forked from extern/easydiffusion
Merge remote-tracking branch 'origin/beta' into restart-needed
This commit is contained in:
Olivia Godone-Maresca
commit
3461bb669d
@ -22,6 +22,7 @@
|
||||
Our focus continues to remain on an easy installation experience, and an easy user-interface. While still remaining pretty powerful, in terms of features and speed.
|
||||
|
||||
### Detailed changelog
|
||||
* 2.5.44 - 15 Jul 2023 - (beta-only) Support for multiple LoRA files.
|
||||
* 2.5.43 - 9 Jul 2023 - (beta-only) Support for loading Textual Inversion embeddings. You can find the option in the Image Settings panel. Thanks @JeLuf.
|
||||
* 2.5.43 - 9 Jul 2023 - Improve the startup time of the UI.
|
||||
* 2.5.42 - 4 Jul 2023 - Keyboard shortcuts for the Image Editor. Thanks @JeLuf.
|
||||
|
||||
@ -41,6 +41,10 @@ call python --version
|
||||
|
||||
echo PYTHONPATH=%PYTHONPATH%
|
||||
|
||||
if exist "%cd%\profile" (
|
||||
set HF_HOME=%cd%\profile\.cache\huggingface
|
||||
)
|
||||
|
||||
@rem done
|
||||
echo.
|
||||
|
||||
|
||||
@ -18,7 +18,7 @@ os_name = platform.system()
|
||||
modules_to_check = {
|
||||
"torch": ("1.11.0", "1.13.1", "2.0.0"),
|
||||
"torchvision": ("0.12.0", "0.14.1", "0.15.1"),
|
||||
"sdkit": "1.0.116",
|
||||
"sdkit": "1.0.125",
|
||||
"stable-diffusion-sdkit": "2.1.4",
|
||||
"rich": "12.6.0",
|
||||
"uvicorn": "0.19.0",
|
||||
|
||||
@ -104,18 +104,21 @@ call python --version
|
||||
|
||||
@FOR /F "tokens=* USEBACKQ" %%F IN (`python scripts\get_config.py --default=False net listen_to_network`) DO (
|
||||
if "%%F" EQU "True" (
|
||||
@SET ED_BIND_IP=0.0.0.0
|
||||
@FOR /F "tokens=* USEBACKQ" %%G IN (`python scripts\get_config.py --default=0.0.0.0 net bind_ip`) DO (
|
||||
@SET ED_BIND_IP=%%G
|
||||
)
|
||||
) else (
|
||||
@SET ED_BIND_IP=127.0.0.1
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
@cd stable-diffusion
|
||||
|
||||
@rem set any overrides
|
||||
set HF_HUB_DISABLE_SYMLINKS_WARNING=true
|
||||
|
||||
@uvicorn main:server_api --app-dir "%SD_UI_PATH%" --port %ED_BIND_PORT% --host %ED_BIND_IP% --log-level error
|
||||
@python -m uvicorn main:server_api --app-dir "%SD_UI_PATH%" --port %ED_BIND_PORT% --host %ED_BIND_IP% --log-level error
|
||||
|
||||
|
||||
@pause
|
||||
|
||||
@ -72,7 +72,7 @@ export SD_UI_PATH=`pwd`/ui
|
||||
export ED_BIND_PORT="$( python scripts/get_config.py --default=9000 net listen_port )"
|
||||
case "$( python scripts/get_config.py --default=False net listen_to_network )" in
|
||||
"True")
|
||||
export ED_BIND_IP=0.0.0.0
|
||||
export ED_BIND_IP=$( python scripts/get_config.py --default=0.0.0.0 net bind_ip)
|
||||
;;
|
||||
"False")
|
||||
export ED_BIND_IP=127.0.0.1
|
||||
|
||||
@ -2,6 +2,7 @@ import os
|
||||
import shutil
|
||||
from glob import glob
|
||||
import traceback
|
||||
from typing import Union
|
||||
|
||||
from easydiffusion import app
|
||||
from easydiffusion.types import TaskData
|
||||
@ -93,7 +94,14 @@ def unload_all(context: Context):
|
||||
del context.model_load_errors[model_type]
|
||||
|
||||
|
||||
def resolve_model_to_use(model_name: str = None, model_type: str = None, fail_if_not_found: bool = True):
|
||||
def resolve_model_to_use(model_name: Union[str, list] = None, model_type: str = None, fail_if_not_found: bool = True):
|
||||
model_names = model_name if isinstance(model_name, list) else [model_name]
|
||||
model_paths = [resolve_model_to_use_single(m, model_type, fail_if_not_found) for m in model_names]
|
||||
|
||||
return model_paths[0] if len(model_paths) == 1 else model_paths
|
||||
|
||||
|
||||
def resolve_model_to_use_single(model_name: str = None, model_type: str = None, fail_if_not_found: bool = True):
|
||||
model_extensions = MODEL_EXTENSIONS.get(model_type, [])
|
||||
default_models = DEFAULT_MODELS.get(model_type, [])
|
||||
config = app.getConfig()
|
||||
|
||||
@ -473,15 +473,15 @@ def start_render_thread(device):
|
||||
render_threads.append(rthread)
|
||||
finally:
|
||||
manager_lock.release()
|
||||
# timeout = DEVICE_START_TIMEOUT
|
||||
# while not rthread.is_alive() or not rthread in weak_thread_data or not "device" in weak_thread_data[rthread]:
|
||||
# if rthread in weak_thread_data and "error" in weak_thread_data[rthread]:
|
||||
# log.error(f"{rthread}, {device}, error: {weak_thread_data[rthread]['error']}")
|
||||
# return False
|
||||
# if timeout <= 0:
|
||||
# return False
|
||||
# timeout -= 1
|
||||
# time.sleep(1)
|
||||
timeout = DEVICE_START_TIMEOUT
|
||||
while not rthread.is_alive() or not rthread in weak_thread_data or not "device" in weak_thread_data[rthread]:
|
||||
if rthread in weak_thread_data and "error" in weak_thread_data[rthread]:
|
||||
log.error(f"{rthread}, {device}, error: {weak_thread_data[rthread]['error']}")
|
||||
return False
|
||||
if timeout <= 0:
|
||||
return False
|
||||
timeout -= 1
|
||||
time.sleep(1)
|
||||
return True
|
||||
|
||||
|
||||
@ -535,12 +535,12 @@ def update_render_threads(render_devices, active_devices):
|
||||
if not start_render_thread(device):
|
||||
log.warn(f"{device} failed to start.")
