Update README.md

updated filename

.gitignore

@@ -1 +1,4 @@
 __pycache__
+installer
+installer.tar
+dist

Dockerfile

@@ -1,15 +0,0 @@
-FROM python:3.9
-
-RUN mkdir /app
-WORKDIR /app
-
-RUN apt update
-
-COPY requirements.txt ./
-RUN pip install --no-cache-dir -r requirements.txt
-
-COPY . .
-
-EXPOSE 9000
-
-ENTRYPOINT ["uvicorn", "main:app", "--reload", "--host", "0.0.0.0", "--port", "9000"]

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
+
+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)

OldPortDockerfile

@@ -1,15 +0,0 @@
-FROM python:3.9
-
-RUN mkdir /app
-WORKDIR /app
-
-RUN apt update
-
-COPY requirements.txt ./
-RUN pip install --no-cache-dir -r requirements.txt
-
-COPY . .
-
-EXPOSE 8000
-
-ENTRYPOINT ["uvicorn", "old_port_main:app", "--host", "0.0.0.0", "--port", "8000"]

README.md

@@ -1,38 +1,41 @@
-# Stable Diffusion UI
-### A simple way to install and use [Stable Diffusion](https://replicate.com/stability-ai/stable-diffusion) on your own computer
+# Stable Diffusion UI - v2 (beta)
+### A simple way to install and use [Stable Diffusion](https://github.com/CompVis/stable-diffusion) on your own computer (Win 10/11, Linux). No dependencies or technical knowledge required.
 
 [![Discord Server](https://badgen.net/badge/icon/discord?icon=discord&label)](https://discord.com/invite/u9yhsFmEkB) (for support, and development discussion)
 
----
-
-# What does this do?
-Two things:
-1. Automatically downloads and installs Stable Diffusion on your own computer (no need to mess with conda or environments)
-2. Gives you a simple browser-based UI to talk to your local Stable Diffusion. Enter text prompts and view the generated image. No API keys required.
-
-All the processing will happen on your computer locally, it does not transmit your prompts or process on any remote server.
+# Features in the new v2 Version:
+- **No Dependencies or Technical Knowledge Required**: 1-click install for Windows 10/11 and Linux. *No dependencies*, no need for WSL or Docker or Conda or technical setup. Just download and run!
+- **Image Modifiers**: A library of *modifier tags* like *"Realistic"*, *"Pencil Sketch"*, *"ArtStation"* etc. Experiment with various styles quickly.
+- **New UI**: with cleaner design
+- Supports "*Text to Image*" and "*Image to Image*"
+- **NSFW Setting**: A setting in the UI to control *NSFW content*
+- **Use CPU setting**: If you don't have a compatible graphics card, but still want to run it on your CPU.
+- **Auto-updater**: Gets you the latest improvements and bug-fixes to a rapidly evolving project.
 
 ![Screenshot](media/shot-v8.jpg?raw=true)
 
-
 # System Requirements
-1. Computer capable of running Stable Diffusion.
-2. Linux or Windows 11 (with [WSL](https://docs.microsoft.com/en-us/windows/wsl/install)) or Windows 10 v2004+ (Build 19041+) with [WSL](https://docs.microsoft.com/en-us/windows/wsl/install).
-3. Requires (a) [Docker](https://docs.docker.com/engine/install/), (b) [docker-compose v1.29](https://docs.docker.com/compose/install/), and (c) [nvidia-container-toolkit](https://stackoverflow.com/a/58432877).
+1. Windows 10/11, or Linux. Experimental support for Mac is coming soon.
+2. An NVIDIA graphics card, preferably with 6GB or more of VRAM. But if you don't have a compatible graphics card, you can still use it with a "Use CPU" setting. It'll be very slow, but it should still work.
 
-**Important:** If you're using Windows, please install docker inside your [WSL](https://docs.microsoft.com/en-us/windows/wsl/install)'s Linux. Install docker for the Linux distro in your WSL. **Don't install Docker for Windows.**
+You do not need anything else. You do not need WSL, Docker or Conda. The installer will take care of it.
 
 # Installation
-1. Clone this repository: `git clone https://github.com/cmdr2/stable-diffusion-ui.git` or [download the zip file](https://github.com/cmdr2/stable-diffusion-ui/archive/refs/heads/main.zip) and unzip.
-2. Open your terminal, and in the project directory run: `docker-compose up &` (warning: this will take some time during the first run, since it'll download Stable Diffusion's [docker image](https://replicate.com/stability-ai/stable-diffusion), nearly 17 GiB)
-3. Open http://localhost:9000 in your browser. That's it!
+1. Download [for Windows](https://drive.google.com/file/d/1MY5gzsQHV_KREbYs3gw33QL4gGIlQRqj/view?usp=sharing) or [for Linux](https://drive.google.com/file/d/1Gwz1LVQUCart8HhCjrmXkS6TWKbTsLsR/view?usp=sharing) (this will be hosted on GitHub in the future).
 
-If you're getting errors, please check the [Troubleshooting](https://github.com/cmdr2/stable-diffusion-ui/wiki/Troubleshooting) page.
+2. Extract:
+  - For Windows: After unzipping the file, please move the `stable-diffusion-ui` folder to your `C:` (or any drive like D: at the top root level). For e.g. `C:\stable-diffusion-ui`. This will avoid a common problem with Windows (of file path length limits).
+  - For Linux: After extracting the .tar.xz file, please open a terminal, and go to the `stable-diffusion-ui` directory.
+
+3. Run:
+  - For Windows: `Start Stable Diffusion UI.cmd` by double-clicking it.
+  - For Linux: In the terminal, run `./start.sh` (or `bash start.sh`)
+
+This will automatically install Stable Diffusion, set it up, and start the interface. No additional steps are needed.
 
-To stop the server, please run `docker-compose down`
 
 # Usage
-Open http://localhost:9000 in your browser (after running `docker-compose up &` from step 2 previously).
+Open http://localhost:9000 in your browser (after running step 3 previously).
 
 ## With a text description
 1. Enter a text prompt, like `a photograph of an astronaut riding a horse` in the textbox.
@@ -44,32 +47,32 @@ Open http://localhost:9000 in your browser (after running `docker-compose up &`
 2. An optional text prompt can help you further describe the kind of image you want to generate.
 3. Press `Make Image`. See the image generated using your prompt.
 
-You can also set an `Image Mask` for telling Stable Diffusion to draw in only the black areas in your image mask. White areas in your mask will be ignored.
-
 **Pro tip:** You can also click `Use as Input` on a generated image, to use it as the input image for your next generation. This can be useful for sequentially refining the generated image with a single click.
 
 **Another tip:** Images with the same aspect ratio of your generated image work best. E.g. 1:1 if you're generating images sized 512x512.
 
 ## Problems?
-Please [file an issue](https://github.com/cmdr2/stable-diffusion-ui/issues) if this did not work for you (after trying the common [troubleshooting](#troubleshooting) steps)!
+Please ask on the new [discord server](https://discord.com/invite/u9yhsFmEkB), or [file an issue](https://github.com/cmdr2/stable-diffusion-ui/issues) if this did not work for you (after trying the common [troubleshooting](#troubleshooting) steps)!
 
