-import logging
-
-from sd_internal import Request, Response
-
-app = FastAPI()
-
-model_loaded = False
-model_is_loading = False
-
-modifiers_cache = None
-outpath = os.path.join(os.path.expanduser("~"), OUTPUT_DIRNAME)
-
-# don't show access log entries for URLs that start with the given prefix
-ACCESS_LOG_SUPPRESS_PATH_PREFIXES = ['/ping', '/modifier-thumbnails']
-
-app.mount('/media', StaticFiles(directory=os.path.join(SD_UI_DIR, 'media/')), name="media")
-
-# defaults from https://huggingface.co/blog/stable_diffusion
-class ImageRequest(BaseModel):
-    session_id: str = "session"
-    prompt: str = ""
-    negative_prompt: str = ""
-    init_image: str = None # base64
-    mask: str = None # base64
-    num_outputs: int = 1
-    num_inference_steps: int = 50
-    guidance_scale: float = 7.5
-    width: int = 512
-    height: int = 512
-    seed: int = 42
-    prompt_strength: float = 0.8
-    sampler: str = None # "ddim", "plms", "heun", "euler", "euler_a", "dpm2", "dpm2_a", "lms"
-    # allow_nsfw: bool = False
-    save_to_disk_path: str = None
-    turbo: bool = True
-    use_cpu: bool = False
-    use_full_precision: bool = False
-    use_face_correction: str = None # or "GFPGANv1.3"
-    use_upscale: str = None # or "RealESRGAN_x4plus" or "RealESRGAN_x4plus_anime_6B"
-    show_only_filtered_image: bool = False
-
-    stream_progress_updates: bool = False
-    stream_image_progress: bool = False
-
-class SetAppConfigRequest(BaseModel):
-    update_branch: str = "main"
-
-@app.get('/')
-def read_root():
-    headers = {"Cache-Control": "no-cache, no-store, must-revalidate", "Pragma": "no-cache", "Expires": "0"}
-    return FileResponse(os.path.join(SD_UI_DIR, 'index.html'), headers=headers)
-
-@app.get('/ping')
-async def ping():
-    global model_loaded, model_is_loading
-
-    try:
-        if model_loaded:
-            return {'OK'}
-
-        if model_is_loading:
-            return {'ERROR'}
-
-        model_is_loading = True
-
-        from sd_internal import runtime
-
-        custom_weight_path = os.path.join(SCRIPT_DIR, 'custom-model.ckpt')
-        ckpt_to_use = "sd-v1-4" if not os.path.exists(custom_weight_path) else "custom-model"
-        runtime.load_model_ckpt(ckpt_to_use=ckpt_to_use)
-
-        model_loaded = True
-        model_is_loading = False
-
-        return {'OK'}
-    except Exception as e:
-        print(traceback.format_exc())
-        return HTTPException(status_code=500, detail=str(e))
-
-@app.post('/image')
-def image(req : ImageRequest):
-    from sd_internal import runtime
-
-    r = Request()
-    r.session_id = req.session_id
-    r.prompt = req.prompt
-    r.negative_prompt = req.negative_prompt
-    r.init_image = req.init_image
-    r.mask = req.mask
-    r.num_outputs = req.num_outputs
-    r.num_inference_steps = req.num_inference_steps
-    r.guidance_scale = req.guidance_scale
-    r.width = req.width
-    r.height = req.height
-    r.seed = req.seed
-    r.prompt_strength = req.prompt_strength
-    r.sampler = req.sampler
-    # r.allow_nsfw = req.allow_nsfw
-    r.turbo = req.turbo
-    r.use_cpu = req.use_cpu
-    r.use_full_precision = req.use_full_precision
-    r.save_to_disk_path = req.save_to_disk_path
-    r.use_upscale: str = req.use_upscale
-    r.use_face_correction = req.use_face_correction
-    r.show_only_filtered_image = req.show_only_filtered_image
-
-    r.stream_progress_updates = True # the underlying implementation only supports streaming
-    r.stream_image_progress = req.stream_image_progress
-
-    try:
-        if not req.stream_progress_updates:
-            r.stream_image_progress = False
-
-        res = runtime.mk_img(r)
-
-        if req.stream_progress_updates:
-            return StreamingResponse(res, media_type='application/json')
-        else: # compatibility mode: buffer the streaming responses, and return the last one
-            last_result = None
-
-            for result in res:
-                last_result = result
-
-            return json.loads(last_result)
-    except Exception as e:
-        print(traceback.format_exc())
-        return HTTPException(status_code=500, detail=str(e))
-
-@app.get('/image/stop')
-def stop():
-    try:
-        if model_is_loading:
-            return {'ERROR'}
-
-        from sd_internal import runtime
-        runtime.stop_processing = True
-
-        return {'OK'}
-    except Exception as e:
-        print(traceback.format_exc())
-        return HTTPException(status_code=500, detail=str(e))
-
-@app.get('/image/tmp/{session_id}/{img_id}')
-def get_image(session_id, img_id):
-    from sd_internal import runtime
-    buf = runtime.temp_images[session_id + '/' + img_id]
-    buf.seek(0)
-    return StreamingResponse(buf, media_type='image/jpeg')
-
-@app.post('/app_config')
-async def setAppConfig(req : SetAppConfigRequest):
-    try:
-        config = {
-            'update_branch': req.update_branch
-        }
-
-        config_json_str = json.dumps(config)
-        config_bat_str = f'@set update_branch={req.update_branch}'
-        config_sh_str = f'export update_branch={req.update_branch}'
-
-        config_json_path = os.path.join(CONFIG_DIR, 'config.json')
-        config_bat_path = os.path.join(CONFIG_DIR, 'config.bat')
-        config_sh_path = os.path.join(CONFIG_DIR, 'config.sh')
-
-        with open(config_json_path, 'w') as f:
-            f.write(config_json_str)
-
-        with open(config_bat_path, 'w') as f:
-            f.write(config_bat_str)
-
-        with open(config_sh_path, 'w') as f:
-            f.write(config_sh_str)
-
-        return {'OK'}
-    except Exception as e:
-        print(traceback.format_exc())
-        return HTTPException(status_code=500, detail=str(e))
-
-@app.get('/app_config')
-def getAppConfig():
-    try:
-        config_json_path = os.path.join(CONFIG_DIR, 'config.json')
-
-        if not os.path.exists(config_json_path):
-            return HTTPException(status_code=500, detail="No config file")
-
-        with open(config_json_path, 'r') as f:
-            config_json_str = f.read()
-            config = json.loads(config_json_str)
-            return config
-    except Exception as e:
-        print(traceback.format_exc())
-        return HTTPException(status_code=500, detail=str(e))
-
-@app.get('/modifiers.json')
-def read_modifiers():
-    headers = {"Cache-Control": "no-cache, no-store, must-revalidate", "Pragma": "no-cache", "Expires": "0"}
-    return FileResponse(os.path.join(SD_UI_DIR, 'modifiers.json'), headers=headers)
-
-@app.get('/output_dir')
-def read_home_dir():
-    return {outpath}
-
-# don't log certain requests
-class LogSuppressFilter(logging.Filter):
-    def filter(self, record: logging.LogRecord) -> bool:
-        path = record.getMessage()
-        for prefix in ACCESS_LOG_SUPPRESS_PATH_PREFIXES:
-            if path.find(prefix) != -1:
-                return False
-
-        return True
-
-logging.getLogger('uvicorn.access').addFilter(LogSuppressFilter())
-
-# start the browser ui
-import webbrowser; webbrowser.open('http://localhost:9000')

environment.yaml

@@ -3,5 +3,5 @@ channels:
   - defaults
   - conda-forge
 dependencies:
+  - conda
   - git
-  - python=3.10.5

installer/bootstrap/bootstrap.bat

@@ -1,34 +0,0 @@
-@echo off
-
-@rem This file initializes micromamba and activates the env.
-@rem A similar bootstrap file needs to exist for each platform (win, linux, macOS)
-@rem Ready to hand-over to the platform-independent installer after this (written in python).
-
-set MAMBA_ROOT_PREFIX=%SD_BASE_DIR%\env\mamba
-set INSTALL_ENV_DIR=%SD_BASE_DIR%\env\installer_env
-set INSTALLER_YAML_FILE=%SD_BASE_DIR%\installer\yaml\installer-environment.yaml
-set MICROMAMBA_BINARY_FILE=%SD_BASE_DIR%\installer\bin\micromamba_win_x64.exe
-
-@rem initialize the mamba dir
-if not exist "%MAMBA_ROOT_PREFIX%" mkdir "%MAMBA_ROOT_PREFIX%"
-
-copy "%MICROMAMBA_BINARY_FILE%" "%MAMBA_ROOT_PREFIX%\micromamba.exe"
-
-@rem test the mamba binary
-echo Micromamba version:
-call "%MAMBA_ROOT_PREFIX%\micromamba.exe" --version
-
-@rem run the shell hook
-if not exist "%MAMBA_ROOT_PREFIX%\Scripts" (
-    call "%MAMBA_ROOT_PREFIX%\micromamba.exe" shell hook --log-level 4 -s cmd.exe
-)
-
-call "%MAMBA_ROOT_PREFIX%\condabin\mamba_hook.bat"
-
-@rem create the installer env
-if not exist "%INSTALL_ENV_DIR%" (
-    call micromamba create -y --prefix "%INSTALL_ENV_DIR%" -f "%INSTALLER_YAML_FILE%"
-)
-
-@rem activate
-call micromamba activate "%INSTALL_ENV_DIR%"

installer/bootstrap/bootstrap.sh

@@ -1,44 +0,0 @@
-#!/bin/bash
-
-# This file initializes micromamba and activates the env.
-# A similar bootstrap file needs to exist for each platform (win, linux, macOS)
-# Ready to hand-over to the platform-independent installer after this (written in python).
-
-OS_NAME=$(uname -s)
-case "${OS_NAME}" in
-    Linux*)     OS_NAME="linux";;
-    Darwin*)    OS_NAME="mac";;
-    *)          echo "Unknown OS: $OS_NAME! This only runs on Linux or Mac" && exit
-esac
-
-OS_ARCH=$(uname -m)
-case "${OS_ARCH}" in
-    x86_64*)    OS_ARCH="x64";;
-    arm64*)     OS_ARCH="arm64";;
-    *)          echo "Unknown system architecture: $OS_ARCH! This only runs on x86_64 or arm64" && exit
-esac
-
-export MAMBA_ROOT_PREFIX=$SD_BASE_DIR/env/mamba
-INSTALL_ENV_DIR=$SD_BASE_DIR/env/installer_env
-INSTALLER_YAML_FILE=$SD_BASE_DIR/installer/yaml/installer-environment.yaml
-MICROMAMBA_BINARY_FILE=$SD_BASE_DIR/installer/bin/micromamba_${OS_NAME}_${OS_ARCH}
-
-# initialize the mamba dir
-mkdir -p "$MAMBA_ROOT_PREFIX"
-
-cp "$MICROMAMBA_BINARY_FILE" "$MAMBA_ROOT_PREFIX/micromamba"
-
-# test the mamba binary
-echo "Micromamba version:"
-"$MAMBA_ROOT_PREFIX/micromamba" --version
-
-# run the shell hook
-eval "$($MAMBA_ROOT_PREFIX/micromamba shell hook -s posix)"
-
-# create the installer env
-if [ ! -e "$INSTALL_ENV_DIR" ]; then
-    micromamba create -y --prefix "$INSTALL_ENV_DIR" -f "$INSTALLER_YAML_FILE"
-fi
-
-# activate
-micromamba activate "$INSTALL_ENV_DIR"

installer/bootstrap/check-install-dir.bat

@@ -1,21 +0,0 @@
-@echo off
-
-if exist "%SD_BASE_DIR%\env" exit /b
-
-set suggested_dir=%~d0\stable-diffusion-ui
-
-echo "Please install Stable Diffusion UI at the root of your drive. This avoids problems with path length limits in Windows." & echo.
-set /p answer="Press Enter to install at %suggested_dir%, or type 'c' (without quotes) to install at the current location (press enter or type 'c'): "
-
-if /i "%answer:~,1%" NEQ "c" (
-    if exist "%suggested_dir%" (
-        echo. & echo "Sorry, %suggested_dir% already exists! Cannot overwrite that folder!" & echo.
-        pause
-        exit
-    )
-
-    xcopy "%SD_BASE_DIR%" "%suggested_dir%" /s /i /Y /Q
-    echo Please run the %START_CMD_FILENAME% file inside %suggested_dir% . Do not use this folder anymore > "%SD_BASE_DIR%/READ_ME - DO_NOT_USE_THIS_FOLDER.txt"
-
-    cd %suggested_dir%
-)

installer/developer/enable_dev_mode.py

@@ -1,78 +0,0 @@
-import argparse
-import subprocess
-import sys
-import json
-import os
-import platform
-import shutil
-
-config_path = os.path.join('config.json')
-
-if not os.path.exists('LICENSE'):
-    print('Error: This script needs to be run from the root of the stable-diffusion-ui folder! Please cd to the correct folder, and run this again.')
-    exit(1)
-
-parser = argparse.ArgumentParser()
-
-parser.add_argument(
-    "--symlink_dir", type=str, default=None, help="the absolute path to the project git repository (to link to)"
-)
-opt = parser.parse_args()
-
-def run(cmd):
-    p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, shell=True)
-
-    for c in iter(lambda: p.stdout.read(1), b""):
-        sys.stdout.buffer.write(c)
-        sys.stdout.flush()
-
-    p.wait()
-
-    return p.returncode == 0
-
-def get_config():
-    if not os.path.exists(config_path):
-        return {}
-
-    with open(config_path, "r") as f:
-        return json.load(f)
-
-def save_config(config):
-    with open(config_path, "w") as f:
-        json.dump(config, f)
-
-# set the `is_developer_mode` flag to `true` in the config
-config = get_config()
-config['is_developer_mode'] = True
-save_config(config)
-
-print('set is_developer_mode=true in config.json')
-
-# make the symlink, if requested
-if opt.symlink_dir is not None:
-    if not os.path.exists(opt.symlink_dir):
-        print(f'Symlink directory "{opt.symlink_dir}" was not found! Are you sure it has been escaped correctly?')
-        exit(1)
-
-    installer_target_path = os.path.join(opt.symlink_dir, 'installer')
-    ui_target_path = os.path.join(opt.symlink_dir, 'ui')
-    engine_target_path = os.path.join(opt.symlink_dir, 'engine')
-
-    shutil.rmtree('installer', ignore_errors=True)
-    shutil.rmtree('ui', ignore_errors=True)
-    shutil.rmtree('engine', ignore_errors=True)
-
-    if not os.path.exists(ui_target_path) or not os.path.exists(installer_target_path) or not os.path.exists(engine_target_path):
-        print('The target symlink directory does not contain the required {ui, installer, engine} folders. Are you sure it is the correct git repo for the project?')
-        exit(1)
-
-    if platform.system() == 'Windows':
-        run(f'mklink /J "installer" "{installer_target_path}"')
-        run(f'mklink /J "ui" "{ui_target_path}"')
-        run(f'mklink /J "engine" "{engine_target_path}"')
-    elif platform.system() in ('Linux', 'Darwin'):
-        run(f'ln -s "{installer_target_path}" "installer"')
-        run(f'ln -s "{ui_target_path}" "ui"')
-        run(f'ln -s "{engine_target_path}" "engine"')
-
-    print(f'Created symlinks! Your installation will now automatically use the files present in the repository at {opt.symlink_dir}')