|
||||
|
||||
# if is_alive() <= 0: # No running devices, probably invalid user config.
|
||||
# raise EnvironmentError(
|
||||
# 'ERROR: No active render devices! Please verify the "render_devices" value in config.json'
|
||||
# )
|
||||
if is_alive() <= 0: # No running devices, probably invalid user config.
|
||||
raise EnvironmentError(
|
||||
'ERROR: No active render devices! Please verify the "render_devices" value in config.json'
|
||||
)
|
||||
|
||||
# log.debug(f"active devices: {get_devices()['active']}")
|
||||
log.debug(f"active devices: {get_devices()['active']}")
|
||||
|
||||
|
||||
def shutdown_event(): # Signal render thread to close on shutdown
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
from typing import Any
|
||||
from typing import Any, List, Union
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
@ -22,7 +22,7 @@ class GenerateImageRequest(BaseModel):
|
||||
|
||||
sampler_name: str = None # "ddim", "plms", "heun", "euler", "euler_a", "dpm2", "dpm2_a", "lms"
|
||||
hypernetwork_strength: float = 0
|
||||
lora_alpha: float = 0
|
||||
lora_alpha: Union[float, List[float]] = 0
|
||||
tiling: str = "none" # "none", "x", "y", "xy"
|
||||
|
||||
|
||||
@ -32,15 +32,14 @@ class TaskData(BaseModel):
|
||||
save_to_disk_path: str = None
|
||||
vram_usage_level: str = "balanced" # or "low" or "medium"
|
||||
|
||||
use_face_correction: str = None # or "GFPGANv1.3"
|
||||
use_upscale: str = None # or "RealESRGAN_x4plus" or "RealESRGAN_x4plus_anime_6B" or "latent_upscaler"
|
||||
use_face_correction: Union[str, List[str]] = None # or "GFPGANv1.3"
|
||||
use_upscale: Union[str, List[str]] = None
|
||||
upscale_amount: int = 4 # or 2
|
||||
latent_upscaler_steps: int = 10
|
||||
use_stable_diffusion_model: str = "sd-v1-4"
|
||||
# use_stable_diffusion_config: str = "v1-inference"
|
||||
use_vae_model: str = None
|
||||
use_hypernetwork_model: str = None
|
||||
use_lora_model: str = None
|
||||
use_stable_diffusion_model: Union[str, List[str]] = "sd-v1-4"
|
||||
use_vae_model: Union[str, List[str]] = None
|
||||
use_hypernetwork_model: Union[str, List[str]] = None
|
||||
use_lora_model: Union[str, List[str]] = None
|
||||
|
||||
show_only_filtered_image: bool = False
|
||||
block_nsfw: bool = False
|
||||
|
||||
@ -1,6 +1,8 @@
|
||||
import os
|
||||
import re
|
||||
import time
|
||||
import regex
|
||||
|
||||
from datetime import datetime
|
||||
from functools import reduce
|
||||
|
||||
@ -30,11 +32,12 @@ TASK_TEXT_MAPPING = {
|
||||
"lora_alpha": "LoRA Strength",
|
||||
"use_hypernetwork_model": "Hypernetwork model",
|
||||
"hypernetwork_strength": "Hypernetwork Strength",
|
||||
"use_embedding_models": "Embedding models",
|
||||
"tiling": "Seamless Tiling",
|
||||
"use_face_correction": "Use Face Correction",
|
||||
"use_upscale": "Use Upscaling",
|
||||
"upscale_amount": "Upscale By",
|
||||
"latent_upscaler_steps": "Latent Upscaler Steps"
|
||||
"latent_upscaler_steps": "Latent Upscaler Steps",
|
||||
}
|
||||
|
||||
time_placeholders = {
|
||||
@ -202,6 +205,9 @@ def get_printable_request(req: GenerateImageRequest, task_data: TaskData):
|
||||
req_metadata = req.dict()
|
||||
task_data_metadata = task_data.dict()
|
||||
|
||||
app_config = app.getConfig()
|
||||
using_diffusers = app_config.get("test_diffusers", False)
|
||||
|
||||
# Save the metadata in the order defined in TASK_TEXT_MAPPING
|
||||
metadata = {}
|
||||
for key in TASK_TEXT_MAPPING.keys():
|
||||
@ -209,6 +215,24 @@ def get_printable_request(req: GenerateImageRequest, task_data: TaskData):
|
||||
metadata[key] = req_metadata[key]
|
||||
elif key in task_data_metadata:
|
||||
metadata[key] = task_data_metadata[key]
|
||||
elif key is "use_embedding_models" and using_diffusers:
|
||||
embeddings_extensions = {".pt", ".bin", ".safetensors"}
|
||||
def scan_directory(directory_path: str):
|
||||
used_embeddings = []
|
||||
for entry in os.scandir(directory_path):
|
||||
if entry.is_file():
|
||||
entry_extension = os.path.splitext(entry.name)[1]
|
||||
if entry_extension not in embeddings_extensions:
|
||||
continue
|
||||
|
||||
embedding_name_regex = regex.compile(r"(^|[\s,])" + regex.escape(os.path.splitext(entry.name)[0]) + r"([+-]*$|[\s,]|[+-]+[\s,])")
|
||||