 # Advanced Settings
 You can also set the configuration like `seed`, `width`, `height`, `num_outputs`, `num_inference_steps` and `guidance_scale` using the 'show' button next to 'Advanced settings'.
 
 Use the same `seed` number to get the same image for a certain prompt. This is useful for refining a prompt without losing the basic image design. Enable the `random images` checkbox to get random images.
 
-![Screenshot of advanced settings](media/config-v4.jpg?raw=true)
+![Screenshot of advanced settings](media/config-v5.jpg?raw=true)
 
 # Troubleshooting
-The [Troubleshooting wiki page](https://github.com/cmdr2/stable-diffusion-ui/wiki/Troubleshooting) contains some common errors and their solutions. Please check that, and if it doesn't work, feel free to [file an issue](https://github.com/cmdr2/stable-diffusion-ui/issues).
+The [Troubleshooting wiki page](https://github.com/cmdr2/stable-diffusion-ui/wiki/Troubleshooting) contains some common errors and their solutions. Please check that, and if it doesn't work, feel free to ask on the [discord server](https://discord.com/invite/u9yhsFmEkB) or [file an issue](https://github.com/cmdr2/stable-diffusion-ui/issues).
 
-# Behind the scenes
-This project is a quick way to get started with Stable Diffusion. You do not need to have Stable Diffusion already installed, and do not need any API keys. This project will automatically download Stable Diffusion's docker image, the first time it is run.
+# What is this? Why no Docker?
+This version is a 1-click installer. You don't need WSL or Docker or anything beyond a working NVIDIA GPU with an updated driver. You don't need to use the command-line at all. Even if you don't have a compatible GPU, you can run it on your CPU (albeit very slowly).
 
-This project runs Stable Diffusion in a docker container behind the scenes, using Stable Diffusion's [Docker image](https://replicate.com/stability-ai/stable-diffusion) on replicate.com.
+It'll download the necessary files from the original [Stable Diffusion](https://github.com/CompVis/stable-diffusion) git repository, and set it up. It'll then start the browser-based interface like before.
+
+The NSFW option is currently off (temporarily), so it'll allow NSFW images, for those people who are unable to run their prompts without hitting the NSFW filter incorrectly.
 
 # Bugs reports and code contributions welcome
-If there are any problems or suggestions, please feel free to [file an issue](https://github.com/cmdr2/stable-diffusion-ui/issues).
+If there are any problems or suggestions, please feel free to ask on the [discord server](https://discord.com/invite/u9yhsFmEkB) or [file an issue](https://github.com/cmdr2/stable-diffusion-ui/issues).
 
 Also, please feel free to submit a pull request, if you have any code contributions in mind. Join the [discord server](https://discord.com/invite/u9yhsFmEkB) for development-related discussions, and for helping other users.
 

build.bat

@@ -0,0 +1,39 @@
+@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 "Setting up startup scripts.."
+
+@mkdir installer\etc\conda\activate.d
+@copy scripts\post_activate.bat installer\etc\conda\activate.d\
+
+@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 "Build ready. Zip the 'dist\stable-diffusion-ui' folder."
+
+@echo "Cleaning up.."
+
+@cd ..\..
+
+@rmdir /s /q installer
+
+@del installer.tar

build.sh

@@ -0,0 +1,39 @@
+#!/bin/bash
+
+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 "Build ready. Zip the 'dist/stable-diffusion-ui' folder."
+
+echo "Cleaning up.."
+
+cd ../..
+
+rm -rf installer
+
+rm installer.tar

docker-compose.yml

@@ -1,28 +0,0 @@
-version: '3.3'
-
-services:
-  stability-ai:
-    container_name: sd
-    ports:
-      - '5000:5000'
-    image: 'r8.im/stability-ai/stable-diffusion@sha256:be04660a5b93ef2aff61e3668dedb4cbeb14941e62a3fd5998364a32d613e35e'
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - capabilities: [gpu]
-
-  stable-diffusion-ui:
-    container_name: sd-ui
-    ports:
-      - '9000:9000'
-    build:
-      context: .
-      dockerfile: Dockerfile
-    volumes:
-      - .:/app
-    depends_on:
-      - stability-ai
-
-networks:
-  default:

environment.yaml

@@ -0,0 +1,7 @@
+name: stable-diffusion-ui-installer
+channels:
+  - defaults
+  - conda-forge
+dependencies:
+  - conda
+  - git

main.py

@@ -1,73 +0,0 @@
-from fastapi import FastAPI, HTTPException
-from starlette.responses import FileResponse
-from pydantic import BaseModel
-
-import requests
-
-LOCAL_SERVER_URL = 'http://stability-ai:5000'
-PREDICT_URL = LOCAL_SERVER_URL + '/predictions'
-
-app = FastAPI()
-
-# defaults from https://huggingface.co/blog/stable_diffusion
-class ImageRequest(BaseModel):
-    prompt: str
-    init_image: str = None # base64
-    mask: str = None # base64
-    num_outputs: str = "1"
-    num_inference_steps: str = "50"
-    guidance_scale: str = "7.5"
-    width: str = "512"
-    height: str = "512"
-    seed: str = "30000"
-    prompt_strength: str = "0.8"
-
-@app.get('/')
-def read_root():
-    return FileResponse('index.html')
-
-@app.get('/ping')
-async def ping():
-    try:
-        requests.get(LOCAL_SERVER_URL)
-        return {'OK'}
-    except:
-        return {'ERROR'}
-
-@app.post('/image')
-async def image(req : ImageRequest):
-    data = {
-        "input": {
-            "prompt": req.prompt,
-            "num_outputs": req.num_outputs,
-            "num_inference_steps": req.num_inference_steps,
-            "width": req.width,
-            "height": req.height,
-            "seed": req.seed,
-            "guidance_scale": req.guidance_scale,
-        }
-    }
-
-    if req.init_image is not None:
-        data['input']['init_image'] = req.init_image
-        data['input']['prompt_strength'] = req.prompt_strength
-
-        if req.mask is not None:
-            data['input']['mask'] = req.mask
-
-    if req.seed == "-1":
-        del data['input']['seed']
-
-    res = requests.post(PREDICT_URL, json=data)
-    if res.status_code != 200:
-        raise HTTPException(status_code=500, detail=res.text)
-
-    return res.json()
-
-@app.get('/media/ding.mp3')
-def read_root():
-    return FileResponse('media/ding.mp3')
-
-@app.get('/modifiers.json')
-def read_modifiers():
-    return FileResponse('modifiers.json')