installer/installer/app.py

@@ -1,70 +0,0 @@
-import os
-import json
-import platform
-
-# config
-PROJECT_REPO_URL = 'https://github.com/cmdr2/stable-diffusion-ui.git'
-DEFAULT_PROJECT_BRANCH = 'installer_new'
-PROJECT_REPO_DIR_NAME = 'project_repo'
-
-STABLE_DIFFUSION_REPO_URL = 'https://github.com/basujindal/stable-diffusion.git'
-DEFAULT_STABLE_DIFFUSION_COMMIT = 'f6cfebffa752ee11a7b07497b8529d5971de916c'
-STABLE_DIFFUSION_REPO_DIR_NAME = 'stable-diffusion'
-
-PROJECT_ENV_DIR_NAME = 'project_env'
-
-START_CMD_FILE_NAME = "Start Stable Diffusion UI.cmd" if platform.system() == "Windows" else "start.sh"
-DEV_CONSOLE_CMD_FILE_NAME = "Developer Console.cmd" if platform.system() == "Windows" else "developer_console.sh"
-CONFIG_FILE_NAME = 'config.json'
-
-# top-level folders
-ENV_DIR_NAME = 'env'
-MODELS_DIR_NAME = 'models'
-
-INSTALLER_DIR_NAME = 'installer'
-UI_DIR_NAME = 'ui'
-ENGINE_DIR_NAME = 'engine'
-
-
-# env
-SD_BASE_DIR = os.environ['SD_BASE_DIR']
-
-
-# model folders
-STABLE_DIFFUSION_MODELS_DIR_NAME = "stable-diffusion"
-GFPGAN_MODELS_DIR_NAME = "gfpgan"
-RealESRGAN_MODELS_DIR_NAME = "realesrgan"
-
-# create references to dirs
-env_dir_path = os.path.join(SD_BASE_DIR, ENV_DIR_NAME)
-
-installer_dir_path = os.path.join(SD_BASE_DIR, INSTALLER_DIR_NAME)
-ui_dir_path = os.path.join(SD_BASE_DIR, UI_DIR_NAME)
-engine_dir_path = os.path.join(SD_BASE_DIR, ENGINE_DIR_NAME)
-
-project_repo_dir_path = os.path.join(env_dir_path, PROJECT_REPO_DIR_NAME)
-stable_diffusion_repo_dir_path = os.path.join(env_dir_path, STABLE_DIFFUSION_REPO_DIR_NAME)
-
-project_env_dir_path = os.path.join(env_dir_path, PROJECT_ENV_DIR_NAME)
-
-patches_dir_path = os.path.join(installer_dir_path, 'patches')
-
-models_dir_path = os.path.join(SD_BASE_DIR, MODELS_DIR_NAME)
-stable_diffusion_models_dir_path = os.path.join(models_dir_path, STABLE_DIFFUSION_MODELS_DIR_NAME)
-gfpgan_models_dir_path = os.path.join(models_dir_path, GFPGAN_MODELS_DIR_NAME)
-realesrgan_models_dir_path = os.path.join(models_dir_path, RealESRGAN_MODELS_DIR_NAME)
-
-
-# useful functions
-def get_config():
-    config_path = os.path.join(SD_BASE_DIR, CONFIG_FILE_NAME)
-    if not os.path.exists(config_path):
-        return {}
-
-    with open(config_path, "r") as f:
-        return json.load(f)
-
-
-# app context
-config = get_config()
-activated_env_dir_path = None

installer/installer/check_modules.py

@@ -1,18 +0,0 @@
-'''
-This script is run by the `installer.helpers.modules_exist_in_env()` function
-'''
-
-import sys
-import pkgutil
-
-modules = sys.argv[1:]
-missing_modules = []
-for m in modules:
-    if pkgutil.find_loader(m) is None:
-        missing_modules.append(m)
-
-if len(missing_modules) == 0:
-    print('42')
-    exit()
-
-print('Missing modules', missing_modules)

installer/installer/helpers.py

@@ -1,80 +0,0 @@
-import os
-from os import path
-import subprocess
-import traceback
-
-from installer import app
-
-def run(cmd, run_in_folder=None, env=None, get_output=False, log_the_cmd=False):
-    if app.activated_env_dir_path is not None and 'micromamba activate' not in cmd:
-        cmd = f'micromamba activate "{app.activated_env_dir_path}" && {cmd}'
-
-    if run_in_folder is not None:
-        cmd = f'cd "{run_in_folder}" && {cmd}'
-
-    if log_the_cmd:
-        log('running: ' + cmd)
-
-    if get_output:
-        p = subprocess.Popen(cmd, shell=True, env=env, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
-    else:
-        p = subprocess.Popen(cmd, shell=True, env=env)
-
-    out, err = p.communicate()
-
-    out = out.decode('utf-8') if isinstance(out, bytes) else out
-    err = err.decode('utf-8') if isinstance(out, bytes) else err
-
-    if get_output:
-        return out, err
-
-def log(msg):
-    print(msg)
-
-def modules_exist_in_env(modules, env_dir_path=app.project_env_dir_path):
-    if not path.exists(env_dir_path):
-        return False
-
-    check_modules_script_path = path.join(app.installer_dir_path, 'installer', 'check_modules.py')
-    module_args = ' '.join(modules)
-    check_modules_cmd = f'python "{check_modules_script_path}" {module_args}'
-
-    env = os.environ.copy()
-    env['PYTHONPATH'] = app.stable_diffusion_repo_dir_path + ';' + os.path.join(app.project_env_dir_path, 'lib', 'site-packages')
-
-    if app.activated_env_dir_path != env_dir_path:
-        activate_cmd = f'micromamba activate "{env_dir_path}"'
-        check_modules_cmd = f'{activate_cmd} && {check_modules_cmd}'
-
-    # activate and run the modules checker
-    output, _ = run(check_modules_cmd, get_output=True, env=env)
-    if 'Missing' in output:
-        log(output)
-        return False
-
-    return True
-
-def fail_with_install_error(error_msg):
-    try:
-        log(traceback.format_stack())
-        log(f'''
-
-Error: {error_msg}. Sorry about that, please try to:
-  1. Run this installer again.
-  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md
-  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB
-  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues
-Thanks!''')
-    except:
-        pass
-
-    exit(1)
-
-def apply_git_patches(repo_dir_path, patch_file_names):
-    is_developer_mode = app.config.get('is_developer_mode', False)
-    if is_developer_mode:
-        return
-
-    for patch_file_name in patch_file_names:
-        patch_file_path = path.join(app.patches_dir_path, patch_file_name)
-        run(f"git apply {patch_file_path}", run_in_folder=repo_dir_path)

installer/installer/main.py

@@ -1,34 +0,0 @@
-import os
-import sys
-from datetime import datetime
-
-sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
-
-from installer import helpers
-from installer.tasks import (
-    fetch_project_repo,
-    apply_project_update,
-    fetch_stable_diffusion_repo,
-    install_stable_diffusion_packages,
-    install_ui_packages,
-    download_weights,
-    start_ui_server,
-)
-
-tasks = [
-    fetch_project_repo,
-    apply_project_update,
-    fetch_stable_diffusion_repo,
-    install_stable_diffusion_packages,
-    install_ui_packages,
-    download_weights,
-    start_ui_server,
-]
-
-helpers.log(f'Starting Stable Diffusion UI at {datetime.now().strftime("%d/%m/%Y %H:%M:%S")}')
-
-def run_tasks():
-    for task in tasks:
-        task.run()
-
-run_tasks()

installer/installer/start.bat

@@ -1,8 +0,0 @@
-@echo off
-rem Never edit this file. If you really, really have to, beware that a script doesn't like
-rem being overwritten while it is running (the auto-updater will do that).
-rem The trick is to update this file while another script is running, and vice versa.
-
-call python %SD_BASE_DIR%\installer\installer\main.py
-
-pause

installer/installer/start.sh

@@ -1,9 +0,0 @@
-#!/bin/bash
-
-# Never edit this file. If you really, really have to, beware that a script doesn't like
-# being overwritten while it is running (the auto-updater will do that).
-# The trick is to update this file while another script is running, and vice versa.
-
-python $SD_BASE_DIR/installer/installer/main.py
-
-read -p "Press enter to continue"

installer/installer/tasks/apply_project_update.py

@@ -1,30 +0,0 @@
-from os import path
-import shutil
-
-from installer import app
-
-def run():
-    is_developer_mode = app.config.get('is_developer_mode', False)
-    if is_developer_mode:
-        return
-
-    installer_src_path = path.join(app.project_repo_dir_path, 'installer')
-    ui_src_path = path.join(app.project_repo_dir_path, 'ui')
-    engine_src_path = path.join(app.project_repo_dir_path, 'engine')
-
-    start_cmd_src_path = path.join(app.project_repo_dir_path, app.START_CMD_FILE_NAME)
-    start_cmd_dst_path = path.join(app.SD_BASE_DIR, app.START_CMD_FILE_NAME)
-
-    dev_console_cmd_src_path = path.join(app.project_repo_dir_path, app.DEV_CONSOLE_CMD_FILE_NAME)
-    dev_console_cmd_dst_path = path.join(app.SD_BASE_DIR, app.DEV_CONSOLE_CMD_FILE_NAME)
-
-    shutil.rmtree(app.installer_dir_path, ignore_errors=True)
-    shutil.rmtree(app.ui_dir_path, ignore_errors=True)
-    shutil.rmtree(app.engine_dir_path, ignore_errors=True)
-
-    shutil.copytree(installer_src_path, app.installer_dir_path, dirs_exist_ok=True)
-    shutil.copytree(ui_src_path, app.ui_dir_path, dirs_exist_ok=True)
-    shutil.copytree(engine_src_path, app.engine_dir_path, dirs_exist_ok=True)
-
-    shutil.copy(start_cmd_src_path, start_cmd_dst_path)
-    shutil.copy(dev_console_cmd_src_path, dev_console_cmd_dst_path)

installer/installer/tasks/download_weights.py

@@ -1,46 +0,0 @@
-import os
-
-from installer import app, helpers
-
-def run():
-    fetch_model('Stable Diffusion', 'sd-v1-4.ckpt', model_dir_path=app.stable_diffusion_models_dir_path, download_url='https://me.cmdr2.org/stable-diffusion-ui/sd-v1-4.ckpt', expected_file_sizes=[4265380512, 7703807346, 7703810927])
-    fetch_model('Face Correction (GFPGAN)', 'GFPGANv1.4.pth', model_dir_path=app.gfpgan_models_dir_path, download_url='https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/GFPGANv1.4.pth', expected_file_sizes=[348632874])
-    fetch_model('Resolution Upscale (RealESRGAN x4)', 'RealESRGAN_x4plus.pth', model_dir_path=app.realesrgan_models_dir_path, download_url='https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth', expected_file_sizes=[67040989])
-    fetch_model('Resolution Upscale (RealESRGAN x4_anime)', 'RealESRGAN_x4plus_anime_6B.pth', model_dir_path=app.realesrgan_models_dir_path, download_url='https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth', expected_file_sizes=[17938799])
-
-def fetch_model(model_type, file_name, model_dir_path, download_url, expected_file_sizes):
-    os.makedirs(model_dir_path, exist_ok=True)
-
-    file_path = os.path.join(model_dir_path, file_name)
-
-    if model_exists(file_name, file_path, expected_file_sizes):
-        helpers.log(f'Data files (weights) necessary for {model_type} were already downloaded')
-        return
-
-    helpers.log(f'Downloading data files (weights) for {model_type}..')
-
-    helpers.run(f'curl -L -k "{download_url}" > "{file_path}"', log_the_cmd=True)
-
-def model_exists(file_name, file_path, expected_file_sizes):
-    legacy_file_path = os.path.join(app.stable_diffusion_repo_dir_path, file_name)
-
-    file_exists = os.path.exists(file_path)
-    legacy_file_exists = os.path.exists(legacy_file_path)
-
-    if legacy_file_exists:
-        file_size = os.path.getsize(legacy_file_path)
-        if file_size in expected_file_sizes:
-            return True
-
-        helpers.log(f'{file_name} is invalid. Was only {file_size} bytes in size. Downloading again..')
-        os.remove(legacy_file_path)
-
-    if file_exists:
-        file_size = os.path.getsize(file_path)
-        if file_size in expected_file_sizes:
-            return True
-
-        helpers.log(f'{file_name} is invalid. Was only {file_size} bytes in size. Downloading again..')
-        os.remove(file_path)
-
-    return False

installer/installer/tasks/fetch_project_repo.py

@@ -1,27 +0,0 @@
-from os import path
-
-from installer import app, helpers
-
-project_repo_git_path = path.join(app.project_repo_dir_path, '.git')
-
-def run():
-    branch_name = app.config.get('update_branch', app.DEFAULT_PROJECT_BRANCH)
-
-    if path.exists(project_repo_git_path):
-        helpers.log(f"Stable Diffusion UI's git repository was already installed. Updating from {branch_name}..")
-
-        helpers.run("git reset --hard", run_in_folder=app.project_repo_dir_path)
-        helpers.run(f'git -c advice.detachedHead=false checkout "{branch_name}"', run_in_folder=app.project_repo_dir_path)
-        helpers.run("git pull", run_in_folder=app.project_repo_dir_path)
-    else:
-        helpers.log("\nDownloading Stable Diffusion UI..\n")
-        helpers.log(f"Using the {branch_name} channel\n")
-
-        helpers.run(f'git clone {app.PROJECT_REPO_URL} "{app.project_repo_dir_path}"')
-
-        if path.exists(project_repo_git_path):
-            helpers.log("Downloaded Stable Diffusion UI")
-        else:
-            helpers.fail_with_install_error(error_msg="Could not download Stable Diffusion UI")
-
-        helpers.run(f'git -c advice.detachedHead=false checkout "{branch_name}"', run_in_folder=app.project_repo_dir_path)