if embedding_name_regex.search(req.prompt) or embedding_name_regex.search(req.negative_prompt):
|
||||
used_embeddings.append(entry.path)
|
||||
elif entry.is_dir():
|
||||
used_embeddings.extend(scan_directory(entry.path))
|
||||
return used_embeddings
|
||||
used_embeddings = scan_directory(os.path.join(app.MODELS_DIR, "embeddings"))
|
||||
metadata["use_embedding_models"] = ", ".join(used_embeddings) if len(used_embeddings) > 0 else None
|
||||
|
||||
# Clean up the metadata
|
||||
if req.init_image is None and "prompt_strength" in metadata:
|
||||
@ -222,8 +246,7 @@ def get_printable_request(req: GenerateImageRequest, task_data: TaskData):
|
||||
if task_data.use_upscale != "latent_upscaler" and "latent_upscaler_steps" in metadata:
|
||||
del metadata["latent_upscaler_steps"]
|
||||
|
||||
app_config = app.getConfig()
|
||||
if not app_config.get("test_diffusers", False):
|
||||
if not using_diffusers:
|
||||
for key in (x for x in ["use_lora_model", "lora_alpha", "clip_skip", "tiling", "latent_upscaler_steps"] if x in metadata):
|
||||
del metadata[key]
|
||||
|
||||
|
||||
@ -31,7 +31,7 @@
|
||||
<h1>
|
||||
<img id="logo_img" src="/media/images/icon-512x512.png" >
|
||||
Easy Diffusion
|
||||
<small><span id="version">v2.5.43</span> <span id="updateBranchLabel"></span></small>
|
||||
<small><span id="version">v2.5.44</span> <span id="updateBranchLabel"></span></small>
|
||||
</h1>
|
||||
</div>
|
||||
<div id="server-status">
|
||||
@ -162,9 +162,10 @@
|
||||
<option value="dpm2_a">DPM2 Ancestral</option>
|
||||
<option value="lms">LMS</option>
|
||||
<option value="dpm_solver_stability">DPM Solver (Stability AI)</option>
|
||||
<option value="dpmpp_2s_a" class="k_diffusion-only">DPM++ 2s Ancestral (Karras)</option>
|
||||
<option value="dpmpp_2s_a">DPM++ 2s Ancestral (Karras)</option>
|
||||
<option value="dpmpp_2m">DPM++ 2m (Karras)</option>
|
||||
<option value="dpmpp_sde" class="k_diffusion-only">DPM++ SDE (Karras)</option>
|
||||
<option value="dpmpp_2m_sde" class="diffusers-only">DPM++ 2m SDE (Karras)</option>
|
||||
<option value="dpmpp_sde">DPM++ SDE (Karras)</option>
|
||||
<option value="dpm_fast" class="k_diffusion-only">DPM Fast (Karras)</option>
|
||||
<option value="dpm_adaptive" class="k_diffusion-only">DPM Adaptive (Karras)</option>
|
||||
<option value="ddpm" class="diffusers-only">DDPM</option>
|
||||
@ -224,21 +225,14 @@
|
||||
<label for="height"><small>(height)</small></label>
|
||||
<div id="small_image_warning" class="displayNone">Small image sizes can cause bad image quality</div>
|
||||
</td></tr>
|
||||
<tr class="pl-5"><td><label for="num_inference_steps">Inference Steps:</label></td><td> <input id="num_inference_steps" name="num_inference_steps" size="4" value="25" onkeypress="preventNonNumericalInput(event)"></td></tr>
|
||||
<tr class="pl-5"><td><label for="num_inference_steps">Inference Steps:</label></td><td> <input id="num_inference_steps" name="num_inference_steps" type="number" min="1" step="1" style="width: 42pt" value="25" onkeypress="preventNonNumericalInput(event)"></td></tr>
|
||||
<tr class="pl-5"><td><label for="guidance_scale_slider">Guidance Scale:</label></td><td> <input id="guidance_scale_slider" name="guidance_scale_slider" class="editor-slider" value="75" type="range" min="11" max="500"> <input id="guidance_scale" name="guidance_scale" size="4" pattern="^[0-9\.]+$" onkeypress="preventNonNumericalInput(event)"></td></tr>
|
||||
<tr id="prompt_strength_container" class="pl-5"><td><label for="prompt_strength_slider">Prompt Strength:</label></td><td> <input id="prompt_strength_slider" name="prompt_strength_slider" class="editor-slider" value="80" type="range" min="0" max="99"> <input id="prompt_strength" name="prompt_strength" size="4" pattern="^[0-9\.]+$" onkeypress="preventNonNumericalInput(event)"><br/></td></tr>
|
||||
<tr id="lora_model_container" class="pl-5">
|
||||
<td><label for="lora_model">LoRA:</label></td>
|
||||
<td class="diffusers-restart-needed">
|
||||
<input id="lora_model" type="text" spellcheck="false" autocomplete="off" class="model-filter" data-path="" />
|
||||
</td>
|
||||
</tr>
|
||||
<tr id="lora_alpha_container" class="pl-5">
|
||||
<td><label for="lora_alpha_slider">LoRA Strength:</label></td>
|
||||
<td class="diffusers-restart-needed">