modifiers.json

@@ -1,92 +0,0 @@
-[
-    ["Drawing Style", [
-        "Sketch",
-        "Doodle",
-        "Children's Drawing",
-        "Line Art",
-        "Dot Art",
-        "Crosshatch",
-        "Detailed and Intricate",
-        "Cel Shading"
-    ]],
-    ["Visual Style", [
-        "2D",
-        "Cartoon",
-        "8-bit",
-        "16-bit",
-        "Graphic Novel",
-        "Visual Novel",
-        "Street Art",
-        "Fantasy",
-        "Realistic",
-        "Photo",
-        "Hard Edge Painting",
-        "Mural",
-        "Mosaic",
-        "Hydrodipped",
-        "Modern Art",
-        "Concept Art",
-        "Digital Art",
-        "CGI",
-        "Anaglyph",
-        "Comic Book",
-        "Lithography"
-    ]],
-    ["Pen", [
-        "Graphite",
-        "Colored Pencil",
-        "Ink",
-        "Chalk",
-        "Pastel Art",
-        "Oil Paint"
-    ]],
-    ["Carving and Etching", [
-        "Etching",
-        "Wood-Carving",
-        "Papercutting",
-        "Paper-Mache",
-        "Paper Model",
-        "Linocut",
-        "Pyrography"
-    ]],
-    ["Camera", [
-        "HD",
-        "Color Grading",
-        "Film Grain",
-        "White Balance",
-        "Golden Hour",
-        "Glamor Shot",
-        "War Photography",
-        "Lens Flare",
-        "Polaroid",
-        "Vintage"
-    ]],
-    ["Color", [
-        "Colorful",
-        "Electric Colors",
-        "Warm Color Palette",
-        "Infrared",
-        "Beautiful Lighting"
-    ]],
-    ["Emotions", [
-        "Happy",
-        "Excited",
-        "Sad",
-        "Lonely",
-        "Angry",
-        "Good",
-        "Evil"
-    ]],
-    ["Style of an artist or community", [
-        "by Andy Warhol",
-        "Artstation",
-        "by Asaf Hanuka",
-        "by Aubrey Beardsley",
-        "by H.R. Giger",
-        "by Hayao Mizaki",
-        "by Salvador Dali",
-        "by Tivadar Csontváry Kosztka",
-        "by Lisa Frank",
-        "by Pablo Piccaso"
-    ]]
-]

old_port_main.py

@@ -1,36 +0,0 @@
-from fastapi import FastAPI
-from fastapi.responses import HTMLResponse
-
-app = FastAPI()
-
-@app.get('/', response_class=HTMLResponse)
-def read_root():
-    return '''
-    <style>
-    body {
-        font-family: Arial;
-        font-size: 11pt;
-    }
-    pre {
-        display: inline;
-        background: #aaa;
-        padding: 2px;
-        border: 1px solid #777;
-        border-radius: 3px;
-    }
-    @media (prefers-color-scheme: dark) {
-        body {
-            background-color: rgb(32, 33, 36);
-            color: #eee;
-        }
-        pre {
-            background: #444;
-        }
-    }
-    </style>
-    <h4>The UI has moved to <a href="http://localhost:9000">http://localhost:9000</a>. The current address that you used (ending with :8000) will be removed in the future, so please use <a href="http://localhost:9000">http://localhost:9000</a> going ahead (and in any bookmarks you've saved).</h4>
-
-    <h3>Why has the address changed?</h3>
-    <p>The previously used port (8000) is often used by other servers, which results in port conflicts. So the project's port number has been changed, while the project is still young. Otherwise port-conflicts with 8000 will be a common source of new-user issues in the future.</p>
-    <p>Sorry about this, and apologies for the inconvenience :)</p>
-    '''

requirements.txt

@@ -1,3 +0,0 @@
-requests
-fastapi==0.80.0
-uvicorn==0.18.2

scripts/Start Stable Diffusion UI.cmd

@@ -0,0 +1 @@
+installer\Scripts\activate.bat

scripts/on_env_start.bat

@@ -0,0 +1,30 @@
+@echo. & echo "Stable Diffusion UI" & echo.
+
+@cd ..
+
+@>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.."
+
+    @cd sd-ui-files
+
+    @call git reset --hard
+    @call git pull
+
+    @cd ..
+) else (
+    @echo. & echo "Downloading Stable Diffusion UI.." & echo.
+
+    @call git clone 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. Please try re-running this installer. If it doesn't work, please copy the messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB or file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues"
+        pause
+        @exit /b
+    )
+)
+
+@xcopy sd-ui-files\ui ui /s /i /Y
+@xcopy sd-ui-files\scripts scripts /s /i /Y
+
+@call scripts\on_sd_start.bat

scripts/on_env_start.sh

@@ -0,0 +1,28 @@
+printf "\n\nStable Diffusion UI\n\n"
+
+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.."
+
+    cd sd-ui-files
+
+    git reset --hard
+    git pull
+
+    cd ..
+else
+    printf "\n\nDownloading Stable Diffusion UI..\n\n"
+
+    if git clone 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. Please try re-running this installer. If it doesn't work, please copy the messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB or file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+fi
+
+cp -Rf sd-ui-files/ui ui
+cp -Rf sd-ui-files/scripts/* scripts/
+cp "scripts/start.sh" .
+
+./scripts/on_sd_start.sh

scripts/on_sd_start.bat

@@ -0,0 +1,104 @@
+@set cmd_had_error=F
+
+@>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
+
+    @cd ..
+) else (
+    @echo. & echo "Downloading Stable Diffusion.." & echo.
+
+    @call git clone https://github.com/basujindal/stable-diffusion.git && (
+        @echo sd_git_cloned >> scripts\install_status.txt
+    ) || (
+        @set cmd_had_error=T
+    )
+
+    if "%ERRORLEVEL%" NEQ "0" (
+        @set cmd_had_error=T
+    )
+
+    if "%cmd_had_error%"=="T" (
+        @echo "Error downloading Stable Diffusion. Please try re-running this installer. If it doesn't work, please copy the messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB or file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues"
+        pause
+        @exit /b
+    )
+)
+
+@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"
+) 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
+
+    @call conda env create --prefix env -f environment.yaml && (
+        @echo conda_sd_env_created >> ..\scripts\install_status.txt
+    ) || (
+        @set cmd_had_error=T
+    )
+
+    if "%cmd_had_error%"=="T" (
+        echo "Error installing the packages necessary for Stable Diffusion. Please try re-running this installer. If it doesn't work, please copy the messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB or file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues"
+        pause
+        exit /b
+    )
+)
+
+@call conda activate .\env
+
+@>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.
+
+    @call conda install -c conda-forge -y --prefix env uvicorn fastapi && (
+        @echo conda_sd_ui_deps_installed >> ..\scripts\install_status.txt
+    ) || (
+        @set cmd_had_error=T
+    )
+
+    if "%ERRORLEVEL%" NEQ "0" (
+        @set cmd_had_error=T
+    )
+
+    if "%cmd_had_error%"=="T" (
+        echo "Error installing the packages necessary for Stable Diffusion UI. Please try re-running this installer. If it doesn't work, please copy the messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB or file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues"
+        pause
+        exit /b
+    )
+)
+
+@if exist "sd-v1-4.ckpt" (
+    echo "Data files (weights) necessary for Stable Diffusion were already downloaded"
+) else (
+    @echo. & echo "Downloading data files (weights) for Stable Diffusion.." & echo.
+
+    @call curl -L https://me.cmdr2.org/stable-diffusion-ui/sd-v1-4.ckpt > sd-v1-4.ckpt
+
+    @if not exist "sd-v1-4.ckpt" (
+        echo "Error downloading the data files (weights) for Stable Diffusion. Please try re-running this installer. If it doesn't work, please copy the messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB or file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues"
+        pause
+        exit /b
+    )
+
+    @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_UI_PATH=%cd%\..\ui
+
+@uvicorn server:app --app-dir "%SD_UI_PATH%" --port 9000 --host 0.0.0.0
+
+@pause