installer/installer/tasks/fetch_stable_diffusion_repo.py

@@ -1,37 +0,0 @@
-from os import path
-
-from installer import app, helpers
-
-stable_diffusion_repo_git_path = path.join(app.stable_diffusion_repo_dir_path, '.git')
-
-is_developer_mode = app.config.get('is_developer_mode', False)
-
-def run():
-    fetch_repo()
-
-    helpers.apply_git_patches(app.stable_diffusion_repo_dir_path, patch_file_names=(
-        "sd_custom.patch",
-    ))
-
-def fetch_repo():
-    commit_id = app.config.get('stable_diffusion_commit', app.DEFAULT_STABLE_DIFFUSION_COMMIT)
-
-    if path.exists(stable_diffusion_repo_git_path):
-        helpers.log(f"Stable Diffusion's git repository was already installed. Using commit: {commit_id}..")
-
-        if not is_developer_mode:
-            helpers.run("git reset --hard", run_in_folder=app.stable_diffusion_repo_dir_path)
-            helpers.run("git fetch origin", run_in_folder=app.stable_diffusion_repo_dir_path)
-            helpers.run(f'git -c advice.detachedHead=false checkout "{commit_id}"', run_in_folder=app.stable_diffusion_repo_dir_path)
-    else:
-        helpers.log("\nDownloading Stable Diffusion..\n")
-        helpers.log(f"Using commit: {commit_id}\n")
-
-        helpers.run(f'git clone {app.STABLE_DIFFUSION_REPO_URL} "{app.stable_diffusion_repo_dir_path}"')
-
-        if path.exists(stable_diffusion_repo_git_path):
-            helpers.log("Downloaded Stable Diffusion")
-        else:
-            helpers.fail_with_install_error(error_msg="Could not download Stable Diffusion")
-
-        helpers.run(f'git -c advice.detachedHead=false checkout "{commit_id}"', run_in_folder=app.stable_diffusion_repo_dir_path)

installer/installer/tasks/install_stable_diffusion_packages.py

@@ -1,59 +0,0 @@
-import os
-import platform
-import shutil
-
-from installer import app, helpers
-
-def run():
-    environment_file_path = get_environment_file_path()
-    local_env_file_path = os.path.join(app.stable_diffusion_repo_dir_path, 'environment.yaml')
-
-    shutil.copy(environment_file_path, local_env_file_path)
-
-    if is_valid_env():
-        helpers.log("Packages necessary for Stable Diffusion were already installed")
-        return
-
-    log_installing_header()
-
-    env = os.environ.copy()
-    env['PYTHONNOUSERSITE'] = '1'
-
-    if not os.path.exists(app.project_env_dir_path):
-        helpers.run(f'micromamba create --prefix {app.project_env_dir_path}', log_the_cmd=True)
-
-    helpers.run(f'micromamba install -y --prefix {app.project_env_dir_path} -f {local_env_file_path}', env=env, log_the_cmd=True, run_in_folder=app.stable_diffusion_repo_dir_path)
-
-    if is_valid_env():
-        helpers.log("Installed the packages necessary for Stable Diffusion")
-
-        app.activated_env_dir_path = app.project_env_dir_path # so that future `run()` invocations will run in the activated env
-    else:
-        helpers.fail_with_install_error(error_msg="Could not install the packages necessary for Stable Diffusion")
-
-    apply_patches()
-
-def apply_patches():
-    gfpgan_repo_dir_path = os.path.join(app.stable_diffusion_repo_dir_path, 'src', 'gfpgan')
-    helpers.apply_git_patches(gfpgan_repo_dir_path, patch_file_names=(
-        "gfpgan_custom.patch",
-    ))
-
-def get_environment_file_path():
-    environment_file_name = 'sd-environment-win-linux-nvidia.yaml'
-    if platform.system() == 'Darwin':
-        environment_file_name = 'sd-environment-mac-nvidia.yaml'
-
-    return os.path.join(app.installer_dir_path, 'yaml', environment_file_name)
-
-def log_installing_header():
-    helpers.log('''
-
-Downloading packages necessary for Stable Diffusion..
-
-***** !! This will take some time (depending on the speed of the Internet connection) and may appear to be stuck, but please be patient *****
-
-''')
-
-def is_valid_env():
-    return helpers.modules_exist_in_env(('torch', 'antlr4', 'transformers', 'numpy', 'gfpgan', 'realesrgan', 'basicsr'))

installer/installer/tasks/install_ui_packages.py

@@ -1,39 +0,0 @@
-import os
-import shutil
-import platform
-
-from installer import app, helpers
-
-def run():
-    if is_valid_env():
-        helpers.log("Packages necessary for Stable Diffusion UI were already installed")
-        return
-
-    log_installing_header()
-
-    env = os.environ.copy()
-    env['PYTHONNOUSERSITE'] = '1'
-
-    helpers.run(f'micromamba install -y --prefix {app.project_env_dir_path} -c conda-forge uvicorn fastapi', env=env, log_the_cmd=True)
-
-    if is_valid_env():
-        helpers.log("Installed the packages necessary for Stable Diffusion UI")
-    else:
-        helpers.fail_with_install_error(error_msg="Could not install the packages necessary for Stable Diffusion UI")
-
-def log_installing_header():
-    helpers.log('''
-
-Downloading packages necessary for Stable Diffusion UI..
-
-''')
-
-def is_valid_env():
-    path = os.environ['PATH']
-    path += ';' + os.path.join(app.project_env_dir_path, 'Scripts' if platform.system() == 'Windows' else 'bin')
-
-    if shutil.which("uvicorn", path=path) is None:
-        helpers.log("uvicorn not found!")
-        return False
-
-    return helpers.modules_exist_in_env(('uvicorn', 'fastapi'))

installer/installer/tasks/start_ui_server.py

@@ -1,23 +0,0 @@
-import os
-import platform
-
-from installer import app, helpers
-
-def run():
-    helpers.log("\nStable Diffusion is ready!\n")
-
-    env = os.environ.copy()
-    env['SD_DIR'] = app.stable_diffusion_repo_dir_path
-    env['PYTHONPATH'] = app.stable_diffusion_repo_dir_path + ';' + os.path.join(app.project_env_dir_path, 'lib', 'site-packages')
-    env['SD_UI_PATH'] = app.ui_dir_path
-    env['PATH'] += ';' + os.path.join(app.project_env_dir_path, 'Scripts' if platform.system() == 'Windows' else 'bin')
-
-    helpers.log(f'PYTHONPATH={env["PYTHONPATH"]}')
-    helpers.run('python --version', log_the_cmd=True)
-
-    host = app.config.get('host', 'localhost')
-    port = app.config.get('port', '9000')
-
-    ui_server_cmd = f'uvicorn server:app --app-dir "{app.ui_dir_path}" --port {port} --host {host}'
-
-    helpers.run(ui_server_cmd, run_in_folder=app.stable_diffusion_repo_dir_path, log_the_cmd=True, env=env)

installer/patches/gfpgan_custom.patch

@@ -1,22 +0,0 @@
-diff --git a/gfpgan/utils.py b/gfpgan/utils.py
-index 74ee5a8..1357f48 100644
---- a/gfpgan/utils.py
-+++ b/gfpgan/utils.py
-@@ -117,14 +117,14 @@ class GFPGANer():
-         # face restoration
-         for cropped_face in self.face_helper.cropped_faces:
-             # prepare data
--            cropped_face_t = img2tensor(cropped_face / 255., bgr2rgb=True, float32=True)
-+            cropped_face_t = img2tensor(cropped_face / 255., bgr2rgb=False, float32=True)
-             normalize(cropped_face_t, (0.5, 0.5, 0.5), (0.5, 0.5, 0.5), inplace=True)
-             cropped_face_t = cropped_face_t.unsqueeze(0).to(self.device)
- 
-             try:
--                output = self.gfpgan(cropped_face_t, return_rgb=False, weight=weight)[0]
-+                output = self.gfpgan(cropped_face_t, return_rgb=True, weight=weight)[0]
-                 # convert to image
--                restored_face = tensor2img(output.squeeze(0), rgb2bgr=True, min_max=(-1, 1))
-+                restored_face = tensor2img(output.squeeze(0), rgb2bgr=False, min_max=(-1, 1))
-             except RuntimeError as error:
-                 print(f'\tFailed inference for GFPGAN: {error}.')
-                 restored_face = cropped_face

installer/yaml/sd-environment-mac-nvidia.yaml

@@ -1,47 +0,0 @@
-name: ldm
-channels:
-  - pytorch
-  - conda-forge
-dependencies:
-  - python==3.10.5
-  - pip==22.2.2
-
-  - pytorch
-  - torchvision
-
-  - albumentations==1.2.1
-  - coloredlogs==15.0.1
-  - einops==0.4.1
-  - grpcio==1.46.4
-  - humanfriendly==10.0
-  - imageio==2.21.2
-  - imageio-ffmpeg==0.4.7
-  - imgaug==0.4.0
-  - kornia==0.6.7
-  - mpmath==1.2.1
-  - nomkl
-  - numpy==1.23.2
-  - omegaconf==2.1.1
-  - onnx==1.12.0
-  - onnxruntime==1.12.1
-  - pudb==2022.1
-  - pytorch-lightning==1.6.5
-  - scipy==1.9.1
-  - streamlit==1.12.2
-  - sympy==1.10.1
-  - tensorboard==2.9.0
-  - torchmetrics==0.9.3
-  - antlr4-python3-runtime=4.8
-  - pip:
-    - opencv-python==4.6.0.66
-    - realesrgan==0.2.5.0
-    - test-tube==0.7.5
-    - transformers==4.21.2
-    - torch-fidelity==0.3.0
-    - -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
-    - -e git+https://github.com/openai/CLIP.git@main#egg=clip
-    - -e git+https://github.com/TencentARC/GFPGAN#egg=GFPGAN
-    - -e git+https://github.com/xinntao/Real-ESRGAN#egg=realesrgan
-    - -e .
-variables:
-  PYTORCH_ENABLE_MPS_FALLBACK: 1

installer/yaml/sd-environment-win-linux-nvidia.yaml

@@ -1,33 +0,0 @@
-name: ldm
-channels:
-  - pytorch
-  - defaults
-  - conda-forge
-dependencies:
-  - python=3.10.5
-  - pip=20.3
-  - cudatoolkit=11.3
-  - pytorch=1.11.0
-  - torchvision=0.12.0
-  - numpy=1.23.2
-  - antlr4-python3-runtime=4.8
-  - pip:
-    - albumentations==0.4.3
-    - opencv-python==4.6.0.66
-    - pudb==2019.2
-    - imageio==2.9.0
-    - imageio-ffmpeg==0.4.2
-    - pytorch-lightning==1.4.2
-    - omegaconf==2.1.1
-    - test-tube>=0.7.5
-    - streamlit>=0.73.1
-    - einops==0.3.0
-    - torch-fidelity==0.3.0
-    - transformers==4.19.2
-    - torchmetrics==0.6.0
-    - kornia==0.6
-    - -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
-    - -e git+https://github.com/openai/CLIP.git@main#egg=clip
-    - -e git+https://github.com/TencentARC/GFPGAN#egg=GFPGAN
-    - -e git+https://github.com/xinntao/Real-ESRGAN#egg=realesrgan
-    - -e .

scripts/Start Stable Diffusion UI.cmd

@@ -0,0 +1,19 @@
+@echo off
+
+@REM Delete the post-activate hook from the old installer
+if exist "installer\etc\conda\activate.d\post_activate.bat" (
+    echo. > installer\etc\conda\activate.d\post_activate.bat
+)
+
+@call installer\Scripts\activate.bat
+
+@call conda-unpack
+
+@call conda --version
+@call git --version
+
+@cd installer
+
+@call ..\scripts\on_env_start.bat
+
+@pause

scripts/on_env_start.bat

@@ -0,0 +1,61 @@
+@echo off
+
+@echo. & echo "Stable Diffusion UI - v2" & echo.
+
+set PATH=C:\Windows\System32;%PATH%
+
+@cd ..
+
+if exist "scripts\config.bat" (
+    @call scripts\config.bat
+)
+
+if "%update_branch%"=="" (
+    set update_branch=main
+)
+
+@>nul grep -c "conda_sd_ui_deps_installed" scripts\install_status.txt
+@if "%ERRORLEVEL%" NEQ "0" (
+    for /f "tokens=*" %%a in ('python -c "import os; parts = os.getcwd().split(os.path.sep); print(len(parts))"') do if "%%a" NEQ "2" (
+        echo. & echo "!!!! WARNING !!!!" & echo.
+        echo "Your 'stable-diffusion-ui' folder is at %cd%" & echo.
+        echo "The 'stable-diffusion-ui' folder needs to be at the top of your drive, for e.g. 'C:\stable-diffusion-ui' or 'D:\stable-diffusion-ui' etc."
+        echo "Not placing this folder at the top of a drive can cause errors on some computers."
+        echo. & echo "Recommended: Please close this window and move the 'stable-diffusion-ui' folder to the top of a drive. For e.g. 'C:\stable-diffusion-ui'. Then run the installer again." & echo.
+        echo "Not Recommended: If you're sure that you want to install at the current location, please press any key to continue." & echo.
+
+        pause
+    )
+)
+
+@>nul grep -c "sd_ui_git_cloned" scripts\install_status.txt
+@if "%ERRORLEVEL%" EQU "0" (
+    @echo "Stable Diffusion UI's git repository was already installed. Updating from %update_branch%.."
+
+    @cd sd-ui-files
+
+    @call git reset --hard
+    @call git checkout "%update_branch%"
+    @call git pull
+
+    @cd ..
+) else (
+    @echo. & echo "Downloading Stable Diffusion UI.." & echo.
+    @echo "Using the %update_branch% channel" & echo.
+
+    @call git clone -b "%update_branch%" https://github.com/cmdr2/stable-diffusion-ui.git sd-ui-files && (
+        @echo sd_ui_git_cloned >> scripts\install_status.txt
+    ) || (
+        @echo "Error downloading Stable Diffusion UI. Sorry about that, please try to:" & echo "  1. Run this installer again." & echo "  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md" & echo "  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB" & echo "  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues" & echo "Thanks!"
+        pause
+        @exit /b
+    )
+)
+
+@xcopy sd-ui-files\ui ui /s /i /Y
+@copy sd-ui-files\scripts\on_sd_start.bat scripts\ /Y
+@copy "sd-ui-files\scripts\Start Stable Diffusion UI.cmd" . /Y
+
+@call scripts\on_sd_start.bat
+
+@pause

scripts/on_env_start.sh

@@ -0,0 +1,43 @@
+#!/bin/bash
+
+printf "\n\nStable Diffusion UI\n\n"
+
+if [ -f "scripts/config.sh" ]; then
+    source scripts/config.sh
+fi
+
+if [ "$update_branch" == "" ]; then
+    export update_branch="main"
+fi
+
+if [ -f "scripts/install_status.txt" ] && [ `grep -c sd_ui_git_cloned scripts/install_status.txt` -gt "0" ]; then
+    echo "Stable Diffusion UI's git repository was already installed. Updating from $update_branch.."
+
+    cd sd-ui-files
+
+    git reset --hard
+    git checkout "$update_branch"
+    git pull
+
+    cd ..
+else
+    printf "\n\nDownloading Stable Diffusion UI..\n\n"
+    printf "Using the $update_branch channel\n\n"
+
+    if git clone -b "$update_branch" https://github.com/cmdr2/stable-diffusion-ui.git sd-ui-files ; then
+        echo sd_ui_git_cloned >> scripts/install_status.txt
+    else
+        printf "\n\nError downloading Stable Diffusion UI. Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+fi
+
+rm -rf ui
+cp -Rf sd-ui-files/ui .
+cp sd-ui-files/scripts/on_sd_start.sh scripts/
+cp sd-ui-files/scripts/start.sh .
+
+./scripts/on_sd_start.sh
+
+read -p "Press any key to continue"