|
||||
<small>-2</small> <input id="lora_alpha_slider" name="lora_alpha_slider" class="editor-slider" value="50" type="range" min="-200" max="200"> <small>2</small>
|
||||
<input id="lora_alpha" name="lora_alpha" size="4" pattern="^-?[0-9]*\.?[0-9]*$" onkeypress="preventNonNumericalInput(event)"><br/>
|
||||
<td>
|
||||
<label for="lora_model">LoRA:</label>
|
||||
</td>
|
||||
<td class="model_entries diffusers-restart-needed"></td>
|
||||
</tr>
|
||||
<tr class="pl-5"><td><label for="hypernetwork_model">Hypernetwork:</label></td><td>
|
||||
<input id="hypernetwork_model" type="text" spellcheck="false" autocomplete="off" class="model-filter" data-path="" />
|
||||
|
||||
@ -1,12 +1,12 @@
|
||||
from easydiffusion import model_manager, app, server
|
||||
from easydiffusion.server import server_api # required for uvicorn
|
||||
|
||||
server.init()
|
||||
|
||||
# Init the app
|
||||
model_manager.init()
|
||||
app.init()
|
||||
server.init()
|
||||
app.init_render_threads()
|
||||
|
||||
# start the browser ui
|
||||
app.open_browser()
|
||||
|
||||
app.init_render_threads()
|
||||
|
||||
@ -5,6 +5,8 @@
|
||||
|
||||
html {
|
||||
position: relative;
|
||||
overscroll-behavior-y: none;
|
||||
color-scheme: dark !important;
|
||||
}
|
||||
|
||||
body {
|
||||
@ -1677,6 +1679,10 @@ body.wait-pause {
|
||||
background: var(--background-color3);
|
||||
}
|
||||
|
||||
.model_entry .model_name {
|
||||
width: 70%;
|
||||
}
|
||||
|
||||
.diffusers-disabled-on-startup .diffusers-restart-needed {
|
||||
font-size: 0;
|
||||
}
|
||||
|
||||
@ -16,7 +16,9 @@ const SETTINGS_IDS_LIST = [
|
||||
"clip_skip",
|
||||
"vae_model",
|
||||
"hypernetwork_model",
|
||||
"lora_model",
|
||||
"lora_model_0",
|
||||
"lora_model_1",
|
||||
"lora_model_2",
|
||||
"sampler_name",
|
||||
"width",
|
||||
"height",
|
||||
@ -24,7 +26,9 @@ const SETTINGS_IDS_LIST = [
|
||||
"guidance_scale",
|
||||
"prompt_strength",
|
||||
"hypernetwork_strength",
|
||||
"lora_alpha",
|
||||
"lora_alpha_0",
|
||||
"lora_alpha_1",
|
||||
"lora_alpha_2",
|
||||
"tiling",
|
||||
"output_format",
|
||||
"output_quality",
|
||||
@ -176,13 +180,14 @@ function loadSettings() {
|
||||
// So this is likely the first time Easy Diffusion is running.
|
||||
// Initialize vram_usage_level based on the available VRAM
|
||||
function initGPUProfile(event) {
|
||||
if ( "detail" in event
|
||||
&& "active" in event.detail
|
||||
&& "cuda:0" in event.detail.active
|
||||
&& event.detail.active["cuda:0"].mem_total <4.5 )
|
||||
{
|
||||
vramUsageLevelField.value = "low"
|
||||
vramUsageLevelField.dispatchEvent(new Event("change"))
|
||||
if (
|
||||
"detail" in event &&
|
||||
"active" in event.detail &&
|
||||
"cuda:0" in event.detail.active &&
|
||||
event.detail.active["cuda:0"].mem_total < 4.5
|
||||
) {
|
||||
vramUsageLevelField.value = "low"
|
||||
vramUsageLevelField.dispatchEvent(new Event("change"))
|
||||
}
|
||||
document.removeEventListener("system_info_update", initGPUProfile)
|
||||
}
|
||||
|
||||
@ -292,29 +292,58 @@ const TASK_MAPPING = {
|
||||
use_lora_model: {
|
||||
name: "LoRA model",
|
||||
setUI: (use_lora_model) => {
|
||||
const oldVal = loraModelField.value
|
||||
use_lora_model =
|
||||
use_lora_model === undefined || use_lora_model === null || use_lora_model === "None"
|
||||
? ""
|
||||
: use_lora_model
|
||||
use_lora_model.forEach((model_name, i) => {
|
||||
let field = loraModels[i][0]
|
||||
const oldVal = field.value
|
||||
|
||||
if (use_lora_model !== "") {
|
||||
use_lora_model = getModelPath(use_lora_model, [".ckpt", ".safetensors"])
|
||||
use_lora_model = use_lora_model !== "" ? use_lora_model : oldVal
|
||||
if (model_name !== "") {
|
||||
model_name = getModelPath(model_name, [".ckpt", ".safetensors"])
|
||||
model_name = model_name !== "" ? model_name : oldVal
|
||||
}
|
||||
field.value = model_name
|
||||
})
|
||||
|
||||
// clear the remaining entries
|
||||
for (let i = use_lora_model.length; i < loraModels.length; i++) {
|
||||
loraModels[i][0].value = ""
|
||||
}
|
||||
loraModelField.value = use_lora_model
|
||||
},
|
||||
readUI: () => loraModelField.value,
|
||||
parse: (val) => val,
|
||||
readUI: () => {
|
||||
let values = loraModels.map((e) => e[0].value)
|
||||
values = values.filter((e) => e.trim() !== "")