scripts/on_sd_start.sh

@@ -0,0 +1,80 @@
+source installer/etc/profile.d/conda.sh
+
+if [ `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
+
+    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. Please try re-running this installer. If it doesn't work, please copy the messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB or file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+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"
+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"
+
+    if conda env create --prefix env --force -f environment.yaml ; then
+        echo conda_sd_env_created >> ../scripts/install_status.txt
+    else
+        printf "\n\nError installing the packages necessary for Stable Diffusion. Please try re-running this installer. If it doesn't work, please copy the messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB or file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+fi
+
+conda activate ./env
+
+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"
+
+    if conda install -c conda-forge --prefix ./env -y uvicorn fastapi ; then
+        echo conda_sd_ui_deps_installed >> ../scripts/install_status.txt
+    else
+        printf "\n\nError installing the packages necessary for Stable Diffusion UI. Please try re-running this installer. If it doesn't work, please copy the messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB or file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+fi
+
+if [ -f "sd-v1-4.ckpt" ]; then
+    echo "Data files (weights) necessary for Stable Diffusion were already downloaded"
+else
+    echo "Downloading data files (weights) for Stable Diffusion.."
+
+    curl -L https://me.cmdr2.org/stable-diffusion-ui/sd-v1-4.ckpt > sd-v1-4.ckpt
+
+    if [ ! -f "sd-v1-4.ckpt" ]; then
+        printf "\n\nError downloading the data files (weights) for Stable Diffusion. Please try re-running this installer. If it doesn't work, please copy the messages in this window, and ask the community at https://discord.com/invite/u9yhsFmEkB or file an issue at https://github.com/cmdr2/stable-diffusion-ui/issues\n\n"
+        read -p "Press any key to continue"
+        exit
+    fi
+
+    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"
+
+export SD_UI_PATH=`pwd`/../ui
+
+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 +1,10 @@
+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 +1,5 @@
+source installer/bin/activate
+
+conda-unpack
+
+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

server

@@ -1,3 +0,0 @@
-#!/bin/bash
-
-echo "Please use 'docker-compose up &' to start the server, and 'docker-compose down' to stop the server"

ui/index.html

@@ -237,9 +237,9 @@
         float: right;
     }
     #server-status-color {
-        width: 10pt;
-        height: 10pt;
-        border-radius: 5pt;
+        width: 8pt;
+        height: 8pt;
+        border-radius: 4pt;
         background-color: rgb(128, 87, 0);
         /* background-color: rgb(197, 1, 1); */
         float: left;
@@ -248,6 +248,7 @@
     #server-status-msg {
         color: rgb(128, 87, 0);
         padding-left: 2pt;
+        font-size: 10pt;
     }
     #preview-prompt {
         font-size: 16pt;
@@ -262,9 +263,9 @@
             <div id="meta">
                 <div id="server-status">
                     <div id="server-status-color">&nbsp;</div>
-                    <span id="server-status-msg">server starting..</span>
+                    <span id="server-status-msg">Stable Diffusion is starting..</span>
                 </div>
-                <h1>Stable Diffusion UI <small>v1</small></h1>
+                <h1>Stable Diffusion UI <small>v2.05 (beta)</small></h1>
             </div>
             <div id="editor-inputs">
                 <div id="editor-inputs-prompt" class="row">
@@ -278,14 +279,6 @@
                         <img id="init_image_preview" src="" width="100" height="100" />
                         <button id="init_image_clear" class="image_clear_btn">X</button>
                     </div>
-
-                    <div id="mask_setting">
-                        <label for="mask"><b>Image Mask:</b> (optional) </label> <input id="mask" name="mask" type="file" /> </button><br/>
-                        <div id="mask_preview_container" class="image_preview_container">
-                            <img id="mask_preview" src="" width="100" height="100" />
-                            <button id="mask_clear" class="image_clear_btn">X</button>
-                        </div>
-                    </div>
                 </div>
 
                 <div id="editor-inputs-tags-container" class="row">
@@ -303,14 +296,55 @@
                 <h4 class="collapsible">Advanced Settings</h4>
                 <ul id="editor-settings-entries" class="collapsible-content">
                     <li><label for="seed">Seed:</label> <input id="seed" name="seed" size="10" value="30000"> <input id="random_seed" name="random_seed" type="checkbox" checked> <label for="random_seed">Random Image</label></li>
-                    <li><label for="num_outputs_total">Number of outputs:</label> <input id="num_outputs_total" name="num_outputs_total" value="1" size="4"> <label for="num_outputs_parallel">Generate in parallel:</label> <select id="num_outputs_parallel" name="num_outputs_parallel" value="1"><option value="1" selected>1 image at a time</option><option value="4">4 images at a time</option></select></li>
-                    <li><label for="width">Width:</label> <select id="width" name="width" value="512"><option value="128">128</option><option value="256">256</option><option value="512" selected>512</option><option value="768">768</option><option value="1024">1024</option></select></li>
-                    <li><label for="height">Height:</label> <select id="height" name="height" value="512"><option value="128">128</option><option value="256">256</option><option value="512" selected>512</option><option value="768">768</option></select></li>
+                    <li><label for="num_outputs_total">Number of images to make:</label> <input id="num_outputs_total" name="num_outputs_total" value="1" size="4"> <label for="num_outputs_parallel">Generate in parallel:</label> <input id="num_outputs_parallel" name="num_outputs_parallel" value="1" size="4"> (images at once)</li>
+                    <li><label for="width">Width:</label> 
+                        <select id="width" name="width" value="512">
+                            <option value="128">128 (*)</option>
+                            <option value="192">192</option>
+                            <option value="256">256 (*)</option>
+                            <option value="320">320</option>
+                            <option value="384">384</option>
+                            <option value="448">448</option>
+                            <option value="512" selected>512 (*)</option>
+                            <option value="576">576</option>
+                            <option value="640">640</option>
+                            <option value="704">704</option>
+                            <option value="768">768 (*)</option>
+                            <option value="832">832</option>
+                            <option value="896">896</option>
+                            <option value="960">960</option>
+                            <option value="1024">1024 (*)</option>
+                        </select>
+                    </li>
+                    <li><label for="height">Height:</label> 
+                        <select id="height" name="height" value="512">
+                            <option value="128">128 (*)</option>
+                            <option value="192">192</option>
+                            <option value="256">256 (*)</option>
+                            <option value="320">320</option>
+                            <option value="384">384</option>
+                            <option value="448">448</option>
+                            <option value="512" selected>512 (*)</option>
+                            <option value="576">576</option>
+                            <option value="640">640</option>
+                            <option value="704">704</option>
+                            <option value="768">768 (*)</option>
+                            <option value="832">832</option>
+                            <option value="896">896</option>
+                            <option value="960">960</option>
+                            <option value="1024">1024 (*)</option>
+                        </select>
+                    </li>
                     <li><label for="num_inference_steps">Number of inference steps:</label> <input id="num_inference_steps" name="num_inference_steps" size="4" value="50"></li>
                     <li><label for="guidance_scale">Guidance Scale:</label> <input id="guidance_scale" name="guidance_scale" value="75" type="range" min="10" max="200"> <span id="guidance_scale_value"></span></li>
                     <li><span id="prompt_strength_container"><label for="prompt_strength">Prompt Strength:</label> <input id="prompt_strength" name="prompt_strength" value="8" type="range" min="0" max="10"> <span id="prompt_strength_value"></span><br/></span></li>
                     <li>&nbsp;</li>
+                    <li><input id="save_to_disk" name="save_to_disk" type="checkbox"> <label for="save_to_disk">Automatically save to disk <span id="diskPath"></span></label></li>
                     <li><input id="sound_toggle" name="sound_toggle" type="checkbox" checked> <label for="sound_toggle">Play sound on task completion</label></li>
+                    <li><input id="turbo" name="turbo" type="checkbox" checked> <label for="turbo">Turbo mode (generates images faster, but uses an additional 1 GB of GPU memory)</label></li>
+                    <li><input id="use_cpu" name="use_cpu" type="checkbox"> <label for="use_cpu">Use CPU instead of GPU (warning: this will be *very* slow)</label></li>
+                    <li><input id="use_full_precision" name="use_full_precision" type="checkbox"> <label for="use_full_precision">Use full precision (for GPU-only. warning: this will consume more VRAM. Use this for NVIDIA 1650 and 1660)</label></li>
+                    <!-- <li><input id="allow_nsfw" name="allow_nsfw" type="checkbox"> <label for="allow_nsfw">Allow NSFW Content (You confirm you are above 18 years of age)</label></li> -->
                 </ul>
             </div>
 