scripts/on_sd_start.bat

@@ -0,0 +1,267 @@
+@echo off
+
+@copy sd-ui-files\scripts\on_env_start.bat scripts\ /Y
+
+@REM Caution, this file will make your eyes and brain bleed. It's such an unholy mess.
+@REM Note to self: Please rewrite this in Python. For the sake of your own sanity.
+
+@call python -c "import os; import shutil; frm = 'sd-ui-files\\ui\\hotfix\\9c24e6cd9f499d02c4f21a033736dabd365962dc80fe3aeb57a8f85ea45a20a3.26fead7ea4f0f843f6eb4055dfd25693f1a71f3c6871b184042d4b126244e142'; dst = os.path.join(os.path.expanduser('~'), '.cache', 'huggingface', 'transformers', '9c24e6cd9f499d02c4f21a033736dabd365962dc80fe3aeb57a8f85ea45a20a3.26fead7ea4f0f843f6eb4055dfd25693f1a71f3c6871b184042d4b126244e142'); shutil.copyfile(frm, dst) if os.path.exists(dst) else print(''); print('Hotfixed broken JSON file from OpenAI');"
+
+@>nul grep -c "sd_git_cloned" scripts\install_status.txt
+@if "%ERRORLEVEL%" EQU "0" (
+    @echo "Stable Diffusion's git repository was already installed. Updating.."
+
+    @cd stable-diffusion
+
+    @call git reset --hard
+    @call git pull
+    @call git checkout d87bd29a6862996d8a0980c1343b6f0d4eb718b4
+
+    @REM @call git apply ..\ui\sd_internal\ddim_callback.patch
+    @REM @call git apply ..\ui\sd_internal\env_yaml.patch
+    @call git apply ..\ui\sd_internal\custom_sd.patch
+
+    @cd ..
+) else (
+    @echo. & echo "Downloading Stable Diffusion.." & echo.
+
+    @call git clone https://github.com/invoke-ai/InvokeAI.git stable-diffusion && (
+        @echo sd_git_cloned >> scripts\install_status.txt
+    ) || (
+        @echo "Error downloading Stable Diffusion. Sorry about that, please try to:" & echo "  1. Run this installer again." & echo "  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md" & echo "  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB" & echo "  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues" & echo "Thanks!"
+        pause
+        @exit /b
+    )
+
+    @cd stable-diffusion
+    @call git checkout d87bd29a6862996d8a0980c1343b6f0d4eb718b4
+
+    @REM @call git apply ..\ui\sd_internal\ddim_callback.patch
+    @REM @call git apply ..\ui\sd_internal\env_yaml.patch
+    @call git apply ..\ui\sd_internal\custom_sd.patch
+
+    @cd ..
+)
+
+@cd stable-diffusion
+
+@>nul grep -c "conda_sd_env_created" ..\scripts\install_status.txt
+@if "%ERRORLEVEL%" EQU "0" (
+    @echo "Packages necessary for Stable Diffusion were already installed"
+
+    @call conda activate .\env
+) else (
+    @echo. & echo "Downloading packages necessary for Stable Diffusion.." & echo. & echo "***** This will take some time (depending on the speed of the Internet connection) and may appear to be stuck, but please be patient ***** .." & echo.
+
+    @rmdir /s /q .\env
+
+    @REM prevent conda from using packages from the user's home directory, to avoid conflicts
+    @set PYTHONNOUSERSITE=1
+
+    @call conda env create --prefix env -f environment.yaml || (
+        @echo. & echo "Error installing the packages necessary for Stable Diffusion. Sorry about that, please try to:" & echo "  1. Run this installer again." & echo "  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md" & echo "  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB" & echo "  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues" & echo "Thanks!" & echo.
+        pause
+        exit /b
+    )
+
+    @call conda activate .\env
+
+    @call conda install -c conda-forge -y --prefix env antlr4-python3-runtime=4.8 || (
+        @echo. & echo "Error installing antlr4-python3-runtime for Stable Diffusion. Sorry about that, please try to:" & echo "  1. Run this installer again." & echo "  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md" & echo "  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB" & echo "  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues" & echo "Thanks!" & echo.
+        pause
+        exit /b
+    )
+
+    for /f "tokens=*" %%a in ('python -c "import torch; import ldm; import transformers; import numpy; import antlr4; print(42)"') do if "%%a" NEQ "42" (
+        @echo. & echo "Dependency test failed! Error installing the packages necessary for Stable Diffusion. Sorry about that, please try to:" & echo "  1. Run this installer again." & echo "  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md" & echo "  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB" & echo "  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues" & echo "Thanks!" & echo.
+        pause
+        exit /b
+    )
+
+    @echo conda_sd_env_created >> ..\scripts\install_status.txt
+)
+
+set PATH=C:\Windows\System32;%PATH%
+
+@>nul grep -c "conda_sd_ui_deps_installed" ..\scripts\install_status.txt
+@if "%ERRORLEVEL%" EQU "0" (
+    echo "Packages necessary for Stable Diffusion UI were already installed"
+) else (
+    @echo. & echo "Downloading packages necessary for Stable Diffusion UI.." & echo.
+
+    @set PYTHONNOUSERSITE=1
+
+    @call conda install -c conda-forge -y --prefix env uvicorn fastapi || (
+        echo "Error installing the packages necessary for Stable Diffusion UI. Sorry about that, please try to:" & echo "  1. Run this installer again." & echo "  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md" & echo "  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB" & echo "  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues" & echo "Thanks!"
+        pause
+        exit /b
+    )
+)
+
+call WHERE uvicorn > .tmp
+@>nul grep -c "uvicorn" .tmp
+@if "%ERRORLEVEL%" NEQ "0" (
+    @echo. & echo "UI packages not found! Sorry about that, please try to:" & echo "  1. Run this installer again." & echo "  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md" & echo "  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB" & echo "  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues" & echo "Thanks!" & echo.
+    pause
+    exit /b
+)
+
+@>nul grep -c "conda_sd_ui_deps_installed" ..\scripts\install_status.txt
+@if "%ERRORLEVEL%" NEQ "0" (
+    @echo conda_sd_ui_deps_installed >> ..\scripts\install_status.txt
+)
+
+
+
+@if exist "sd-v1-4.ckpt" (
+    for %%I in ("sd-v1-4.ckpt") do if "%%~zI" EQU "4265380512" (
+        echo "Data files (weights) necessary for Stable Diffusion were already downloaded. Using the HuggingFace 4 GB Model."
+    ) else (
+        for %%J in ("sd-v1-4.ckpt") do if "%%~zJ" EQU "7703807346" (
+            echo "Data files (weights) necessary for Stable Diffusion were already downloaded. Using the HuggingFace 7 GB Model."
+        ) else (
+            for %%K in ("sd-v1-4.ckpt") do if "%%~zK" EQU "7703810927" (
+                echo "Data files (weights) necessary for Stable Diffusion were already downloaded. Using the Waifu Model."
+            ) else (
+                echo. & echo "The model file present at %cd%\sd-v1-4.ckpt is invalid. It is only %%~zK bytes in size. Re-downloading.." & echo.
+                del "sd-v1-4.ckpt"
+            )
+        )
+    )
+)
+
+@if not exist "sd-v1-4.ckpt" (
+    @echo. & echo "Downloading data files (weights) for Stable Diffusion.." & echo.
+
+    @call curl -L -k https://me.cmdr2.org/stable-diffusion-ui/sd-v1-4.ckpt > sd-v1-4.ckpt
+
+    @if exist "sd-v1-4.ckpt" (
+        for %%I in ("sd-v1-4.ckpt") do if "%%~zI" NEQ "4265380512" (
+            echo. & echo "Error: The downloaded model file was invalid! Bytes downloaded: %%~zI" & echo.
+            echo. & echo "Error downloading the data files (weights) for Stable Diffusion. Sorry about that, please try to:" & echo "  1. Run this installer again." & echo "  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md" & echo "  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB" & echo "  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues" & echo "Thanks!" & echo.
+            pause
+            exit /b
+        )
+    ) else (
+        @echo. & echo "Error downloading the data files (weights) for Stable Diffusion. Sorry about that, please try to:" & echo "  1. Run this installer again." & echo "  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md" & echo "  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB" & echo "  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues" & echo "Thanks!" & echo.
+        pause
+        exit /b
+    )
+)
+
+
+
+@if exist "GFPGANv1.3.pth" (
+    for %%I in ("GFPGANv1.3.pth") do if "%%~zI" EQU "348632874" (
+        echo "Data files (weights) necessary for GFPGAN (Face Correction) were already downloaded"
+    ) else (
+        echo. & echo "The GFPGAN model file present at %cd%\GFPGANv1.3.pth is invalid. It is only %%~zI bytes in size. Re-downloading.." & echo.
+        del "GFPGANv1.3.pth"
+    )
+)
+
+@if not exist "GFPGANv1.3.pth" (
+    @echo. & echo "Downloading data files (weights) for GFPGAN (Face Correction).." & echo.
+
+    @call curl -L -k https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth > GFPGANv1.3.pth
+
+    @if exist "GFPGANv1.3.pth" (
+        for %%I in ("GFPGANv1.3.pth") do if "%%~zI" NEQ "348632874" (
+            echo. & echo "Error: The downloaded GFPGAN model file was invalid! Bytes downloaded: %%~zI" & echo.
+            echo. & echo "Error downloading the data files (weights) for GFPGAN (Face Correction). Sorry about that, please try to:" & echo "  1. Run this installer again." & echo "  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md" & echo "  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB" & echo "  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues" & echo "Thanks!" & echo.
+            pause
+            exit /b
+        )
+    ) else (
+        @echo. & echo "Error downloading the data files (weights) for GFPGAN (Face Correction). Sorry about that, please try to:" & echo "  1. Run this installer again." & echo "  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md" & echo "  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB" & echo "  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues" & echo "Thanks!" & echo.
+        pause
+        exit /b
+    )
+)
+
+
+
+@if exist "RealESRGAN_x4plus.pth" (
+    for %%I in ("RealESRGAN_x4plus.pth") do if "%%~zI" EQU "67040989" (
+        echo "Data files (weights) necessary for ESRGAN (Resolution Upscaling) x4plus were already downloaded"
+    ) else (
+        echo. & echo "The GFPGAN model file present at %cd%\RealESRGAN_x4plus.pth is invalid. It is only %%~zI bytes in size. Re-downloading.." & echo.
+        del "RealESRGAN_x4plus.pth"
+    )
+)
+
+@if not exist "RealESRGAN_x4plus.pth" (
+    @echo. & echo "Downloading data files (weights) for ESRGAN (Resolution Upscaling) x4plus.." & echo.
+
+    @call curl -L -k https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth > RealESRGAN_x4plus.pth
+
+    @if exist "RealESRGAN_x4plus.pth" (
+        for %%I in ("RealESRGAN_x4plus.pth") do if "%%~zI" NEQ "67040989" (
+            echo. & echo "Error: The downloaded ESRGAN x4plus model file was invalid! Bytes downloaded: %%~zI" & echo.
+            echo. & echo "Error downloading the data files (weights) for ESRGAN (Resolution Upscaling) x4plus. Sorry about that, please try to:" & echo "  1. Run this installer again." & echo "  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md" & echo "  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB" & echo "  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues" & echo "Thanks!" & echo.
+            pause
+            exit /b
+        )
+    ) else (
+        @echo. & echo "Error downloading the data files (weights) for ESRGAN (Resolution Upscaling) x4plus. Sorry about that, please try to:" & echo "  1. Run this installer again." & echo "  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md" & echo "  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB" & echo "  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues" & echo "Thanks!" & echo.
+        pause
+        exit /b
+    )
+)
+
+
+
+@if exist "RealESRGAN_x4plus_anime_6B.pth" (
+    for %%I in ("RealESRGAN_x4plus_anime_6B.pth") do if "%%~zI" EQU "17938799" (
+        echo "Data files (weights) necessary for ESRGAN (Resolution Upscaling) x4plus_anime were already downloaded"
+    ) else (
+        echo. & echo "The GFPGAN model file present at %cd%\RealESRGAN_x4plus_anime_6B.pth is invalid. It is only %%~zI bytes in size. Re-downloading.." & echo.
+        del "RealESRGAN_x4plus_anime_6B.pth"
+    )
+)
+
+@if not exist "RealESRGAN_x4plus_anime_6B.pth" (
+    @echo. & echo "Downloading data files (weights) for ESRGAN (Resolution Upscaling) x4plus_anime.." & echo.
+
+    @call curl -L -k https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth > RealESRGAN_x4plus_anime_6B.pth
+
+    @if exist "RealESRGAN_x4plus_anime_6B.pth" (
+        for %%I in ("RealESRGAN_x4plus_anime_6B.pth") do if "%%~zI" NEQ "17938799" (
+            echo. & echo "Error: The downloaded ESRGAN x4plus_anime model file was invalid! Bytes downloaded: %%~zI" & echo.
+            echo. & echo "Error downloading the data files (weights) for ESRGAN (Resolution Upscaling) x4plus_anime. Sorry about that, please try to:" & echo "  1. Run this installer again." & echo "  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md" & echo "  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB" & echo "  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues" & echo "Thanks!" & echo.
+            pause
+            exit /b
+        )
+    ) else (
+        @echo. & echo "Error downloading the data files (weights) for ESRGAN (Resolution Upscaling) x4plus_anime. Sorry about that, please try to:" & echo "  1. Run this installer again." & echo "  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md" & echo "  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB" & echo "  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues" & echo "Thanks!" & echo.
+        pause
+        exit /b
+    )
+)
+
+
+
+@>nul grep -c "sd_install_complete" ..\scripts\install_status.txt
+@if "%ERRORLEVEL%" NEQ "0" (
+    @echo sd_weights_downloaded >> ..\scripts\install_status.txt
+    @echo sd_install_complete >> ..\scripts\install_status.txt
+)
+
+@echo. & echo "Stable Diffusion is ready!" & echo.
+
+@set SD_DIR=%cd%
+
+@cd env\lib\site-packages
+@set PYTHONPATH=%SD_DIR%;%cd%
+@cd ..\..\..
+@echo PYTHONPATH=%PYTHONPATH%
+
+@cd ..
+@set SD_UI_PATH=%cd%\ui
+@cd stable-diffusion
+
+@call python --version
+
+@uvicorn server:app --app-dir "%SD_UI_PATH%" --port 9000 --host 0.0.0.0
+
+@pause