|
||||
values = values.length > 0 ? values : "None"
|
||||
return values
|
||||
},
|
||||
parse: (val) => {
|
||||
val = !val || val === "None" ? "" : val
|
||||
val = Array.isArray(val) ? val : [val]
|
||||
return val
|
||||
},
|
||||
},
|
||||
lora_alpha: {
|
||||
name: "LoRA Strength",
|
||||
setUI: (lora_alpha) => {
|
||||
loraAlphaField.value = lora_alpha
|
||||
updateLoraAlphaSlider()
|
||||
lora_alpha.forEach((model_strength, i) => {
|
||||
let field = loraModels[i][1]
|
||||
field.value = model_strength
|
||||
})
|
||||
|
||||
// clear the remaining entries
|
||||
for (let i = lora_alpha.length; i < loraModels.length; i++) {
|
||||
loraModels[i][1].value = 0
|
||||
}
|
||||
},
|
||||
readUI: () => {
|
||||
let models = loraModels.filter((e) => e[0].value.trim() !== "")
|
||||
let values = models.map((e) => e[1].value)
|
||||
values = values.length > 0 ? values : 0
|
||||
return values
|
||||
},
|
||||
parse: (val) => {
|
||||
val = Array.isArray(val) ? val : [val]
|
||||
val = val.map((e) => parseFloat(e))
|
||||
return val
|
||||
},
|
||||
readUI: () => parseFloat(loraAlphaField.value),
|
||||
parse: (val) => parseFloat(val),
|
||||
},
|
||||
use_hypernetwork_model: {
|
||||
name: "Hypernetwork model",
|
||||
@ -426,8 +455,11 @@ function restoreTaskToUI(task, fieldsToSkip) {
|
||||
}
|
||||
|
||||
if (!("use_lora_model" in task.reqBody)) {
|
||||
loraModelField.value = ""
|
||||
loraModelField.dispatchEvent(new Event("change"))
|
||||
loraModels.forEach((e) => {
|
||||
e[0].value = ""
|
||||
e[1].value = 0
|
||||
e[0].dispatchEvent(new Event("change"))
|
||||
})
|
||||
}
|
||||
|
||||
// restore the original prompt if provided (e.g. use settings), fallback to prompt as needed (e.g. copy/paste or d&d)
|
||||
|
||||
@ -103,9 +103,6 @@ let vaeModelField = new ModelDropdown(document.querySelector("#vae_model"), "vae
|
||||
let hypernetworkModelField = new ModelDropdown(document.querySelector("#hypernetwork_model"), "hypernetwork", "None")
|
||||
let hypernetworkStrengthSlider = document.querySelector("#hypernetwork_strength_slider")
|
||||
let hypernetworkStrengthField = document.querySelector("#hypernetwork_strength")
|
||||
let loraModelField = new ModelDropdown(document.querySelector("#lora_model"), "lora", "None")
|
||||
let loraAlphaSlider = document.querySelector("#lora_alpha_slider")
|
||||
let loraAlphaField = document.querySelector("#lora_alpha")
|
||||
let outputFormatField = document.querySelector("#output_format")
|
||||
let outputLosslessField = document.querySelector("#output_lossless")
|
||||
let outputLosslessContainer = document.querySelector("#output_lossless_container")
|
||||
@ -159,6 +156,8 @@ let undoButton = document.querySelector("#undo")
|
||||
let undoBuffer = []
|
||||
const UNDO_LIMIT = 20
|
||||
|
||||
let loraModels = []
|
||||
|
||||
imagePreview.addEventListener("drop", function(ev) {
|
||||
const data = ev.dataTransfer?.getData("text/plain")
|
||||
if (!data) {
|
||||
@ -1292,13 +1291,31 @@ function getCurrentUserRequest() {
|
||||
newTask.reqBody.use_hypernetwork_model = hypernetworkModelField.value
|
||||
newTask.reqBody.hypernetwork_strength = parseFloat(hypernetworkStrengthField.value)
|
||||
}
|
||||
if (testDiffusers.checked && loraModelField.value) {
|
||||
newTask.reqBody.use_lora_model = loraModelField.value
|
||||
newTask.reqBody.lora_alpha = parseFloat(loraAlphaField.value)
|
||||
if (testDiffusers.checked) {
|
||||
let [modelNames, modelStrengths] = getModelInfo(loraModels)
|
||||
|
||||
if (modelNames.length > 0) {
|
||||
modelNames = modelNames.length == 1 ? modelNames[0] : modelNames
|
||||
modelStrengths = modelStrengths.length == 1 ? modelStrengths[0] : modelStrengths
|
||||
|
||||
newTask.reqBody.use_lora_model = modelNames
|
||||
newTask.reqBody.lora_alpha = modelStrengths
|
||||
}
|
||||
}
|
||||
return newTask
|
||||
}
|
||||
|
||||
function getModelInfo(models) {
|
||||
let modelInfo = models.map((e) => [e[0].value, e[1].value])
|
||||
modelInfo = modelInfo.filter((e) => e[0].trim() !== "")
|
||||
modelInfo = modelInfo.map((e) => [e[0], parseFloat(e[1])])
|
||||
|
||||
let modelNames = modelInfo.map((e) => e[0])
|
||||
let modelStrengths = modelInfo.map((e) => e[1])
|
||||
|
||||
return [modelNames, modelStrengths]