@@ -322,7 +356,7 @@
         </div>
 
         <div id="preview" class="col-50">
-            <div id="preview-prompt">Type a prompt and press the "Make Image" button.<br/><br/>You can also add modifiers like "Realistic", "Pencil Sketch", "ArtStation" etc by browsing through the "Image Modifiers" section and selecting the desired modifiers.<br/><br/>Click "Advanced Settings" for additional settings like seed, image size, number of images to generate etc.<br/><br/>Enjoy! :)</div>
+            <div id="preview-prompt">Type a prompt and press the "Make Image" button.<br/><br/>You can set an "Initial Image" if you want to guide the AI.<br/><br/>You can also add modifiers like "Realistic", "Pencil Sketch", "ArtStation" etc by browsing through the "Image Modifiers" section and selecting the desired modifiers.<br/><br/>Click "Advanced Settings" for additional settings like seed, image size, number of images to generate etc.<br/><br/>Enjoy! :)</div>
 
             <div id="outputMsg"></div>
             <div id="current-images" class="img-preview">
@@ -345,6 +379,9 @@
 
 <script>
 const SOUND_ENABLED_KEY = "soundEnabled"
+const USE_CPU_KEY = "useCPU"
+const USE_FULL_PRECISION_KEY = "useFullPrecision"
+const USE_TURBO_MODE_KEY = "useTurboMode"
 const HEALTH_PING_INTERVAL = 5 // seconds
 
 let promptField = document.querySelector('#prompt')
@@ -359,8 +396,13 @@ let widthField = document.querySelector('#width')
 let heightField = document.querySelector('#height')
 let initImageSelector = document.querySelector("#init_image")
 let initImagePreview = document.querySelector("#init_image_preview")
-let maskImageSelector = document.querySelector("#mask")
-let maskImagePreview = document.querySelector("#mask_preview")
+// let maskImageSelector = document.querySelector("#mask")
+// let maskImagePreview = document.querySelector("#mask_preview")
+let turboField = document.querySelector('#turbo')
+let useCPUField = document.querySelector('#use_cpu')
+let useFullPrecisionField = document.querySelector('#use_full_precision')
+let saveToDiskField = document.querySelector('#save_to_disk')
+// let allowNSFWField = document.querySelector("#allow_nsfw")
 let promptStrengthField = document.querySelector('#prompt_strength')
 let promptStrengthValueLabel = document.querySelector('#prompt_strength_value')
 
@@ -371,9 +413,9 @@ let initImagePreviewContainer = document.querySelector('#init_image_preview_cont
 let initImageClearBtn = document.querySelector('#init_image_clear')
 let promptStrengthContainer = document.querySelector('#prompt_strength_container')
 
-let maskSetting = document.querySelector('#mask_setting')
-let maskImagePreviewContainer = document.querySelector('#mask_preview_container')
-let maskImageClearBtn = document.querySelector('#mask_clear')
+// let maskSetting = document.querySelector('#mask_setting')
+// let maskImagePreviewContainer = document.querySelector('#mask_preview_container')
+// let maskImageClearBtn = document.querySelector('#mask_clear')
 
 let editorModifierEntries = document.querySelector('#editor-modifiers-entries')
 let editorModifierTagsList = document.querySelector('#editor-inputs-tags-list')
@@ -392,12 +434,46 @@ let serverStatusMsg = document.querySelector('#server-status-msg')
 
 let serverStatus = 'offline'
 let activeTags = []
+let lastPromptUsed = ''
+
+function getLocalStorageItem(key, fallback) {
+    let item = localStorage.getItem(key)
+    if (item === null) {
+        return fallback
+    }
+
+    return item
+}
+
+function getLocalStorageBoolItem(key, fallback) {
+    let item = localStorage.getItem(key)
+    if (item === null) {
+        return fallback
+    }
+
+    return (item === 'true' ? true : false)
+}
+
+function handleBoolSettingChange(key) {
+    return function(e) {
+        localStorage.setItem(key, e.target.checked.toString())
+    }
+}
 
 function isSoundEnabled() {
-    if (localStorage.getItem(SOUND_ENABLED_KEY) === 'false') {
-        return false
+    return getLocalStorageBoolItem(SOUND_ENABLED_KEY, true)
 }
-    return true
+
+function isUseCPUEnabled() {
+    return getLocalStorageBoolItem(USE_CPU_KEY, false)
+}
+
+function isUseFullPrecisionEnabled() {
+    return getLocalStorageBoolItem(USE_FULL_PRECISION_KEY, false)
+}
+
+function isUseTurboModeEnabled() {
+    return getLocalStorageBoolItem(USE_TURBO_MODE_KEY, true)
 }
 
 function setStatus(statusType, msg, msgType) {
@@ -409,12 +485,12 @@ function setStatus(statusType, msg, msgType) {
         // msg = '<span style="color: red">' + msg + '<span>'
         serverStatusColor.style.backgroundColor = 'red'
         serverStatusMsg.style.color = 'red'
-        serverStatusMsg.innerHTML = 'server offline'
+        serverStatusMsg.innerHTML = 'Stable Diffusion has stopped'
     } else if (msgType == 'success') {
         // msg = '<span style="color: green">' + msg + '<span>'
         serverStatusColor.style.backgroundColor = 'green'
         serverStatusMsg.style.color = 'green'
-        serverStatusMsg.innerHTML = 'server online'
+        serverStatusMsg.innerHTML = 'Stable Diffusion is ready'
         serverStatus = 'online'
     }
 }
@@ -473,7 +549,7 @@ async function doMakeImage(reqBody) {
             if (res.status !== 'succeeded') {
                 let msg = ''
                 if (res.detail !== undefined) {
-                    msg = res.detail[0].msg + " in " + JSON.stringify(res.detail[0].loc)
+                    msg = res.detail
                 } else {
                     msg = res
                 }
@@ -490,11 +566,14 @@ async function doMakeImage(reqBody) {
         return false
     }
 
