extern/easydiffusion
1
0
Fork 1
mirror of https://github.com/easydiffusion/easydiffusion.git synced 2025-04-30 22:34:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #227 from cmdr2/beta

Browse Source 
Merge beta
This commit is contained in:
cmdr2 2022-09-23 17:59:31 +05:30 committed by GitHub
commit 0d13fe67b0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 485 additions and 150 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

260
ui/index.html
View File

@ -25,7 +25,8 @@
} }
#prompt { #prompt {
width: 100%; width: 100%;
height: 50pt; height: 65pt;
box-sizing: border-box;
} }
@media screen and (max-width: 600px) { @media screen and (max-width: 600px) {
#prompt { #prompt {
@ -51,14 +52,14 @@
font-family: Verdana; font-family: Verdana;
font-size: 8pt; font-size: 8pt;
} }
#editor-settings-entries { .settings-box ul {
font-size: 9pt; font-size: 9pt;
margin-bottom: 5px; margin-bottom: 5px;
padding-left: 10px; padding-left: 10px;
list-style-type: none; list-style-type: none;
} }
#editor-settings-entries li { .settings-box li {
padding-bottom: 3pt; padding-bottom: 4pt;
} }
.editor-slider { .editor-slider {
transform: translateY(30%); transform: translateY(30%);
@ -111,23 +112,26 @@
} }
#container { #container {
width: 75%; width: 90%;
margin-left: auto; margin-left: auto;
margin-right: auto; margin-right: auto;
} }
@media screen and (max-width: 1400px) { @media screen and (max-width: 1800px) {
#container { #container {
width: 100%; width: 100%;
} }
} }
#meta small { #logo small {
font-size: 11pt; font-size: 11pt;
} }
#editor { #editor {
padding: 5px; padding: 5px;
} }
#editor label { #editor label {
font-weight: bold; font-weight: normal;
}
.settings-box label small {
color: rgb(153, 153, 153);
} }
#preview { #preview {
padding: 5px; padding: 5px;
@ -178,6 +182,9 @@
.col-50 { .col-50 {
flex: 50%; flex: 50%;
} }
.col-fixed-10 {
flex: 0 0 400pt;
}
.col-free { .col-free {
flex: 1; flex: 1;
} }
@ -256,16 +263,19 @@
display: none; display: none;
} }
#server-status { #server-status {
display: inline;
float: right; float: right;
transform: translateY(-5pt);
} }
#server-status-color { #server-status-color {
width: 8pt; /* width: 8pt;
height: 8pt; height: 8pt;
border-radius: 4pt; border-radius: 4pt; */
background-color: rgb(128, 87, 0); font-size: 14pt;
color: rgb(128, 87, 0);
/* background-color: rgb(197, 1, 1); */ /* background-color: rgb(197, 1, 1); */
float: left; /* transform: translateY(15%); */
transform: translateY(15%); display: inline;
} }
#server-status-msg { #server-status-msg {
color: rgb(128, 87, 0); color: rgb(128, 87, 0);
@ -294,21 +304,141 @@
#enable_mask { #enable_mask {
margin-top: 8pt; margin-top: 8pt;
} }
#top-nav {
padding-top: 3pt;
padding-bottom: 15pt;
}
#top-nav .icon {
padding-right: 4pt;
font-size: 14pt;
transform: translateY(1pt);
}
#logo {
display: inline;
}
#logo h1 {
display: inline;
}
#top-nav-items {
list-style-type: none;
display: inline;
float: right;
}
#top-nav-items > li {
float: left;
display: inline;
padding-left: 20pt;
cursor: default;
}
#initial-text {
padding-top: 15pt;
padding-left: 4pt;
}
.settings-subheader {
font-size: 10pt;
font-weight: bold;
}
.pl-5 {
padding-left: 5pt;
}
#system-settings {
width: 360pt;
transform: translateX(-100%) translateX(70pt);
padding-top: 10pt;
padding-bottom: 10pt;
}
#system-settings ul {
margin: 0;
padding: 0;
}
#system-settings li {
padding-left: 5pt;
}
#community-links {
list-style-type: none;
margin: 0;
padding: 12pt;
padding-bottom: 0pt;
transform: translateX(-15%);
}
#community-links li {
padding-bottom: 12pt;
display: block;
font-size: 10pt;
}
#community-links li .fa-fw {
padding-right: 2pt;
}
#community-links li a {
color: white;
text-decoration: none;
}
.dropdown {
overflow: hidden;
}
.dropdown-content {
display: none;
position: absolute;
z-index: 2;
background: rgb(18, 18, 19);
border: 2px solid rgb(37, 38, 41);
border-radius: 7px;
padding: 5px;
margin-bottom: 15px;
box-shadow: 0 20px 28px 0 rgba(0, 0, 0, 0.15), 0 6px 20px 0 rgba(0, 0, 0, 0.15);
}
.dropdown:hover .dropdown-content {
display: block;
}
</style> </style>
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.2.0/css/all.min.css">
<link rel="stylesheet" href="/media/drawingboard.min.css"> <link rel="stylesheet" href="/media/drawingboard.min.css">
<script src="/media/jquery-3.6.1.min.js"></script> <script src="/media/jquery-3.6.1.min.js"></script>
<script src="/media/drawingboard.min.js"></script> <script src="/media/drawingboard.min.js"></script>
</html> </html>
<body> <body>
<div id="container"> <div id="container">
<div class="flex-container"> <div id="top-nav">
<div id="editor" class="col-50"> <div id="logo">
<div id="meta"> <h1>Stable Diffusion UI <small>v2.16 <span id="updateBranchLabel"></span></small></h1>
<div id="server-status"> </div>
<div id="server-status-color">&nbsp;</div> <ul id="top-nav-items">
<span id="server-status-msg">Stable Diffusion is starting..</span> <li class="dropdown">
<span><i class="fa fa-comments icon"></i> Help & Community</span>
<ul id="community-links" class="dropdown-content">