|
||||
}
|
||||
|
||||
function getPrompts(prompts) {
|
||||
if (typeof prompts === "undefined") {
|
||||
prompts = promptField.value
|
||||
@ -1346,7 +1363,8 @@ function getPromptsNumber(prompts) {
|
||||
|
||||
let promptsToMake = []
|
||||
let numberOfPrompts = 0
|
||||
if (prompts.trim() !== "") { // this needs to stay sort of the same, as the prompts have to be passed through to the other functions
|
||||
if (prompts.trim() !== "") {
|
||||
// this needs to stay sort of the same, as the prompts have to be passed through to the other functions
|
||||
prompts = prompts.split("\n")
|
||||
prompts = prompts.map((prompt) => prompt.trim())
|
||||
prompts = prompts.filter((prompt) => prompt !== "")
|
||||
@ -1354,7 +1372,11 @@ function getPromptsNumber(prompts) {
|
||||
// estimate number of prompts
|
||||
let estimatedNumberOfPrompts = 0
|
||||
prompts.forEach((prompt) => {
|
||||
estimatedNumberOfPrompts += (prompt.match(/{[^}]*}/g) || []).map((e) => (e.match(/,/g) || []).length + 1).reduce( (p,a) => p*a, 1) * (2**(prompt.match(/\|/g) || []).length)
|
||||
estimatedNumberOfPrompts +=
|
||||
(prompt.match(/{[^}]*}/g) || [])
|
||||
.map((e) => (e.match(/,/g) || []).length + 1)
|
||||
.reduce((p, a) => p * a, 1) *
|
||||
2 ** (prompt.match(/\|/g) || []).length
|
||||
})
|
||||
|
||||
if (estimatedNumberOfPrompts >= 10000) {
|
||||
@ -1394,7 +1416,8 @@ function applySetOperator(prompts) {
|
||||
return promptsToMake
|
||||
}
|
||||
|
||||
function applyPermuteOperator(prompts) { // prompts is array of input, trimmed, filtered and split by \n
|
||||
function applyPermuteOperator(prompts) {
|
||||
// prompts is array of input, trimmed, filtered and split by \n
|
||||
let promptsToMake = []
|
||||
prompts.forEach((prompt) => {
|
||||
let promptMatrix = prompt.split("|")
|
||||
@ -1414,7 +1437,8 @@ function applyPermuteOperator(prompts) { // prompts is array of input, trimmed,
|
||||
}
|
||||
|
||||
// returns how many prompts would have to be made with the given prompts
|
||||
function applyPermuteOperatorNumber(prompts) { // prompts is array of input, trimmed, filtered and split by \n
|
||||
function applyPermuteOperatorNumber(prompts) {
|
||||
// prompts is array of input, trimmed, filtered and split by \n
|
||||
let numberOfPrompts = 0
|
||||
prompts.forEach((prompt) => {
|
||||
let promptCounter = 1
|
||||
@ -1510,8 +1534,12 @@ clearAllPreviewsBtn.addEventListener("click", (e) => {
|
||||
})
|
||||
|
||||
/* Download images popup */
|
||||
showDownloadDialogBtn.addEventListener("click", (e) => { saveAllImagesDialog.showModal() })
|
||||
saveAllImagesCloseBtn.addEventListener("click", (e) => { saveAllImagesDialog.close() })
|
||||
showDownloadDialogBtn.addEventListener("click", (e) => {
|
||||
saveAllImagesDialog.showModal()
|
||||
})
|
||||
saveAllImagesCloseBtn.addEventListener("click", (e) => {
|
||||
saveAllImagesDialog.close()
|
||||
})
|
||||
modalDialogCloseOnBackdropClick(saveAllImagesDialog)
|
||||
makeDialogDraggable(saveAllImagesDialog)
|
||||
|
||||
@ -1629,15 +1657,11 @@ function renameMakeImageButton() {
|
||||
imageLabel = totalImages + " Images"
|
||||
}
|
||||
if (SD.activeTasks.size == 0) {
|
||||
if (totalImages >= 10000)
|
||||
makeImageBtn.innerText = "Make 10000+ images"
|
||||
else
|
||||
makeImageBtn.innerText = "Make " + imageLabel
|
||||
if (totalImages >= 10000) makeImageBtn.innerText = "Make 10000+ images"
|
||||
else makeImageBtn.innerText = "Make " + imageLabel
|
||||
} else {
|
||||
if (totalImages >= 10000)
|
||||
makeImageBtn.innerText = "Enqueue 10000+ images"
|
||||
else
|
||||
makeImageBtn.innerText = "Enqueue Next " + imageLabel
|
||||
if (totalImages >= 10000) makeImageBtn.innerText = "Enqueue 10000+ images"
|
||||
else makeImageBtn.innerText = "Enqueue Next " + imageLabel
|
||||
}
|
||||
}
|
||||
numOutputsTotalField.addEventListener("change", renameMakeImageButton)
|
||||
@ -1829,36 +1853,6 @@ function updateHypernetworkStrengthContainer() {
|
||||
hypernetworkModelField.addEventListener("change", updateHypernetworkStrengthContainer)
|
||||
updateHypernetworkStrengthContainer()
|
||||
|
||||
/********************* LoRA alpha **********************/
|
||||
function updateLoraAlpha() {
|
||||
loraAlphaField.value = loraAlphaSlider.value / 100