+    lastPromptUsed = reqBody['prompt']
+
     for (let idx in res.output) {
         let imgBody = ''
 
         try {
-            imgBody = res.output[idx]
+            let imgData = res.output[idx]
+            imgBody = imgData.data
         } catch (e) {
             console.log(imgBody)
             setStatus('request', 'invalid image', 'error')
@@ -538,7 +617,7 @@ async function doMakeImage(reqBody) {
             initImagePreviewContainer.style.display = 'block'
             promptStrengthContainer.style.display = 'block'
 
-            maskSetting.style.display = 'block'
+            // maskSetting.style.display = 'block'
 
             randomSeedField.checked = false
             seedField.value = seed
@@ -547,7 +626,7 @@ async function doMakeImage(reqBody) {
 
         imgSaveBtn.addEventListener('click', function() {
             let imgDownload = document.createElement('a')
-            imgDownload.download = generateUUID() + '.png'
+            imgDownload.download = createFileName();
             imgDownload.href = imgBody
             imgDownload.click()
         })
@@ -598,16 +677,21 @@ async function makeImage() {
         num_inference_steps: numInferenceStepsField.value,
         guidance_scale: parseInt(guidanceScaleField.value) / 10,
         width: widthField.value,
-        height: heightField.value
+        height: heightField.value,
+        // allow_nsfw: allowNSFWField.checked,
+        save_to_disk: saveToDiskField.checked,
+        turbo: turboField.checked,
+        use_cpu: useCPUField.checked,
+        use_full_precision: useFullPrecisionField.checked
     }
 
     if (imageRegex.test(initImagePreview.src)) {
         reqBody['init_image'] = initImagePreview.src
         reqBody['prompt_strength'] = parseInt(promptStrengthField.value) / 10
 
-        if (imageRegex.test(maskImagePreview.src)) {
-            reqBody['mask'] = maskImagePreview.src
-        }
+        // if (imageRegex.test(maskImagePreview.src)) {
+        //     reqBody['mask'] = maskImagePreview.src
+        // }
     }
 
     let time = new Date().getTime()
@@ -647,38 +731,56 @@ async function makeImage() {
     }
 }
 
-function generateUUID() { // Public Domain/MIT
-    var d = new Date().getTime();//Timestamp
-    var d2 = ((typeof performance !== 'undefined') && performance.now && (performance.now()*1000)) || 0;//Time in microseconds since page-load or 0 if unsupported
-    return 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'.replace(/[xy]/g, function(c) {
-        var r = Math.random() * 16;//random number between 0 and 16
-        if(d > 0){//Use timestamp until depleted
-            r = (d + r)%16 | 0;
-            d = Math.floor(d/16);
-        } else {//Use microseconds since page-load if supported
-            r = (d2 + r)%16 | 0;
-            d2 = Math.floor(d2/16);
-        }
-        return (c === 'x' ? r : (r & 0x3 | 0x8)).toString(16);
-    });
+// create a file name with embedded prompt and metadata
+// for easier cateloging and comparison
+function createFileName() {
+
+    // Most important information is the prompt
+    const underscoreName = lastPromptUsed.replace(/[^a-zA-Z0-9]/g, '_');
+    const seed = seedField.value;
+    const steps = numInferenceStepsField.value;
+    const guidance =  guidanceScaleField.value; 
+
+    // name and the top level metadata
+    let fileName = `sd_${underscoreName}_Seed-${seed}_Steps-${steps}_Guidance-${guidance}`;
+
+    // add the tags
+    // let tags = [];
+    // let tagString = '';
+    // document.querySelectorAll(modifyTagsSelector).forEach(function(tag) {
+    //     tags.push(tag.innerHTML);
+    // })
+
+    // join the tags with a pipe
+    // if (activeTags.length > 0) {
+    //     tagString = '_Tags-';
+    //     tagString += tags.join('|');
+    // }
+
+    // // append empty or populated tags
+    // fileName += `${tagString}`;
+
+    // add the file extension
+    fileName += `.png`;
+
+    return fileName;
 }
 
-function handleAudioEnabledChange(e) {
-    localStorage.setItem(SOUND_ENABLED_KEY, e.target.checked.toString())
-}
 
-soundToggle.addEventListener('click', handleAudioEnabledChange)
-soundToggle.checked = isSoundEnabled();
+soundToggle.addEventListener('click', handleBoolSettingChange(SOUND_ENABLED_KEY))
+soundToggle.checked = isSoundEnabled()
+
+useCPUField.addEventListener('click', handleBoolSettingChange(USE_CPU_KEY))
+useCPUField.checked = isUseCPUEnabled()
+
+useFullPrecisionField.addEventListener('click', handleBoolSettingChange(USE_FULL_PRECISION_KEY))
+useFullPrecisionField.checked = isUseFullPrecisionEnabled()
+
+turboField.addEventListener('click', handleBoolSettingChange(USE_TURBO_MODE_KEY))
+turboField.checked = isUseTurboModeEnabled()
 
 makeImageBtn.addEventListener('click', makeImage)
 
-// configBox.style.display = 'none'
-
-// showConfigToggle.addEventListener('click', function() {
-//     configBox.style.display = (configBox.style.display === 'none' ? 'block' : 'none')
-//     showConfigToggle.innerHTML = (configBox.style.display === 'none' ? 'show' : 'hide')
-//     return false
-// })
 
 function updateGuidanceScale() {
     guidanceScaleValueLabel.innerHTML = guidanceScaleField.value / 10
@@ -709,7 +811,7 @@ function showInitImagePreview() {
     if (initImageSelector.files.length === 0) {
         initImagePreviewContainer.style.display = 'none'
         promptStrengthContainer.style.display = 'none'
-        maskSetting.style.display = 'none'
+        // maskSetting.style.display = 'none'
         return
     }
 
@@ -722,7 +824,7 @@ function showInitImagePreview() {
         initImagePreviewContainer.style.display = 'block'
         promptStrengthContainer.style.display = 'block'
 
-        maskSetting.style.display = 'block'
+        // maskSetting.style.display = 'block'
     })
 
     if (file) {
@@ -734,45 +836,45 @@ showInitImagePreview()
 
 initImageClearBtn.addEventListener('click', function() {
     initImageSelector.value = null
-    maskImageSelector.value = null
+    // maskImageSelector.value = null
 
     initImagePreview.src = ''
-    maskImagePreview.src = ''
+    // maskImagePreview.src = ''
 
     initImagePreviewContainer.style.display = 'none'
-    maskImagePreviewContainer.style.display = 'none'
+    // maskImagePreviewContainer.style.display = 'none'
 
-    maskSetting.style.display = 'none'
+    // maskSetting.style.display = 'none'
 
     promptStrengthContainer.style.display = 'none'
 })
 