scripts/on_sd_start.sh

@@ -0,0 +1,309 @@
+#!/bin/bash
+
+cp sd-ui-files/scripts/on_env_start.sh scripts/
+
+source installer/etc/profile.d/conda.sh
+
+python -c "import os; import shutil; frm = 'sd-ui-files/ui/hotfix/9c24e6cd9f499d02c4f21a033736dabd365962dc80fe3aeb57a8f85ea45a20a3.26fead7ea4f0f843f6eb4055dfd25693f1a71f3c6871b184042d4b126244e142'; dst = os.path.join(os.path.expanduser('~'), '.cache', 'huggingface', 'transformers', '9c24e6cd9f499d02c4f21a033736dabd365962dc80fe3aeb57a8f85ea45a20a3.26fead7ea4f0f843f6eb4055dfd25693f1a71f3c6871b184042d4b126244e142'); shutil.copyfile(frm, dst) if os.path.exists(dst) else print(''); print('Hotfixed broken JSON file from OpenAI');"
+
+# Caution, this file will make your eyes and brain bleed. It's such an unholy mess.
+# Note to self: Please rewrite this in Python. For the sake of your own sanity.
+
+if [ -e "scripts/install_status.txt" ] && [ `grep -c sd_git_cloned scripts/install_status.txt` -gt "0" ]; then
+    echo "Stable Diffusion's git repository was already installed. Updating.."
+
+    cd stable-diffusion
+
+    git reset --hard
+    git pull
+    git checkout f6cfebffa752ee11a7b07497b8529d5971de916c
+
+    git apply ../ui/sd_internal/ddim_callback.patch
+    git apply ../ui/sd_internal/env_yaml.patch
+
+    cd ..
+else
+    printf "\n\nDownloading Stable Diffusion..\n\n"
+
+    if git clone https://github.com/basujindal/stable-diffusion.git ; then
+        echo sd_git_cloned >> scripts/install_status.txt
+    else
+        printf "\n\nError downloading Stable Diffusion. Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+
+    cd stable-diffusion
+    git checkout f6cfebffa752ee11a7b07497b8529d5971de916c
+
+    git apply ../ui/sd_internal/ddim_callback.patch
+    git apply ../ui/sd_internal/env_yaml.patch
+
+    cd ..
+fi
+
+cd stable-diffusion
+
+if [ `grep -c conda_sd_env_created ../scripts/install_status.txt` -gt "0" ]; then
+    echo "Packages necessary for Stable Diffusion were already installed"
+
+    conda activate ./env
+else
+    printf "\n\nDownloading packages necessary for Stable Diffusion..\n"
+    printf "\n\n***** This will take some time (depending on the speed of the Internet connection) and may appear to be stuck, but please be patient ***** ..\n\n"
+
+    # prevent conda from using packages from the user's home directory, to avoid conflicts
+    export PYTHONNOUSERSITE=1
+
+    if conda env create --prefix env --force -f environment.yaml ; then
+        echo "Installed. Testing.."
+    else
+        printf "\n\nError installing the packages necessary for Stable Diffusion. Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+
+    conda activate ./env
+
+    if conda install -c conda-forge --prefix ./env -y antlr4-python3-runtime=4.8 ; then
+        echo "Installed. Testing.."
+    else
+        printf "\n\nError installing antlr4-python3-runtime for Stable Diffusion. Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+
+    out_test=`python -c "import torch; import ldm; import transformers; import numpy; import antlr4; print(42)"`
+    if [ "$out_test" != "42" ]; then
+        printf "\n\nDependency test failed! Error installing the packages necessary for Stable Diffusion. Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+
+    echo conda_sd_env_created >> ../scripts/install_status.txt
+fi
+
+if [ `grep -c conda_sd_gfpgan_deps_installed ../scripts/install_status.txt` -gt "0" ]; then
+    echo "Packages necessary for GFPGAN (Face Correction) were already installed"
+else
+    printf "\n\nDownloading packages necessary for GFPGAN (Face Correction)..\n"
+
+    export PYTHONNOUSERSITE=1
+
+    if pip install -e git+https://github.com/TencentARC/GFPGAN#egg=GFPGAN ; then
+        echo "Installed. Testing.."
+    else
+        printf "\n\nError installing the packages necessary for GFPGAN (Face Correction). Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+
+    out_test=`python -c "from gfpgan import GFPGANer; print(42)"`
+    if [ "$out_test" != "42" ]; then
+        printf "\n\nDependency test failed! Error installing the packages necessary for GFPGAN (Face Correction). Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+
+    echo conda_sd_gfpgan_deps_installed >> ../scripts/install_status.txt
+fi
+
+if [ `grep -c conda_sd_esrgan_deps_installed ../scripts/install_status.txt` -gt "0" ]; then
+    echo "Packages necessary for ESRGAN (Resolution Upscaling) were already installed"
+else
+    printf "\n\nDownloading packages necessary for ESRGAN (Resolution Upscaling)..\n"
+
+    export PYTHONNOUSERSITE=1
+
+    if pip install -e git+https://github.com/xinntao/Real-ESRGAN#egg=realesrgan ; then
+        echo "Installed. Testing.."
+    else
+        printf "\n\nError installing the packages necessary for ESRGAN (Resolution Upscaling). Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+
+    out_test=`python -c "from basicsr.archs.rrdbnet_arch import RRDBNet; from realesrgan import RealESRGANer; print(42)"`
+    if [ "$out_test" != "42" ]; then
+        printf "\n\nDependency test failed! Error installing the packages necessary for ESRGAN (Resolution Upscaling). Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+
+    echo conda_sd_esrgan_deps_installed >> ../scripts/install_status.txt
+fi
+
+if [ `grep -c conda_sd_ui_deps_installed ../scripts/install_status.txt` -gt "0" ]; then
+    echo "Packages necessary for Stable Diffusion UI were already installed"
+else
+    printf "\n\nDownloading packages necessary for Stable Diffusion UI..\n\n"
+
+    export PYTHONNOUSERSITE=1
+
+    if conda install -c conda-forge --prefix ./env -y uvicorn fastapi ; then
+        echo "Installed. Testing.."
+    else
+        printf "\n\nError installing the packages necessary for Stable Diffusion UI. Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+
+    if ! command -v uvicorn &> /dev/null; then
+        printf "\n\nUI packages not found! Error installing the packages necessary for Stable Diffusion UI. Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+
+    echo conda_sd_ui_deps_installed >> ../scripts/install_status.txt
+fi
+
+
+
+if [ -f "sd-v1-4.ckpt" ]; then
+    model_size=`ls -l sd-v1-4.ckpt | awk '{print $5}'`
+
+    if [ "$model_size" -eq "4265380512" ] || [ "$model_size" -eq "7703807346" ] || [ "$model_size" -eq "7703810927" ]; then
+        echo "Data files (weights) necessary for Stable Diffusion were already downloaded"
+    else
+        printf "\n\nThe model file present at $PWD/sd-v1-4.ckpt is invalid. It is only $model_size bytes in size. Re-downloading.."
+        rm sd-v1-4.ckpt
+    fi
+fi
+
+if [ ! -f "sd-v1-4.ckpt" ]; then
+    echo "Downloading data files (weights) for Stable Diffusion.."
+
+    curl -L -k https://me.cmdr2.org/stable-diffusion-ui/sd-v1-4.ckpt > sd-v1-4.ckpt
+
+    if [ -f "sd-v1-4.ckpt" ]; then
+        model_size=`ls -l sd-v1-4.ckpt | awk '{print $5}'`
+        if [ ! "$model_size" == "4265380512" ]; then
+            printf "\n\nError: The downloaded model file was invalid! Bytes downloaded: $model_size\n\n"
+            printf "\n\nError downloading the data files (weights) for Stable Diffusion. Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+            read -p "Press any key to continue"
+            exit
+        fi
+    else
+        printf "\n\nError downloading the data files (weights) for Stable Diffusion. Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+fi
+
+
+if [ -f "GFPGANv1.3.pth" ]; then
+    model_size=`ls -l GFPGANv1.3.pth | awk '{print $5}'`
+
+    if [ "$model_size" -eq "348632874" ]; then
+        echo "Data files (weights) necessary for GFPGAN (Face Correction) were already downloaded"
+    else
+        printf "\n\nThe model file present at $PWD/GFPGANv1.3.pth is invalid. It is only $model_size bytes in size. Re-downloading.."
+        rm GFPGANv1.3.pth
+    fi
+fi
+
+if [ ! -f "GFPGANv1.3.pth" ]; then
+    echo "Downloading data files (weights) for GFPGAN (Face Correction).."
+
+    curl -L -k https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth > GFPGANv1.3.pth
+
+    if [ -f "GFPGANv1.3.pth" ]; then
+        model_size=`ls -l GFPGANv1.3.pth | awk '{print $5}'`
+        if [ ! "$model_size" -eq "348632874" ]; then
+            printf "\n\nError: The downloaded GFPGAN model file was invalid! Bytes downloaded: $model_size\n\n"
+            printf "\n\nError downloading the data files (weights) for GFPGAN (Face Correction). Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+            read -p "Press any key to continue"
+            exit
+        fi
+    else
+        printf "\n\nError downloading the data files (weights) for GFPGAN (Face Correction). Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+fi
+
+
+if [ -f "RealESRGAN_x4plus.pth" ]; then
+    model_size=`ls -l RealESRGAN_x4plus.pth | awk '{print $5}'`
+
+    if [ "$model_size" -eq "67040989" ]; then
+        echo "Data files (weights) necessary for ESRGAN (Resolution Upscaling) x4plus were already downloaded"
+    else
+        printf "\n\nThe model file present at $PWD/RealESRGAN_x4plus.pth is invalid. It is only $model_size bytes in size. Re-downloading.."
+        rm RealESRGAN_x4plus.pth
+    fi
+fi
+
+if [ ! -f "RealESRGAN_x4plus.pth" ]; then
+    echo "Downloading data files (weights) for ESRGAN (Resolution Upscaling) x4plus.."
+
+    curl -L -k https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth > RealESRGAN_x4plus.pth
+
+    if [ -f "RealESRGAN_x4plus.pth" ]; then
+        model_size=`ls -l RealESRGAN_x4plus.pth | awk '{print $5}'`
+        if [ ! "$model_size" -eq "67040989" ]; then
+            printf "\n\nError: The downloaded ESRGAN x4plus model file was invalid! Bytes downloaded: $model_size\n\n"
+            printf "\n\nError downloading the data files (weights) for ESRGAN (Resolution Upscaling) x4plus. Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+            read -p "Press any key to continue"
+            exit
+        fi
+    else
+        printf "\n\nError downloading the data files (weights) for ESRGAN (Resolution Upscaling) x4plus. Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+fi
+
+
+if [ -f "RealESRGAN_x4plus_anime_6B.pth" ]; then
+    model_size=`ls -l RealESRGAN_x4plus_anime_6B.pth | awk '{print $5}'`
+
+    if [ "$model_size" -eq "17938799" ]; then
+        echo "Data files (weights) necessary for ESRGAN (Resolution Upscaling) x4plus_anime were already downloaded"
+    else
+        printf "\n\nThe model file present at $PWD/RealESRGAN_x4plus_anime_6B.pth is invalid. It is only $model_size bytes in size. Re-downloading.."
+        rm RealESRGAN_x4plus_anime_6B.pth
+    fi
+fi
+
+if [ ! -f "RealESRGAN_x4plus_anime_6B.pth" ]; then
+    echo "Downloading data files (weights) for ESRGAN (Resolution Upscaling) x4plus_anime.."
+
+    curl -L -k https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth > RealESRGAN_x4plus_anime_6B.pth
+
+    if [ -f "RealESRGAN_x4plus_anime_6B.pth" ]; then
+        model_size=`ls -l RealESRGAN_x4plus_anime_6B.pth | awk '{print $5}'`
+        if [ ! "$model_size" -eq "17938799" ]; then
+            printf "\n\nError: The downloaded ESRGAN x4plus_anime model file was invalid! Bytes downloaded: $model_size\n\n"
+            printf "\n\nError downloading the data files (weights) for ESRGAN (Resolution Upscaling) x4plus_anime. Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+            read -p "Press any key to continue"
+            exit
+        fi
+    else
+        printf "\n\nError downloading the data files (weights) for ESRGAN (Resolution Upscaling) x4plus_anime. Sorry about that, please try to:\n  1. Run this installer again.\n  2. If that doesn't fix it, please try the common troubleshooting steps at https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md\n  3. If those steps don't help, please copy *all* the error messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB\n  4. If that doesn't solve the problem, please file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\nThanks!\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+fi
+
+
+if [ `grep -c sd_install_complete ../scripts/install_status.txt` -gt "0" ]; then
+    echo sd_weights_downloaded >> ../scripts/install_status.txt
+    echo sd_install_complete >> ../scripts/install_status.txt
+fi
+
+printf "\n\nStable Diffusion is ready!\n\n"
+
+SD_PATH=`pwd`
+export PYTHONPATH="$SD_PATH;$SD_PATH/env/lib/python3.8/site-packages"
+echo "PYTHONPATH=$PYTHONPATH"
+
+cd ..
+export SD_UI_PATH=`pwd`/ui
+cd stable-diffusion
+
+python --version
+
+uvicorn server:app --app-dir "$SD_UI_PATH" --port 9000 --host 0.0.0.0
+
+read -p "Press any key to continue"

scripts/post_activate.bat

@@ -0,0 +1,6 @@
+@call conda --version
+@call git --version
+
+cd %CONDA_PREFIX%\..\scripts
+
+on_env_start.bat

scripts/post_activate.sh

@@ -0,0 +1,12 @@
+#!/bin/bash
+
+conda-unpack
+
+source $CONDA_PREFIX/etc/profile.d/conda.sh
+
+conda --version
+git --version
+
+cd $CONDA_PREFIX/../scripts
+
+./on_env_start.sh

scripts/start.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+source installer/bin/activate
+
+conda-unpack
+
+conda --version
+git --version
+
+scripts/on_env_start.sh

scripts/win_enable_long_filepaths.ps1

@@ -0,0 +1,2 @@
+Set-ItemProperty -Path 'HKLM:\SYSTEM\CurrentControlSet\Control\FileSystem' -Name LongPathsEnabled -Type DWord -Value 1
+pause

start.sh

@@ -1,18 +0,0 @@
-#!/bin/bash
-
-echo "Stable Diffusion UI - v2.5"
-echo ""
-
-export SD_BASE_DIR=$(pwd)
-
-echo "Working in $SD_BASE_DIR"
-
-# Setup the packages required for the installer
-installer/bootstrap/bootstrap.sh
-
-# Test the bootstrap
-git --version
-python --version
-
-# Download the rest of the installer and UI
-installer/installer/start.sh

ui/index.html

@@ -4,7 +4,7 @@
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
     <link rel="icon" type="image/png" href="/media/favicon-16x16.png" sizes="16x16">
     <link rel="icon" type="image/png" href="/media/favicon-32x32.png" sizes="32x32">
-    <link rel="stylesheet" href="/media/main.css?v=10">
+    <link rel="stylesheet" href="/media/main.css?v=21">
     <link rel="stylesheet" href="/media/modifier-thumbnails.css?v=1">
     <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.2.0/css/all.min.css">
     <link rel="stylesheet" href="/media/drawingboard.min.css">
@@ -15,7 +15,7 @@
 <div id="container">
     <div id="top-nav">
         <div id="logo">
-            <h1>Stable Diffusion UI <small>v2.195 <span id="updateBranchLabel"></span></small></h1>
+            <h1>Stable Diffusion UI <small>v2.2 <span id="updateBranchLabel"></span></small></h1>
         </div>
         <ul id="top-nav-items">
             <li class="dropdown">
@@ -213,7 +213,7 @@
 </div>
 </body>
 