|
||||
loraAlphaField.dispatchEvent(new Event("change"))
|
||||
}
|
||||
|
||||
function updateLoraAlphaSlider() {
|
||||
if (loraAlphaField.value < -2) {
|
||||
loraAlphaField.value = -2
|
||||
} else if (loraAlphaField.value > 2) {
|
||||
loraAlphaField.value = 2
|
||||
}
|
||||
|
||||
loraAlphaSlider.value = loraAlphaField.value * 100
|
||||
loraAlphaSlider.dispatchEvent(new Event("change"))
|
||||
}
|
||||
|
||||
loraAlphaSlider.addEventListener("input", updateLoraAlpha)
|
||||
loraAlphaField.addEventListener("input", updateLoraAlphaSlider)
|
||||
updateLoraAlpha()
|
||||
|
||||
function updateLoraAlphaContainer() {
|
||||
const loraModelContainer = document.querySelector("#lora_model_container")
|
||||
if (loraModelContainer && window.getComputedStyle(loraModelContainer).display !== "none") {
|
||||
document.querySelector("#lora_alpha_container").style.display = loraModelField.value === "" ? "none" : ""
|
||||
}
|
||||
}
|
||||
loraModelField.addEventListener("change", updateLoraAlphaContainer)
|
||||
updateLoraAlphaContainer()
|
||||
|
||||
/********************* JPEG/WEBP Quality **********************/
|
||||
function updateOutputQuality() {
|
||||
outputQualityField.value = 0 | outputQualitySlider.value
|
||||
@ -2076,9 +2070,8 @@ function resumeClient() {
|
||||
})
|
||||
}
|
||||
|
||||
|
||||
function splashScreen(force = false) {
|
||||
const splashVersion = splashScreenPopup.dataset['version']
|
||||
const splashVersion = splashScreenPopup.dataset["version"]
|
||||
const lastSplash = localStorage.getItem("lastSplashScreenVersion") || 0
|
||||
if (testDiffusers.checked) {
|
||||
if (force || lastSplash < splashVersion) {
|
||||
@ -2088,8 +2081,9 @@ function splashScreen(force = false) {
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
document.getElementById("logo_img").addEventListener("click", (e) => { splashScreen(true) })
|
||||
document.getElementById("logo_img").addEventListener("click", (e) => {
|
||||
splashScreen(true)
|
||||
})
|
||||
|
||||
promptField.addEventListener("input", debounce(renameMakeImageButton, 1000))
|
||||
|
||||
@ -2142,21 +2136,21 @@ document.getElementById("toggle-cloudflare-tunnel").addEventListener("click", as
|
||||
|
||||
/* Embeddings */
|
||||
|
||||
function updateEmbeddingsList(filter="") {
|
||||
function html(model, prefix="", filter="") {
|
||||
function updateEmbeddingsList(filter = "") {
|
||||
function html(model, prefix = "", filter = "") {
|
||||
filter = filter.toLowerCase()
|
||||
let toplevel=""
|
||||
let folders=""
|
||||
let toplevel = ""
|
||||
let folders = ""
|
||||
|
||||
model?.forEach( m => {
|
||||
if (typeof(m) == "string") {
|
||||
if (m.toLowerCase().search(filter)!=-1) {
|
||||
model?.forEach((m) => {
|
||||
if (typeof m == "string") {
|
||||
if (m.toLowerCase().search(filter) != -1) {
|
||||
toplevel += `<button data-embedding="${m}">${m}</button> `
|
||||
}
|
||||
} else {
|
||||
let subdir = html(m[1], prefix+m[0]+"/", filter)
|
||||
let subdir = html(m[1], prefix + m[0] + "/", filter)
|
||||
if (subdir != "") {
|
||||
folders += `<h4>${prefix}${m[0]}</h4>` + subdir
|
||||
folders += `<h4>${prefix}${m[0]}</h4>` + subdir
|
||||
}
|
||||
}
|
||||
})
|
||||
@ -2174,7 +2168,7 @@ function updateEmbeddingsList(filter="") {
|
||||
insertAtCursor(promptField, text)
|
||||
}
|
||||
} else {
|
||||
let pad=""
|
||||
let pad = ""
|
||||
if (e.shiftKey) {
|
||||
if (!negativePromptField.value.endsWith(" ")) {
|
||||
pad = " "
|
||||
@ -2189,13 +2183,25 @@ function updateEmbeddingsList(filter="") {
|
||||
}
|
||||
}
|
||||
|
||||
embeddingsList.innerHTML = html(modelsOptions.embeddings, "", filter)
|
||||
embeddingsList.querySelectorAll("button").forEach( (b) => { b.addEventListener("click", onButtonClick)})
|
||||
// Remove after fixing https://github.com/huggingface/diffusers/issues/3922
|
||||
let warning = ""
|
||||
if (vramUsageLevelField.value == "low") {
|
||||
warning = `
|
||||
<div style="border-color: var(--accent-color); border-width: 4px; border-radius: 1em; border-style: solid; background: black; text-align: center; padding: 1em; margin: 1em; ">
|
||||
<i class="fa fa-fire" style="color:#f7630c;"></i> Warning: Your GPU memory profile is set to "Low". Embeddings currently only work in "Balanced" mode!