-function showMaskImagePreview() {
-    if (maskImageSelector.files.length === 0) {
-        maskImagePreviewContainer.style.display = 'none'
-        return
-    }
+// function showMaskImagePreview() {
+//     if (maskImageSelector.files.length === 0) {
+//         maskImagePreviewContainer.style.display = 'none'
+//         return
+//     }
 
-    let reader = new FileReader()
-    let file = maskImageSelector.files[0]
+//     let reader = new FileReader()
+//     let file = maskImageSelector.files[0]
 
-    reader.addEventListener('load', function() {
-        maskImagePreview.src = reader.result
-        maskImagePreviewContainer.style.display = 'block'
-    })
+//     reader.addEventListener('load', function() {
+//         maskImagePreview.src = reader.result
+//         maskImagePreviewContainer.style.display = 'block'
+//     })
 
-    if (file) {
-        reader.readAsDataURL(file)
-    }
-}
-maskImageSelector.addEventListener('change', showMaskImagePreview)
-showMaskImagePreview()
+//     if (file) {
+//         reader.readAsDataURL(file)
+//     }
+// }
+// maskImageSelector.addEventListener('change', showMaskImagePreview)
+// showMaskImagePreview()
 
-maskImageClearBtn.addEventListener('click', function() {
-    maskImageSelector.value = null
-    maskImagePreview.src = ''
-    maskImagePreviewContainer.style.display = 'none'
-})
+// maskImageClearBtn.addEventListener('click', function() {
+//     maskImageSelector.value = null
+//     maskImagePreview.src = ''
+//     maskImagePreviewContainer.style.display = 'none'
+// })
 </script>
 <script>
 function createCollapsibles(node) {
@@ -833,6 +935,20 @@ function refreshTagsList() {
     editorModifierTagsList.appendChild(brk)
 }
 
+async function getDiskPath() {
+    try {
+        let res = await fetch('/output_dir')
+        if (res.status === 200) {
+            res = await res.json()
+            res = res[0]
+
+            document.querySelector('#diskPath').innerHTML = '(to ' + res + ')'
+        }
+    } catch (e) {
+        console.log('error fetching output dir path', e)
+    }
+}
+
 async function loadModifiers() {
     try {
         let res = await fetch('/modifiers.json')
@@ -886,6 +1002,7 @@ async function loadModifiers() {
 
 async function init() {
     await loadModifiers()
+    await getDiskPath()
 
     setInterval(healthCheck, HEALTH_PING_INTERVAL * 1000)
     healthCheck()

ui/modifiers.json

@@ -0,0 +1,140 @@
+[
+  [
+    "Drawing Style",
+    [
+      "Cel Shading",
+      "Children's Drawing",
+      "Crosshatch",
+      "Detailed and Intricate",
+      "Doodle",
+      "Dot Art",
+      "Line Art",
+      "Sketch"
+    ]
+  ],
+  [
+    "Visual Style",
+    [
+      "2D",
+      "8-bit",
+      "16-bit",
+      "Anaglyph",
+      "Anime",
+      "Cartoon",
+      "CGI",
+      "Comic Book",
+      "Concept Art",
+      "Digital Art",
+      "Fantasy",
+      "Graphic Novel",
+      "Hard Edge Painting",
+      "Hydrodipped",
+      "Lithography",
+      "Modern Art",
+      "Mosaic",
+      "Mural",
+      "Photo",
+      "Realistic",
+      "Street Art",
+      "Visual Novel",
+      "Watercolor"
+    ]
+  ],
+  [
+    "Pen",
+    [
+      "Chalk",
+      "Colored Pencil",
+      "Graphite",
+      "Ink",
+      "Oil Paint",
+      "Pastel Art"
+    ]
+  ],
+  [
+    "Carving and Etching",
+    [
+      "Etching",
+      "Linocut",
+      "Paper Model",
+      "Paper-Mache",
+      "Papercutting",
+      "Pyrography",
+      "Wood-Carving"
+    ]
+  ],
+  [
+    "Camera",
+    [
+      "Aerial View",
+      "Cinematic",
+      "Color Grading",
+      "Dramatic",
+      "Film Grain",
+      "Fisheye Lens",
+      "Glamor Shot",
+      "Golden Hour",
+      "HD",
+      "Lens Flare",
+      "Macro",
+      "Polaroid",
+      "Vintage",
+      "War Photography",
+      "White Balance",
+      "Wildlife Photography"
+    ]
+  ],
+  [
+    "Color",
+    [
+      "Beautiful Lighting",
+      "Colorful",
+      "Electric Colors",
+      "Infrared",
+      "Synthwave",
+      "Warm Color Palette"
+    ]
+  ],
+  [
+    "Emotions",
+    [
+      "Angry",
+      "Evil",
+      "Excited",
+      "Good",
+      "Happy",
+      "Lonely",
+      "Sad"
+    ]
+  ],
+  [
+    "Style of an artist or community",
+    [
+      "Artstation",
+      "by Agnes Lawrence Pelton",
+      "by Akihito Yoshida",
+      "by Andy Warhol",
+      "by Asaf Hanuka",
+      "by Aubrey Beardsley",
+      "by Ben Enwonwu",
+      "by Caravaggio Michelangelo Merisi",
+      "by David Mann",
+      "by Frida Kahlo",
+      "by H.R. Giger",
+      "by Hayao Mizaki",
+      "by Ivan Shishkin",
+      "by Johannes Vermeer",
+      "by Katsushika Hokusai",
+      "by Ko Young Hoon",
+      "by Leonardo Da Vinci",
+      "by Lisa Frank",
+      "by Mahmoud Sai",
+      "by Mark Brooks",
+      "by Pablo Picasso",
+      "by Richard Dadd",
+      "by Salvador Dali",
+      "by Tivadar Csontváry Kosztka",
+      "by Yoshitaka Amano"
+    ]
+  ]
+]

ui/sd_internal/__init__.py

@@ -0,0 +1,62 @@
+import json
+
+class Request:
+    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
+    # allow_nsfw: bool = False
+    precision: str = "autocast" # or "full"
+    save_to_disk_path: str = None
+    turbo: bool = True
+    use_cpu: bool = False
+    use_full_precision: bool = False
+
+    def to_string(self):
+        return f'''
+    prompt: {self.prompt}
+    seed: {self.seed}
+    num_inference_steps: {self.num_inference_steps}
+    guidance_scale: {self.guidance_scale}
+    w: {self.width}
+    h: {self.height}
+    precision: {self.precision}
+    save_to_disk_path: {self.save_to_disk_path}
+    turbo: {self.turbo}
+    use_cpu: {self.use_cpu}
+    use_full_precision: {self.use_full_precision}'''
+
+class Image:
+    data: str # base64
+    seed: int
+    is_nsfw: bool
+
+    def __init__(self, data, seed):
+        self.data = data
+        self.seed = seed
+
+    def json(self):
+        return {
+            "data": self.data,
+            "seed": self.seed,
+        }
+
+class Response:
+    images: list
+
+    def json(self):
+        res = {
+            "status": 'succeeded',
+            "output": [],
+        }
+
+        for image in self.images:
+            res["output"].append(image.json())
+
+        return res