-<script src="media/main.js?v=15"></script>
+<script src="media/main.js?v=21"></script>
 <script>
 async function init() {
     await loadModifiers()

ui/media/main.css

@@ -70,38 +70,36 @@ label {
     font-size: 8pt;
 }
 .imgSeedLabel {
-    position: absolute;
-    transform: translateX(-100%);
-    margin-top: 5pt;
-    margin-left: -5pt;
-    font-size: 10pt;
-
-    background-color: #333;
-    opacity: 0.8;
-    color: #ddd;
-    border-radius: 3pt;
-    padding: 1pt 3pt;
-}
-.imgUseBtn {
-    position: absolute;
-    transform: translateX(-100%);
-    margin-top: 30pt;
-    margin-left: -5pt;
-}
-.imgSaveBtn {
-    position: absolute;
-    transform: translateX(-100%);
-    margin-top: 55pt;
-    margin-left: -5pt;
+    font-size: 0.8em;
+    background-color: rgb(44, 45, 48);
+    border-radius: 3px;
+    padding: 5px;
 }
 .imgItem {
-    display: inline;
-    padding-right: 10px;
+    display: inline-block;
+    margin-top: 1em;
+    margin-right: 1em;
+}
+.imgContainer {
+    display: flex;
+    justify-content: flex-end;
 }
 .imgItemInfo {
-    opacity: 0.5;
+    padding-bottom: 0.5em;
+    display: flex;
+    align-items: flex-end;
+    flex-direction: column;
+    position: absolute;
+    padding: 5px;
+    opacity: 0;
+    transition: 0.1s all;
+}
+.imgContainer:hover > .imgItemInfo {
+    opacity: 1;
+}
+.imgItemInfo * {
+    margin-bottom: 7px;
 }
-
 #container {
     width: 90%;
     margin-left: auto;
@@ -410,3 +408,6 @@ img {
     color: #aaa;
     margin-bottom: 5pt;
 }
+.img-batch {
+    display: inline;
+}

ui/media/main.js

@@ -73,10 +73,10 @@ let editorTagsContainer = document.querySelector('#editor-inputs-tags-container'
 
 let imagePreview = document.querySelector("#preview")
 let previewImageField = document.querySelector('#preview-image')
-previewImageField.onchange = () => changePreviewImages(previewImageField.value);
+previewImageField.onchange = () => changePreviewImages(previewImageField.value)
 
 let modifierCardSizeSlider = document.querySelector('#modifier-card-size-slider')
-modifierCardSizeSlider.onchange = () => resizeModifierCards(modifierCardSizeSlider.value);
+modifierCardSizeSlider.onchange = () => resizeModifierCards(modifierCardSizeSlider.value)
 
 // let previewPrompt = document.querySelector('#preview-prompt')
 
@@ -119,8 +119,8 @@ let bellPending = false
 let taskQueue = []
 let currentTask = null
 
-const modifierThumbnailPath = 'media/modifier-thumbnails';
-const activeCardClass = 'modifier-card-active';
+const modifierThumbnailPath = 'media/modifier-thumbnails'
+const activeCardClass = 'modifier-card-active'
 
 function getLocalStorageItem(key, fallback) {
     let item = localStorage.getItem(key)
@@ -202,7 +202,7 @@ function isStreamImageProgressEnabled() {
 
 function setStatus(statusType, msg, msgType) {
     if (statusType !== 'server') {
-        return;
+        return
     }
 
     if (msgType == 'error') {
@@ -259,18 +259,100 @@ async function healthCheck() {
     }
 }
 
-function makeImageElement(width, height, outputContainer) {
-    let imgItem = document.createElement('div')
-    imgItem.className = 'imgItem'
+function showImages(req, res, outputContainer, livePreview) {
+    let imageItemElements = outputContainer.querySelectorAll('.imgItem')
 
-    let img = document.createElement('img')
-    img.width = parseInt(width)
-    img.height = parseInt(height)
+    res.output.reverse()
 
-    imgItem.appendChild(img)
-    outputContainer.insertBefore(imgItem, outputContainer.firstChild)
+    res.output.forEach((result, index) => {
+        if(typeof res != 'object') return
 
-    return imgItem
+        const imageData = result?.data || result?.path + '?t=' + new Date().getTime(),
+            imageSeed = result?.seed,
+            imageWidth = req.width,
+            imageHeight = req.height;
+
+        if (!imageData.includes('/')) {
+            // res contained no data for the image, stop execution
+
+            setStatus('request', 'invalid image', 'error')
+            return
+        }
+
+        let imageItemElem = (index < imageItemElements.length ? imageItemElements[index] : null)
+
+        if(!imageItemElem) {
+            imageItemElem = document.createElement('div')
+            imageItemElem.className = 'imgItem'
+            imageItemElem.innerHTML = `
+                <div class="imgContainer">
+                    <img/>
+                    <div class="imgItemInfo">
+                        <span class="imgSeedLabel"></span>
+                        <button class="imgUseBtn">Use as Input</button>
+                        <button class="imgSaveBtn">Download</button>
+                    </div>
+                </div>
+            `
+
+            const useAsInputBtn = imageItemElem.querySelector('.imgUseBtn'),
+                saveImageBtn = imageItemElem.querySelector('.imgSaveBtn');
+
+            useAsInputBtn.addEventListener('click', getUseAsInputHandler(imageItemElem))
+            saveImageBtn.addEventListener('click', getSaveImageHandler(imageItemElem))
+
+            outputContainer.appendChild(imageItemElem)
+        }
+
+        const imageElem = imageItemElem.querySelector('img'),
+            imageSeedLabel = imageItemElem.querySelector('.imgSeedLabel');
+
+        imageElem.src = imageData
+        imageElem.width = parseInt(imageWidth)
+        imageElem.height = parseInt(imageHeight)
+        imageElem.setAttribute('data-seed', imageSeed)
+
+        const imageInfo = imageItemElem.querySelector('.imgItemInfo')
+        imageInfo.style.visibility = (livePreview ? 'hidden' : 'visible')
+
+        imageSeedLabel.innerText = 'Seed: ' + imageSeed
+    })
+}
+
+function getUseAsInputHandler(imageItemElem) {
+    return function() {
+        const imageElem = imageItemElem.querySelector('img')
+        const imgData = imageElem.src
+        const imageSeed = imageElem.getAttribute('data-seed')
+
+        initImageSelector.value = null
+        initImagePreview.src = imgData
+
+        initImagePreviewContainer.style.display = 'block'
+        inpaintingEditorContainer.style.display = 'none'
+        promptStrengthContainer.style.display = 'block'
+        maskSetting.checked = false
+        samplerSelectionContainer.style.display = 'none'
+
+        // maskSetting.style.display = 'block'
+
+        randomSeedField.checked = false
+        seedField.value = imageSeed
+        seedField.disabled = false
+    }
+}
+
+function getSaveImageHandler(imageItemElem) {
+    return function() {
+        const imageElem = imageItemElem.querySelector('img')
+        const imgData = imageElem.src
+        const imageSeed = imageElem.getAttribute('data-seed')
+
+        const imgDownload = document.createElement('a')
+        imgDownload.download = createFileName(imageSeed)
+        imgDownload.href = imgData
+        imgDownload.click()
+    }
 }
 
 // makes a single image. don't call this directly, use makeImage() instead
@@ -281,7 +363,10 @@ async function doMakeImage(task) {
 
     const reqBody = task.reqBody
     const batchCount = task.batchCount
-    const outputContainer = task.outputContainer
+    const outputContainer = document.createElement('div')
+
+    outputContainer.className = 'img-batch'
+    task.outputContainer.insertBefore(outputContainer, task.outputContainer.firstChild)
 
     const outputMsg = task['outputMsg']
     const previewPrompt = task['previewPrompt']
@@ -291,14 +376,6 @@ async function doMakeImage(task) {
     let seed = reqBody['seed']
     let numOutputs = parseInt(reqBody['num_outputs'])
 
-    let images = []
-
-    function makeImageContainers(numImages) {
-        for (let i = images.length; i < numImages; i++) {
-            images.push(makeImageElement(reqBody.width, reqBody.height, outputContainer))
-        }
-    }
-
     try {
         res = await fetch('/image', {
             method: 'POST',
@@ -351,14 +428,7 @@ async function doMakeImage(task) {
                         outputMsg.style.display = 'block'
 
                         if (stepUpdate.output !== undefined) {
-                            makeImageContainers(numOutputs)
-
-                            for (idx in stepUpdate.output) {
-                                let imgItem = images[idx]
-                                let img = imgItem.firstChild
-                                let tmpImageData = stepUpdate.output[idx]
-                                img.src = tmpImageData['path'] + '?t=' + new Date().getTime()
-                            }
+                            showImages(reqBody, stepUpdate, outputContainer, true)
                         }
                     }
                 } catch (e) {
@@ -426,85 +496,11 @@ async function doMakeImage(task) {
         res = undefined
     }
 
-    if (!res) {
-        return false
-    }
+    if (!res) return false
 
     lastPromptUsed = reqBody['prompt']
 
-    makeImageContainers(res.output.length)
-
-    for (let idx in res.output) {
-        let imgBody = ''
-        let seed = 0
-
-        try {
-            let imgData = res.output[idx]
-            imgBody = imgData.data
-            seed = imgData.seed
-        } catch (e) {
-            console.log(imgBody)
-            setStatus('request', 'invalid image', 'error')
-            continue
-        }
-
-        let imgItem = images[idx]
-        let img = imgItem.firstChild
-
-        img.src = imgBody
-
-        let imgItemInfo = document.createElement('span')
-        imgItemInfo.className = 'imgItemInfo'
-        imgItemInfo.style.opacity = 0
-
-        let imgSeedLabel = document.createElement('span')
-        imgSeedLabel.className = 'imgSeedLabel'
-        imgSeedLabel.innerText = 'Seed: ' + seed
-
-        let imgUseBtn = document.createElement('button')
-        imgUseBtn.className = 'imgUseBtn'
-        imgUseBtn.innerText = 'Use as Input'
-
-        let imgSaveBtn = document.createElement('button')
-        imgSaveBtn.className = 'imgSaveBtn'
-        imgSaveBtn.innerText = 'Download'
-
-        imgItem.appendChild(imgItemInfo)
-        imgItemInfo.appendChild(imgSeedLabel)
-        imgItemInfo.appendChild(imgUseBtn)
-        imgItemInfo.appendChild(imgSaveBtn)
-
-        imgUseBtn.addEventListener('click', function() {
-            initImageSelector.value = null
-            initImagePreview.src = imgBody
-
-            initImagePreviewContainer.style.display = 'block'
-            inpaintingEditorContainer.style.display = 'none'
-            promptStrengthContainer.style.display = 'block'
-            maskSetting.checked = false
-
-            // maskSetting.style.display = 'block'
-
-            randomSeedField.checked = false
-            seedField.value = seed
-            seedField.disabled = false
-        })
-
-        imgSaveBtn.addEventListener('click', function() {
-            let imgDownload = document.createElement('a')
-            imgDownload.download = createFileName();
-            imgDownload.href = imgBody
-            imgDownload.click()
-        })
-
-        imgItem.addEventListener('mouseenter', function() {
-            imgItemInfo.style.opacity = 1
-        })
-
-        imgItem.addEventListener('mouseleave', function() {
-            imgItemInfo.style.opacity = 0
-        })
-    }
+    showImages(reqBody, res, outputContainer, false)
 
     return true
 }
@@ -547,7 +543,6 @@ async function checkTasks() {
     task['stopTask'].innerHTML = '<i class="fa-solid fa-circle-stop"></i> Stop'
     task['taskStatusLabel'].innerText = "Processing"
     task['taskStatusLabel'].className += " activeTaskLabel"
-    console.log(task['taskStatusLabel'].className)
 
     for (let i = 0; i < task.batchCount; i++) {
         task.reqBody['seed'] = task.seed + (i * task.reqBody['num_outputs'])
@@ -612,8 +607,8 @@ async function makeImage() {
 
     let prompt = promptField.value
     if (activeTags.length > 0) {
-        let promptTags = activeTags.map(x => x.name).join(", ");
-        prompt += ", " + promptTags;
+        let promptTags = activeTags.map(x => x.name).join(", ")
+        prompt += ", " + promptTags
     }
 
     let reqBody = {
@@ -736,12 +731,11 @@ async function makeImage() {
 
 // create a file name with embedded prompt and metadata
 // for easier cateloging and comparison
-function createFileName() {
+function createFileName(seed) {
 
     // Most important information is the prompt
     let underscoreName = lastPromptUsed.replace(/[^a-zA-Z0-9]/g, '_')
     underscoreName = underscoreName.substring(0, 100)
-    const seed = seedField.value
     const steps = numInferenceStepsField.value
     const guidance =  guidanceScaleField.value
 
@@ -749,20 +743,20 @@ function createFileName() {
     let fileName = `${underscoreName}_Seed-${seed}_Steps-${steps}_Guidance-${guidance}`
 
     // add the tags
-    // let tags = [];
-    // let tagString = '';
+    // let tags = []
+    // let tagString = ''
     // document.querySelectorAll(modifyTagsSelector).forEach(function(tag) {
-    //     tags.push(tag.innerHTML);
+    //     tags.push(tag.innerHTML)
     // })
 
     // join the tags with a pipe
     // if (activeTags.length > 0) {
-    //     tagString = '_Tags-';
-    //     tagString += tags.join('|');
+    //     tagString = '_Tags-'
+    //     tagString += tags.join('|')
     // }
 
     // // append empty or populated tags
-    // fileName += `${tagString}`;
+    // fileName += `${tagString}`
 
     // add the file extension
     fileName += `.png`
@@ -1037,25 +1031,25 @@ maskSetting.addEventListener('click', function() {
 // https://stackoverflow.com/a/8212878
 function millisecondsToStr(milliseconds) {
     function numberEnding (number) {
-        return (number > 1) ? 's' : '';
+        return (number > 1) ? 's' : ''
     }
 