|
||||
</div>`
|
||||
}
|
||||
// END of remove block
|
||||
|
||||
embeddingsList.innerHTML = warning + html(modelsOptions.embeddings, "", filter)
|
||||
embeddingsList.querySelectorAll("button").forEach((b) => {
|
||||
b.addEventListener("click", onButtonClick)
|
||||
})
|
||||
}
|
||||
|
||||
embeddingsButton.addEventListener("click", () => {
|
||||
updateEmbeddingsList()
|
||||
embeddingsSearchBox.value=""
|
||||
embeddingsSearchBox.value = ""
|
||||
embeddingsDialog.showModal()
|
||||
})
|
||||
embeddingsDialogCloseBtn.addEventListener("click", (e) => {
|
||||
@ -2208,7 +2214,6 @@ embeddingsSearchBox.addEventListener("input", (e) => {
|
||||
modalDialogCloseOnBackdropClick(embeddingsDialog)
|
||||
makeDialogDraggable(embeddingsDialog)
|
||||
|
||||
|
||||
if (testDiffusers.checked) {
|
||||
document.getElementById("embeddings-container").classList.remove("displayNone")
|
||||
}
|
||||
@ -2235,3 +2240,43 @@ prettifyInputs(document)
|
||||
// set the textbox as focused on start
|
||||
promptField.focus()
|
||||
promptField.selectionStart = promptField.value.length
|
||||
|
||||
// multi-models
|
||||
function addModelEntry(i, modelContainer, modelsList, modelType, defaultValue, strengthStep) {
|
||||
let nameId = modelType + "_model_" + i
|
||||
let strengthId = modelType + "_alpha_" + i
|
||||
|
||||
const modelEntry = document.createElement("div")
|
||||
modelEntry.className = "model_entry"
|
||||
modelEntry.innerHTML = `
|
||||
<input id="${nameId}" class="model_name" type="text" spellcheck="false" autocomplete="off" class="model-filter" data-path="" />
|
||||
<input id="${strengthId}" class="model_strength" type="number" step="${strengthStep}" style="width: 50pt" value="${defaultValue}" pattern="^-?[0-9]*\.?[0-9]*$" onkeypress="preventNonNumericalInput(event)"><br/>
|
||||
`
|
||||
|
||||
let modelName = new ModelDropdown(modelEntry.querySelector(".model_name"), modelType, "None")
|
||||
let modelStrength = modelEntry.querySelector(".model_strength")
|
||||
|
||||
modelContainer.appendChild(modelEntry)
|
||||
modelsList.push([modelName, modelStrength])
|
||||
}
|
||||
|
||||
function createLoRAEntries() {
|
||||
let container = document.querySelector("#lora_model_container .model_entries")
|
||||
for (let i = 0; i < 3; i++) {
|
||||
addModelEntry(i, container, loraModels, "lora", 0.5, 0.02)
|
||||
}
|
||||
}
|
||||
createLoRAEntries()
|
||||
|
||||
// chrome-like spinners only on hover
|
||||
function showSpinnerOnlyOnHover(e) {
|
||||
e.addEventListener("mouseenter", () => {
|
||||
e.setAttribute("type", "number")
|
||||
})
|
||||
e.addEventListener("mouseleave", () => {
|
||||
e.removeAttribute("type")
|
||||
})
|
||||
e.removeAttribute("type")
|
||||
}
|
||||
|
||||
document.querySelectorAll("input[type=number]").forEach(showSpinnerOnlyOnHover)
|
||||
|
||||
@ -436,7 +436,6 @@ async function getAppConfig() {
|
||||
|
||||
if (!testDiffusersEnabled) {
|
||||
document.querySelector("#lora_model_container").style.display = "none"
|
||||
document.querySelector("#lora_alpha_container").style.display = "none"
|
||||
document.querySelector("#tiling_container").style.display = "none"
|
||||
|
||||
document.querySelectorAll("#sampler_name option.diffusers-only").forEach((option) => {
|
||||
@ -444,7 +443,6 @@ async function getAppConfig() {
|
||||
})
|
||||
} else {
|
||||
document.querySelector("#lora_model_container").style.display = ""
|
||||
document.querySelector("#lora_alpha_container").style.display = loraModelField.value ? "" : "none"
|
||||
document.querySelector("#tiling_container").style.display = ""
|
||||
|
||||
document.querySelectorAll("#sampler_name option.k_diffusion-only").forEach((option) => {
|
||||
|
||||
@ -1074,6 +1074,12 @@ async function deleteKeys(keyToDelete) {
|
||||
|
||||
function modalDialogCloseOnBackdropClick(dialog) {
|
||||
dialog.addEventListener('mousedown', function (event) {
|
||||
// Firefox creates an event with clientX|Y = 0|0 when choosing an <option>.
|
||||
// Test whether the element interacted with is a child of the dialog, but not the
|
||||
// dialog itself (the backdrop would be a part of the dialog)
|
||||
if (dialog.contains(event.target) && dialog != event.target) {
|
||||
return
|
||||
}
|
||||
var rect = dialog.getBoundingClientRect()
|
||||
var isInDialog=(rect.top <= event.clientY && event.clientY <= rect.top + rect.height
|
||||
&& rect.left <= event.clientX && event.clientX <= rect.left + rect.width)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user