ui/sd_internal/runtime.py

@@ -0,0 +1,359 @@
+import os, re
+import torch
+import numpy as np
+from omegaconf import OmegaConf
+from PIL import Image
+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
+
+import uuid
+
+logging.set_verbosity_error()
+
+# consts
+config_yaml = "optimizedSD/v1-inference.yaml"
+
+# api stuff
+from . import Request, Response, Image as ResponseImage
+import base64
+from io import BytesIO
+
+# local
+session_id = str(uuid.uuid4())
+
+ckpt = None
+model = None
+modelCS = None
+modelFS = None
+model_is_half = False
+model_fs_is_half = False
+device = None
+unet_bs = 1
+precision = 'autocast'
+sampler_plms = None
+sampler_ddim = None
+
+# api
+def load_model(ckpt_to_use, device_to_use='cuda', turbo=False, unet_bs_to_use=1, precision_to_use='autocast', half_model_fs=False):
+    global ckpt, model, modelCS, modelFS, model_is_half, device, unet_bs, precision, model_fs_is_half
+
+    ckpt = ckpt_to_use
+    device = device_to_use
+    precision = precision_to_use
+    unet_bs = unet_bs_to_use
+
+    sd = load_model_from_config(f"{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
+
+def mk_img(req: Request):
+    global modelFS, device
+
+    res = Response()
+    res.images = []
+
+    model.turbo = req.turbo
+    if req.use_cpu:
+        device = 'cpu'
+
+        if model_is_half:
+            print('reloading model for cpu')
+            load_model(ckpt, device)
+    else:
+        device = 'cuda'
+
+        if (precision == 'autocast' and (req.use_full_precision or not model_is_half)) or \
+            (precision == 'full' and not req.use_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):
+
+            print('reloading model for cuda')
+            load_model(ckpt, device, model.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))
+
+    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_format = 'png'
+
+    print(req.to_string(), '\n    device', device)
+
+    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
+
+    if req.init_image is None:
+        handler = _txt2img
+
+        init_latent = None
+        t_enc = None
+    else:
+        handler = _img2img
+
+        init_image = load_img(req.init_image)
+        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 device != "cpu":
+            mem = torch.cuda.memory_allocated() / 1e6
+            modelFS.to("cpu")
+            while torch.cuda.memory_allocated() / 1e6 >= mem:
+                time.sleep(1)
+
+        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, 'session-' + 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"):
+
+                if opt_save_to_disk_path is not None:
+                    base_count = len(os.listdir(session_out_path))
+
+                with precision_scope("cuda"):
+                    modelCS.to(device)
+                    uc = None
+                    if opt_scale != 1.0:
+                        uc = modelCS.get_learned_conditioning(batch_size * [""])
+                    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)
+
+                    # run the handler
+                    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)
+                    else:
+                        x_samples = _img2img(init_latent, t_enc, batch_size, opt_scale, c, uc, opt_ddim_steps, opt_ddim_eta, opt_seed)
+
+                    modelFS.to(device)
+
+                    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")
+                        img = Image.fromarray(x_sample.astype(np.uint8))
+
+                        img_data = img_to_base64_str(img)
+                        res.images.append(ResponseImage(data=img_data, seed=opt_seed))
+
+                        if opt_save_to_disk_path is not None:
+                            prompt_flattened = "_".join(re.split(":| ", prompts[0]))
+                            prompt_flattened = prompt_flattened[:150]
+
+                            file_path = f"sd_{prompt_flattened}_Seed-{opt_seed}_Steps-{opt_ddim_steps}_Guidance-{opt_scale}_{base_count:05}"
+                            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")
+
+                            metadata = f"{prompts[0]}\nSeed: {opt_seed}\nSteps: {opt_ddim_steps}\nGuidance Scale: {opt_scale}"
+                            img.save(img_out_path)
+                            with open(meta_out_path, 'w') as f:
+                                f.write(metadata)
+
+                            base_count += 1
+
+                        seeds += str(opt_seed) + ","
+                        opt_seed += 1
+
+                    if device != "cpu":
+                        mem = torch.cuda.memory_allocated() / 1e6
+                        modelFS.to("cpu")
+                        while torch.cuda.memory_allocated() / 1e6 >= mem:
+                            time.sleep(1)
+                    del x_samples
+                    print("memory_final = ", torch.cuda.memory_allocated() / 1e6)
+
+    return res
+
+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):
+    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)
+
+    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,
+        sampler = 'plms',
+    )
+
+    return samples_ddim
+
+def _img2img(init_latent, t_enc, batch_size, opt_scale, c, uc, opt_ddim_steps, opt_ddim_eta, opt_seed):
+    # 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,
+    )
+    # decode it
+    samples_ddim = model.sample(
+        t_enc,
+        c,
+        z_enc,
+        unconditional_guidance_scale=opt_scale,
+        unconditional_conditioning=uc,
+        sampler = 'ddim'
+    )
+
+    return samples_ddim
+
+# 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
+
+def load_img(img_str):
+    image = base64_str_to_img(img_str).convert("RGB")
+    w, h = image.size
+    print(f"loaded input image of size ({w}, {h}) from base64")
+    w, h = map(lambda x: x - x % 64, (w, h))  # resize to integer multiple of 64
+    image = image.resize((w, h), resample=Image.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.
+
+# 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

@@ -0,0 +1,118 @@
+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))
+
+OUTPUT_DIRNAME = "Stable Diffusion UI" # in the user's home folder
+
+from fastapi import FastAPI, HTTPException
+from starlette.responses import FileResponse
+from pydantic import BaseModel
+
+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)
+
+# defaults from https://huggingface.co/blog/stable_diffusion
+class ImageRequest(BaseModel):
+    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
+    # allow_nsfw: bool = False
+    save_to_disk: bool = False
+    turbo: bool = True
+    use_cpu: bool = False
+    use_full_precision: bool = False
+
+@app.get('/')
+def read_root():
+    return FileResponse(os.path.join(SD_UI_DIR, 'index.html'))
+
+@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
+        runtime.load_model(ckpt_to_use="sd-v1-4.ckpt")
+
+        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')
+async def image(req : ImageRequest):
+    from sd_internal import runtime
+
+    r = Request()
+    r.prompt = req.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.allow_nsfw = req.allow_nsfw
+    r.turbo = req.turbo
+    r.use_cpu = req.use_cpu
+    r.use_full_precision = req.use_full_precision
+
+    if req.save_to_disk:
+        r.save_to_disk_path = outpath
+
+    try:
+        res: Response = runtime.mk_img(r)
+
+        return res.json()
+    except Exception as e:
+        print(traceback.format_exc())
+        return HTTPException(status_code=500, detail=str(e))
+
+@app.get('/media/ding.mp3')
+def read_ding():
+    return FileResponse(os.path.join(SD_UI_DIR, 'media/ding.mp3'))
+
+@app.get('/modifiers.json')
+def read_modifiers():
+    return FileResponse(os.path.join(SD_UI_DIR, 'modifiers.json'))
+
+@app.get('/output_dir')
+def read_home_dir():
+    return {outpath}
+
+# start the browser ui
+import webbrowser; webbrowser.open('http://localhost:9000')