-    var temp = Math.floor(milliseconds / 1000);
-    var hours = Math.floor((temp %= 86400) / 3600);
+    var temp = Math.floor(milliseconds / 1000)
+    var hours = Math.floor((temp %= 86400) / 3600)
     var s = ''
     if (hours) {
-        s += hours + ' hour' + numberEnding(hours) + ' ';
+        s += hours + ' hour' + numberEnding(hours) + ' '
     }
-    var minutes = Math.floor((temp %= 3600) / 60);
+    var minutes = Math.floor((temp %= 3600) / 60)
     if (minutes) {
-        s += minutes + ' minute' + numberEnding(minutes) + ' ';
+        s += minutes + ' minute' + numberEnding(minutes) + ' '
     }
-    var seconds = temp % 60;
+    var seconds = temp % 60
     if (!hours && minutes < 4 && seconds) {
-        s += seconds + ' second' + numberEnding(seconds);
+        s += seconds + ' second' + numberEnding(seconds)
     }
 
-    return s;
+    return s
 }
 
 // https://gomakethings.com/finding-the-next-and-previous-sibling-elements-that-match-a-selector-with-vanilla-js/
@@ -1115,33 +1109,33 @@ function createCollapsibles(node) {
 createCollapsibles()
 
 function refreshTagsList() {
-    editorModifierTagsList.innerHTML = '';
+    editorModifierTagsList.innerHTML = ''
 
     if (activeTags.length == 0) {
-        editorTagsContainer.style.display = 'none';
-        return;
+        editorTagsContainer.style.display = 'none'
+        return
     } else {
-        editorTagsContainer.style.display = 'block';
+        editorTagsContainer.style.display = 'block'
     }
 
     activeTags.forEach((tag, index) => {
-        tag.element.querySelector('.modifier-card-image-overlay').innerText = '-';
-        tag.element.classList.add('modifier-card-tiny');
+        tag.element.querySelector('.modifier-card-image-overlay').innerText = '-'
+        tag.element.classList.add('modifier-card-tiny')
 
-        editorModifierTagsList.appendChild(tag.element);
+        editorModifierTagsList.appendChild(tag.element)
 
         tag.element.addEventListener('click', () => {
-            let idx = activeTags.indexOf(tag);
+            let idx = activeTags.indexOf(tag)
 
             if (idx !== -1) {
-                activeTags[idx].originElement.classList.remove(activeCardClass);
-                activeTags[idx].originElement.querySelector('.modifier-card-image-overlay').innerText = '+';
+                activeTags[idx].originElement.classList.remove(activeCardClass)
+                activeTags[idx].originElement.querySelector('.modifier-card-image-overlay').innerText = '+'
 
-                activeTags.splice(idx, 1);
-                refreshTagsList();
+                activeTags.splice(idx, 1)
+                refreshTagsList()
             }
-        });
-    });
+        })
+    })
 
     let brk = document.createElement('br')
     brk.style.clear = 'both'
@@ -1170,8 +1164,8 @@ async function getDiskPath() {
 }
 
 function createModifierCard(name, previews) {
-    const modifierCard = document.createElement('div');
-    modifierCard.className = 'modifier-card';
+    const modifierCard = document.createElement('div')
+    modifierCard.className = 'modifier-card'
     modifierCard.innerHTML = `
     <div class="modifier-card-overlay"></div>
     <div class="modifier-card-image-container">
@@ -1181,96 +1175,96 @@ function createModifierCard(name, previews) {
     </div>
     <div class="modifier-card-container">
         <div class="modifier-card-label"><p></p></div>
-    </div>`;
+    </div>`
 
-    const image = modifierCard.querySelector('.modifier-card-image');
-    const errorText =  modifierCard.querySelector('.modifier-card-error-label');
-    const label = modifierCard.querySelector('.modifier-card-label');
+    const image = modifierCard.querySelector('.modifier-card-image')
+    const errorText =  modifierCard.querySelector('.modifier-card-error-label')
+    const label = modifierCard.querySelector('.modifier-card-label')
 
-    errorText.innerText = 'No Image';
+    errorText.innerText = 'No Image'
 
     if (typeof previews == 'object') {
         image.src = previews[0]; // portrait
-        image.setAttribute('preview-type', 'portrait');
+        image.setAttribute('preview-type', 'portrait')
     } else {
-        image.remove();
+        image.remove()
     }
 
-    const maxLabelLength = 30;
-    const nameWithoutBy = name.replace('by ', '');
+    const maxLabelLength = 30
+    const nameWithoutBy = name.replace('by ', '')
 
     if(nameWithoutBy.length <= maxLabelLength) {
-        label.querySelector('p').innerText = nameWithoutBy;
+        label.querySelector('p').innerText = nameWithoutBy
     } else {
-        const tooltipText = document.createElement('span');
-        tooltipText.className = 'tooltip-text';
-        tooltipText.innerText = name;
+        const tooltipText = document.createElement('span')
+        tooltipText.className = 'tooltip-text'
+        tooltipText.innerText = name
 
-        label.classList.add('tooltip');
-        label.appendChild(tooltipText);
+        label.classList.add('tooltip')
+        label.appendChild(tooltipText)
 
-        label.querySelector('p').innerText = nameWithoutBy.substring(0, maxLabelLength) + '...';
+        label.querySelector('p').innerText = nameWithoutBy.substring(0, maxLabelLength) + '...'
     }
 
-    return modifierCard;
+    return modifierCard
 }
 
 function changePreviewImages(val) {
-    const previewImages = document.querySelectorAll('.modifier-card-image-container img');
+    const previewImages = document.querySelectorAll('.modifier-card-image-container img')
 
-    let previewArr = [];
+    let previewArr = []
 
-    modifiers.map(x => x.modifiers).forEach(x => previewArr.push(...x.map(m => m.previews)));
+    modifiers.map(x => x.modifiers).forEach(x => previewArr.push(...x.map(m => m.previews)))
     
     previewArr = previewArr.map(x => {
-        let obj = {};
+        let obj = {}
 
         x.forEach(preview => {
-            obj[preview.name] = preview.path;
-        });
+            obj[preview.name] = preview.path
+        })
         
-        return obj;
-    });
+        return obj
+    })
 
     previewImages.forEach(previewImage => {
-        const currentPreviewType = previewImage.getAttribute('preview-type');
-        const relativePreviewPath = previewImage.src.split(modifierThumbnailPath + '/').pop();
+        const currentPreviewType = previewImage.getAttribute('preview-type')
+        const relativePreviewPath = previewImage.src.split(modifierThumbnailPath + '/').pop()
 
-        const previews = previewArr.find(preview => relativePreviewPath == preview[currentPreviewType]);
+        const previews = previewArr.find(preview => relativePreviewPath == preview[currentPreviewType])
 
         if(typeof previews == 'object') {
-            let preview = null;
+            let preview = null
 
             if (val == 'portrait') {
-                preview = previews.portrait;
+                preview = previews.portrait
             }
             else if (val == 'landscape') {
-                preview = previews.landscape;
+                preview = previews.landscape
             }
 
             if(preview != null) {
-                previewImage.src = `${modifierThumbnailPath}/${preview}`;
-                previewImage.setAttribute('preview-type', val);
+                previewImage.src = `${modifierThumbnailPath}/${preview}`
+                previewImage.setAttribute('preview-type', val)
             }
         }
-    });
+    })
 }
 
 function resizeModifierCards(val) {
-    const cardSizePrefix = 'modifier-card-size_';
-    const modifierCardClass = 'modifier-card';
+    const cardSizePrefix = 'modifier-card-size_'
+    const modifierCardClass = 'modifier-card'
 
-    const modifierCards = document.querySelectorAll(`.${modifierCardClass}`);
-    const cardSize = n => `${cardSizePrefix}${n}`;
+    const modifierCards = document.querySelectorAll(`.${modifierCardClass}`)
+    const cardSize = n => `${cardSizePrefix}${n}`
 
     modifierCards.forEach(card => {
         // remove existing size classes
-        const classes = card.className.split(' ').filter(c => !c.startsWith(cardSizePrefix));
-        card.className = classes.join(' ').trim();
+        const classes = card.className.split(' ').filter(c => !c.startsWith(cardSizePrefix))
+        card.className = classes.join(' ').trim()
 
         if(val != 0)
-            card.classList.add(cardSize(val));
-    });
+            card.classList.add(cardSize(val))
+    })
 }
 
 async function loadModifiers() {
@@ -1282,15 +1276,15 @@ async function loadModifiers() {
             modifiers = res; // update global variable
 
             res.forEach((modifierGroup, idx) => {
-                const title = modifierGroup.category;
-                const modifiers = modifierGroup.modifiers;
+                const title = modifierGroup.category
+                const modifiers = modifierGroup.modifiers
 
-                const titleEl = document.createElement('h5');
-                titleEl.className = 'collapsible';
-                titleEl.innerText = title;
+                const titleEl = document.createElement('h5')
+                titleEl.className = 'collapsible'
+                titleEl.innerText = title
 
-                const modifiersEl = document.createElement('div');
-                modifiersEl.classList.add('collapsible-content', 'editor-modifiers-leaf');
+                const modifiersEl = document.createElement('div')
+                modifiersEl.classList.add('collapsible-content', 'editor-modifiers-leaf')
 
                 if (idx == 0) {
                     titleEl.className += ' active'
@@ -1298,21 +1292,21 @@ async function loadModifiers() {
                 }
 
                 modifiers.forEach(modObj => {
-                    const modifierName = modObj.modifier;
-                    const modifierPreviews = modObj?.previews?.map(preview => `${modifierThumbnailPath}/${preview.path}`);
+                    const modifierName = modObj.modifier
+                    const modifierPreviews = modObj?.previews?.map(preview => `${modifierThumbnailPath}/${preview.path}`)
 
-                    const modifierCard = createModifierCard(modifierName, modifierPreviews);
+                    const modifierCard = createModifierCard(modifierName, modifierPreviews)
 
                     if(typeof modifierCard == 'object') {
-                        modifiersEl.appendChild(modifierCard);
+                        modifiersEl.appendChild(modifierCard)
 
                         modifierCard.addEventListener('click', () => {
                             if (activeTags.map(x => x.name).includes(modifierName)) {
                                 // remove modifier from active array
-                                activeTags = activeTags.filter(x => x.name != modifierName);
-                                modifierCard.classList.remove(activeCardClass);
+                                activeTags = activeTags.filter(x => x.name != modifierName)
+                                modifierCard.classList.remove(activeCardClass)
                                 
-                                modifierCard.querySelector('.modifier-card-image-overlay').innerText = '+';
+                                modifierCard.querySelector('.modifier-card-image-overlay').innerText = '+'
                             } else {
                                 // add modifier to active array
                                 activeTags.push({
@@ -1320,17 +1314,17 @@ async function loadModifiers() {
                                     'element': modifierCard.cloneNode(true),
                                     'originElement': modifierCard,
                                     'previews': modifierPreviews
-                                });
+                                })
 
-                                modifierCard.classList.add(activeCardClass);
+                                modifierCard.classList.add(activeCardClass)
 
-                                modifierCard.querySelector('.modifier-card-image-overlay').innerText = '-';
+                                modifierCard.querySelector('.modifier-card-image-overlay').innerText = '-'
                             }
 
-                            refreshTagsList();
-                        });
+                            refreshTagsList()
+                        })
                     }
-                });
+                })
 
                 let brk = document.createElement('br')
                 brk.style.clear = 'both'

ui/sd_internal/__init__.py

@@ -23,6 +23,7 @@ class Request:
     use_face_correction: str = None # or "GFPGANv1.3"
     use_upscale: str = None # or "RealESRGAN_x4plus" or "RealESRGAN_x4plus_anime_6B"
     show_only_filtered_image: bool = False
+    output_format: str = "jpeg" # "png", "jpeg"
 
     stream_progress_updates: bool = False
     stream_image_progress: bool = False
@@ -42,6 +43,7 @@ class Request:
             "sampler": self.sampler,
             "use_face_correction": self.use_face_correction,
             "use_upscale": self.use_upscale,
+            "output_format": self.output_format,
         }
 
     def to_string(self):
@@ -63,6 +65,7 @@ class Request:
     use_face_correction: {self.use_face_correction}
     use_upscale: {self.use_upscale}
     show_only_filtered_image: {self.show_only_filtered_image}
+    output_format: {self.output_format}
 
     stream_progress_updates: {self.stream_progress_updates}
     stream_image_progress: {self.stream_image_progress}'''

ui/sd_internal/custom_sd.patch

@@ -0,0 +1,46 @@
+diff --git a/ldm/dream/conditioning.py b/ldm/dream/conditioning.py
+index dfa1089..e4908ad 100644
+--- a/ldm/dream/conditioning.py
++++ b/ldm/dream/conditioning.py
+@@ -12,8 +12,8 @@ log_tokenization()              print out colour-coded tokens and warn if trunca
+ import re
+ import torch
+ 
+-def get_uc_and_c(prompt, model, log_tokens=False, skip_normalize=False):
+-    uc = model.get_learned_conditioning([''])
++def get_uc_and_c(prompt, model, log_tokens=False, skip_normalize=False, negative_prompt=''):
++    uc = model.get_learned_conditioning([negative_prompt])
+ 
+     # get weighted sub-prompts
+     weighted_subprompts = split_weighted_subprompts(
+diff --git a/ldm/generate.py b/ldm/generate.py
+index 8f67403..d88ce2d 100644
+--- a/ldm/generate.py
++++ b/ldm/generate.py
+@@ -205,6 +205,7 @@ class Generate:
+             init_mask      =    None,
+             fit            =    False,
+             strength       =    None,
++            init_img_is_path =  True,
+             # these are specific to GFPGAN/ESRGAN
+             gfpgan_strength=    0,
+             save_original  =    False,
+@@ -303,11 +304,15 @@ class Generate:
+             uc, c = get_uc_and_c(
+                 prompt, model=self.model,
+                 skip_normalize=skip_normalize,
+-                log_tokens=self.log_tokenization
++                log_tokens=self.log_tokenization,
++                negative_prompt=(args['negative_prompt'] if 'negative_prompt' in args else '')
+             )
+ 
+-            (init_image,mask_image) = self._make_images(init_img,init_mask, width, height, fit)
+-            
++            if init_img_is_path:
++                (init_image,mask_image) = self._make_images(init_img,init_mask, width, height, fit)
++            else:
++                (init_image,mask_image) = (init_img, init_mask)
++
+             if (init_image is not None) and (mask_image is not None):
+                 generator = self._make_inpaint()
+             elif init_image is not None:

ui/sd_internal/runtime.py

@@ -0,0 +1,409 @@
+import sys
+import os
+import uuid
+import re
+import torch
+import traceback
+import numpy as np
+from omegaconf import OmegaConf
+from pytorch_lightning import logging
+from einops import rearrange
+from PIL import Image, ImageOps, ImageChops
+from ldm.generate import Generate
+import transformers
+
+from gfpgan import GFPGANer
+from basicsr.archs.rrdbnet_arch import RRDBNet
+from realesrgan import RealESRGANer
+
+transformers.logging.set_verbosity_error()
+
+from . import Request, Response, Image as ResponseImage
+import base64
+import json
+from io import BytesIO
+
+filename_regex = re.compile('[^a-zA-Z0-9]')
+
+generator = None
+
+gfpgan_file = None
+real_esrgan_file = None
+model_gfpgan = None
+model_real_esrgan = None
+
+device = None
+precision = 'autocast'
+
+has_valid_gpu = False
+force_full_precision = False
+
+# local
+stop_processing = False
+temp_images = {}
+
+try:
+    gpu = torch.cuda.current_device()
+    gpu_name = torch.cuda.get_device_name(gpu)
+    print('GPU detected: ', gpu_name)
+
+    force_full_precision = ('nvidia' in gpu_name.lower() or 'geforce' in gpu_name.lower()) and (' 1660' in gpu_name or ' 1650' in gpu_name) # otherwise these NVIDIA cards create green images
+    if force_full_precision:
+        print('forcing full precision on NVIDIA 16xx cards, to avoid green images. GPU detected: ', gpu_name)
+
+    mem_free, mem_total = torch.cuda.mem_get_info(gpu)
+    mem_total /= float(10**9)
+    if mem_total < 3.0:
+        print("GPUs with less than 3 GB of VRAM are not compatible with Stable Diffusion")
+        raise Exception()
+
+    has_valid_gpu = True
+except:
+    print('WARNING: No compatible GPU found. Using the CPU, but this will be very slow!')
+    pass
+
+def load_model_ckpt(ckpt_to_use, device_to_use='cuda', precision_to_use='autocast'):
+    global generator
+
+    device = device_to_use if has_valid_gpu else 'cpu'
+    precision = precision_to_use if not force_full_precision else 'full'
+
+    try:
+        config = 'configs/models.yaml'
+        model = 'stable-diffusion-1.4'
+
+        models = OmegaConf.load(config)
+        width = models[model].width
+        height = models[model].height
+        config = models[model].config
+        weights = ckpt_to_use + '.ckpt'
+    except (FileNotFoundError, IOError, KeyError) as e:
+        print(f'{e}. Aborting.')
+        sys.exit(-1)
+
+    generator = Generate(
+        width=width,
+        height=height,
+        sampler_name='ddim',
+        weights=weights,
+        full_precision=(precision == 'full'),
+        config=config,
+        grid=False,
+        # this is solely for recreating the prompt
+        seamless=False,
+        embedding_path=None,
+        device_type=device,
+        ignore_ctrl_c=True,
+    )
+
+    # gets rid of annoying messages about random seed
+    logging.getLogger('pytorch_lightning').setLevel(logging.ERROR)
+
+    # preload the model
+    generator.load_model()
+
+def load_model_gfpgan(gfpgan_to_use):
+    global gfpgan_file, model_gfpgan
+
+    if gfpgan_to_use is None:
+        return
+
+    gfpgan_file = gfpgan_to_use
+    model_path = gfpgan_to_use + ".pth"
+
+    if device == 'cpu':
+        model_gfpgan = GFPGANer(model_path=model_path, upscale=1, arch='clean', channel_multiplier=2, bg_upsampler=None, device=torch.device('cpu'))
+    else:
+        model_gfpgan = GFPGANer(model_path=model_path, upscale=1, arch='clean', channel_multiplier=2, bg_upsampler=None, device=torch.device('cuda'))
+
+    print('loaded ', gfpgan_to_use, 'to', device, 'precision', precision)
+
+def load_model_real_esrgan(real_esrgan_to_use):
+    global real_esrgan_file, model_real_esrgan
+
+    if real_esrgan_to_use is None:
+        return
+
+    real_esrgan_file = real_esrgan_to_use
+    model_path = real_esrgan_to_use + ".pth"
+
+    RealESRGAN_models = {
+        'RealESRGAN_x4plus': RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4),
+        'RealESRGAN_x4plus_anime_6B': RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=6, num_grow_ch=32, scale=4)
+    }
+
+    model_to_use = RealESRGAN_models[real_esrgan_to_use]
+
+    if device == 'cpu':
+        model_real_esrgan = RealESRGANer(scale=2, model_path=model_path, model=model_to_use, pre_pad=0, half=False) # cpu does not support half
+        model_real_esrgan.device = torch.device('cpu')
+        model_real_esrgan.model.to('cpu')
+    else:
+        model_real_esrgan = RealESRGANer(scale=2, model_path=model_path, model=model_to_use, pre_pad=0, half=(precision != 'full'))
+
+    model_real_esrgan.model.name = real_esrgan_to_use
+
+    print('loaded ', real_esrgan_to_use, 'to', device, 'precision', precision)
+
+def mk_img(req: Request):
+    try:
+        yield from do_mk_img(req)
+    except Exception as e:
+        print(traceback.format_exc())
+
+        gc()
+
+        # if device != "cpu":
+        #     modelFS.to("cpu")
+        #     modelCS.to("cpu")
+
+        #     model.model1.to("cpu")
+        #     model.model2.to("cpu")
+
+        # gc()
+
+        yield json.dumps({
+            "status": 'failed',
+            "detail": str(e)
+        })
+
+def do_mk_img(req: Request):
+    stop_processing = False
+
+    if req.use_face_correction != gfpgan_file:
+        load_model_gfpgan(req.use_face_correction)
+
+    if req.use_upscale != real_esrgan_file:
+        load_model_real_esrgan(req.use_upscale)
+
+    init_image = None
+    init_mask = None
+
+    if req.init_image is not None:
+        image = base64_str_to_img(req.init_image)
+
+        w, h = image.size
+        print(f"loaded input image of size ({w}, {h}) from base64")
+        if req.width is not None and req.height is not None:
+            h, w = req.height, req.width
+
+        w, h = map(lambda x: x - x % 64, (w, h))  # resize to integer multiple of 64
+        image = image.resize((w, h), resample=Image.Resampling.LANCZOS)
+        init_image = generator._create_init_image(image)
+
+        if generator._has_transparency(image) and req.mask is None:      # if image has a transparent area and no mask was provided, then try to generate mask
+            print('>> Initial image has transparent areas. Will inpaint in these regions.')
+            if generator._check_for_erasure(image):
+                print(
+                    '>> WARNING: Colors underneath the transparent region seem to have been erased.\n',
+                    '>>          Inpainting will be suboptimal. Please preserve the colors when making\n',
+                    '>>          a transparency mask, or provide mask explicitly using --init_mask (-M).'
+                )
+            init_mask = generator._create_init_mask(image)                   # this returns a torch tensor
+
+        if device != "cpu" and precision != "full":
+            init_image = init_image.half()
+
+        if req.mask is not None:
+            image = base64_str_to_img(req.mask)
+
+            image = ImageChops.invert(image)
+
+            w, h = image.size
+            print(f"loaded input image of size ({w}, {h}) from base64")
+            if req.width is not None and req.height is not None:
+                h, w = req.height, req.width
+
+            w, h = map(lambda x: x - x % 64, (w, h))  # resize to integer multiple of 64
+            image = image.resize((w, h), resample=Image.Resampling.LANCZOS)
+
+            init_mask = generator._create_init_mask(image)
+
+        if init_mask is not None:
+            req.sampler = 'plms' # hack to force the underlying implementation to initialize DDIM properly
+
+    result = generator.prompt2image(
+        req.prompt,
+        iterations     =    req.num_outputs,
+        steps          =    req.num_inference_steps,
+        seed           =    req.seed,
+        cfg_scale      =    req.guidance_scale,
+        ddim_eta       =    0.0,
+        skip_normalize =    False,
+        image_callback =    None,
+        step_callback  =    None,
+        width          =    req.width,
+        height         =    req.height,
+        sampler_name   =    req.sampler,
+        seamless       =    False,
+        log_tokenization=  False,
+        with_variations =   None,
+        variation_amount =  0.0,
+        # these are specific to img2img and inpaint
+        init_img       =    init_image,
+        init_mask      =    init_mask,
+        fit            =    False,
+        strength       =    req.prompt_strength,
+        init_img_is_path = False,
+        # these are specific to GFPGAN/ESRGAN
+        gfpgan_strength=    0,
+        save_original  =    False,
+        upscale        =    None,
+        negative_prompt=    req.negative_prompt,
+    )
+
+    has_filters =   (req.use_face_correction is not None and req.use_face_correction.startswith('GFPGAN')) or \
+                    (req.use_upscale is not None and req.use_upscale.startswith('RealESRGAN'))
+
+    print('has filter', has_filters)
+
+    return_orig_img = not has_filters or not req.show_only_filtered_image
+
+    res = Response()
+    res.request = req
+    res.images = []
+
+    if req.save_to_disk_path is not None:
+        session_out_path = os.path.join(req.save_to_disk_path, req.session_id)
+        os.makedirs(session_out_path, exist_ok=True)
+    else:
+        session_out_path = None
+
+    for img, seed in result:
+        if req.save_to_disk_path is not None:
+            prompt_flattened = filename_regex.sub('_', req.prompt)
+            prompt_flattened = prompt_flattened[:50]
+
+            img_id = str(uuid.uuid4())[-8:]
+
+            file_path = f"{prompt_flattened}_{img_id}"
+            img_out_path = os.path.join(session_out_path, f"{file_path}.{req.output_format}")
+            meta_out_path = os.path.join(session_out_path, f"{file_path}.txt")
+
+            if return_orig_img:
+                save_image(img, img_out_path)
+
+            save_metadata(meta_out_path, req.prompt, seed, req.width, req.height, req.num_inference_steps, req.guidance_scale, req.prompt_strength, req.use_face_correction, req.use_upscale, req.sampler, req.negative_prompt)
+
+        if return_orig_img:
+            img_data = img_to_base64_str(img)
+            res_image_orig = ResponseImage(data=img_data, seed=seed)
+            res.images.append(res_image_orig)
+
+            if req.save_to_disk_path is not None:
+                res_image_orig.path_abs = img_out_path
+
+        if has_filters and not stop_processing:
+            print('Applying filters..')
+
+            gc()
+            filters_applied = []
+
+            np_img = img.convert('RGB')
+            np_img = np.array(np_img, dtype=np.uint8)
+
+            if req.use_face_correction:
+                _, _, np_img = model_gfpgan.enhance(np_img, has_aligned=False, only_center_face=False, paste_back=True)
+                filters_applied.append(req.use_face_correction)
+
+            if req.use_upscale:
+                np_img, _ = model_real_esrgan.enhance(np_img)
+                filters_applied.append(req.use_upscale)
+
+            filtered_image = Image.fromarray(np_img)
+
+            filtered_img_data = img_to_base64_str(filtered_image)
+            res_image_filtered = ResponseImage(data=filtered_img_data, seed=seed)
+            res.images.append(res_image_filtered)
+
+            filters_applied = "_".join(filters_applied)
+
+            if req.save_to_disk_path is not None:
+                filtered_img_out_path = os.path.join(session_out_path, f"{file_path}_{filters_applied}.{req.output_format}")
+                save_image(filtered_image, filtered_img_out_path)
+                res_image_filtered.path_abs = filtered_img_out_path
+
+            del filtered_image
+        
+        del img
+
+    print('Task completed')
+
+    yield json.dumps(res.json())
+
+def save_image(img, img_out_path):
+    try:
+        img.save(img_out_path)
+    except:
+        print('could not save the file', traceback.format_exc())
+
+def save_metadata(meta_out_path, prompt, seed, width, height, num_inference_steps, guidance_scale, prompt_strength, use_correct_face, use_upscale, sampler_name, negative_prompt):
+    metadata = f"{prompt}\nWidth: {width}\nHeight: {height}\nSeed: {seed}\nSteps: {num_inference_steps}\nGuidance Scale: {guidance_scale}\nPrompt Strength: {prompt_strength}\nUse Face Correction: {use_correct_face}\nUse Upscaling: {use_upscale}\nSampler: {sampler_name}\nNegative Prompt: {negative_prompt}"
+
+    try:
+        with open(meta_out_path, 'w') as f:
+            f.write(metadata)
+    except:
+        print('could not save the file', traceback.format_exc())
+
+def gc():
+    if device == 'cpu':
+        return
+
+    torch.cuda.empty_cache()
+    torch.cuda.ipc_collect()
+
+def load_img(img_str, w0, h0):
+    image = base64_str_to_img(img_str).convert("RGB")
+    w, h = image.size
+    print(f"loaded input image of size ({w}, {h}) from base64")
+    if h0 is not None and w0 is not None:
+        h, w = h0, w0
+
+    w, h = map(lambda x: x - x % 64, (w, h))  # resize to integer multiple of 64
+    image = image.resize((w, h), resample=Image.Resampling.LANCZOS)
+    image = np.array(image).astype(np.float32) / 255.0
+    image = image[None].transpose(0, 3, 1, 2)
+    image = torch.from_numpy(image)
+    return 2.*image - 1.
+
+def load_mask(mask_str, h0, w0, newH, newW, invert=False):
+    image = base64_str_to_img(mask_str).convert("RGB")
+    w, h = image.size
+    print(f"loaded input mask of size ({w}, {h})")
+
+    if invert:
+        print("inverted")
+        image = ImageOps.invert(image)
+        # where_0, where_1 = np.where(image == 0), np.where(image == 255)
+        # image[where_0], image[where_1] = 255, 0
+
+    if h0 is not None and w0 is not None:
+        h, w = h0, w0
+
+    w, h = map(lambda x: x - x % 64, (w, h))  # resize to integer multiple of 64
+
+    print(f"New mask size ({w}, {h})")
+    image = image.resize((newW, newH), resample=Image.Resampling.LANCZOS)
+    image = np.array(image)
+
+    image = image.astype(np.float32) / 255.0
+    image = image[None].transpose(0, 3, 1, 2)
+    image = torch.from_numpy(image)
+    return image
+
+# https://stackoverflow.com/a/61114178
+def img_to_base64_str(img):
+    buffered = BytesIO()
+    img.save(buffered, format="PNG")
+    buffered.seek(0)
+    img_byte = buffered.getvalue()
+    img_str = "data:image/png;base64," + base64.b64encode(img_byte).decode()
+    return img_str
+
+def base64_str_to_img(img_str):
+    img_str = img_str[len("data:image/png;base64,"):]
+    data = base64.b64decode(img_str)
+    buffered = BytesIO(data)
+    img = Image.open(buffered)
+    return img

ui/server.py

@@ -58,6 +58,7 @@ class ImageRequest(BaseModel):
     use_face_correction: str = None # or "GFPGANv1.3"
     use_upscale: str = None # or "RealESRGAN_x4plus" or "RealESRGAN_x4plus_anime_6B"
     show_only_filtered_image: bool = False
+    output_format: str = "jpeg" # "png", "jpeg"
 
     stream_progress_updates: bool = False
     stream_image_progress: bool = False
@@ -123,6 +124,7 @@ def image(req : ImageRequest):
     r.use_upscale: str = req.use_upscale
     r.use_face_correction = req.use_face_correction
     r.show_only_filtered_image = req.show_only_filtered_image
+    r.output_format = req.output_format
 
     r.stream_progress_updates = True # the underlying implementation only supports streaming
     r.stream_image_progress = req.stream_image_progress