<li><a href="https://github.com/cmdr2/stable-diffusion-ui/blob/main/Troubleshooting.md" target="_blank"><i class="fa-solid fa-circle-question fa-fw"></i> Usual problems and solutions</a></li>
<li><a href="https://discord.com/invite/u9yhsFmEkB" target="_blank"><i class="fa-brands fa-discord fa-fw"></i> Discord user community</a></li>
<li><a href="https://github.com/cmdr2/stable-diffusion-ui" target="_blank"><i class="fa-brands fa-github fa-fw"></i> Source code on GitHub</a></li>
</ul>
</li>
<li class="dropdown">
<span><i class="fa fa-gear icon"></i> Settings</span>
<div id="system-settings" class="panel-box settings-box dropdown-content">
<ul id="system-settings-entries">
<li><b class="settings-subheader">System Settings</b></li>
<br/>
<li><input id="save_to_disk" name="save_to_disk" type="checkbox"> <label for="save_to_disk">Automatically save to <input id="diskPath" name="diskPath" size="40" disabled></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 <small>(generates images faster, but uses an additional 1 GB of GPU memory)</small></label></li>
<li><input id="use_cpu" name="use_cpu" type="checkbox"> <label for="use_cpu">Use CPU instead of GPU <small>(warning: this will be *very* slow)</small></label></li>
<li><input id="use_full_precision" name="use_full_precision" type="checkbox"> <label for="use_full_precision">Use full precision <small>(for GPU-only. warning: this will consume more VRAM)</small></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> -->
<br/>
<li><input id="use_beta_channel" name="use_beta_channel" type="checkbox"> <label for="use_beta_channel">🔥Beta channel. Get the latest features immediately (but could be less stable). Please restart the program after changing this.</label></li>
</ul>
</div> </div>
<h1>Stable Diffusion UI <small>v2.14 <span id="updateBranchLabel"></span></small></h1> </li>
</ul>
</div>
<div class="flex-container">
<div id="editor" class="col-fixed-10">
<div id="server-status">
<div id="server-status-color">●</div>
<span id="server-status-msg">Stable Diffusion is starting..</span>
</div> </div>
<div id="editor-inputs"> <div id="editor-inputs">
<div id="editor-inputs-prompt" class="row"> <div id="editor-inputs-prompt" class="row">
@ -341,23 +471,25 @@
<div class="line-separator">&nbsp;</div> <div class="line-separator">&nbsp;</div>
<div id="editor-settings" class="panel-box"> <div id="editor-settings" class="panel-box settings-box">
<h4 class="collapsible">Advanced Settings</h4> <h4 class="collapsible">Image Settings</h4>
<ul id="editor-settings-entries" class="collapsible-content"> <ul id="editor-settings-entries" class="collapsible-content">
<li><input id="stream_image_progress" name="stream_image_progress" type="checkbox"> <label for="stream_image_progress">Show a live preview of the image (consumes more VRAM, slightly slower image generation)</label></li> <li><b class="settings-subheader">Image Settings</b></li>
<li><input id="use_face_correction" name="use_face_correction" type="checkbox" checked> <label for="use_face_correction">Fix incorrect faces and eyes (uses GFPGAN)</label></li> <li class="pl-5"><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> <li class="pl-5"><label for="num_outputs_total">Number of images to make:</label> <input id="num_outputs_total" name="num_outputs_total" value="1" size="1"> <label for="num_outputs_parallel">Generate in parallel:</label> <input id="num_outputs_parallel" name="num_outputs_parallel" value="1" size="1"> (images at once)</li>
<input id="use_upscale" name="use_upscale" type="checkbox"> <label for="use_upscale">Upscale the image to 4x resolution using </label> <li id="samplerSelection" class="pl-5"><label for="sampler">Sampler:</label>
<select id="upscale_model" name="upscale_model"> <select id="sampler" name="sampler">
<option value="RealESRGAN_x4plus" selected>RealESRGAN_x4plus</option> <option value="plms" selected>plms</option>
<option value="RealESRGAN_x4plus_anime_6B">RealESRGAN_x4plus_anime_6B</option> <option value="ddim">ddim</option>
<option value="heun">heun</option>
<option value="euler">euler</option>
<option value="euler_a">euler_a</option>
<option value="dpm2">dpm2</option>
<option value="dpm2_a">dpm2_a</option>
<option value="lms">lms</option>
</select> </select>
</li> </li>
<li><input id="show_only_filtered_image" name="show_only_filtered_image" type="checkbox" checked> <label for="show_only_filtered_image">Show only the corrected/upscaled image</label></li> <li class="pl-5"><label>Image Size: </label>
<br/>
<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 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"> <select id="width" name="width" value="512">
<option value="128">128 (*)</option> <option value="128">128 (*)</option>
<option value="192">192</option> <option value="192">192</option>
@ -378,9 +510,7 @@
<option value="1536">1536</option> <option value="1536">1536</option>
<option value="1792">1792</option> <option value="1792">1792</option>
<option value="2048">2048</option> <option value="2048">2048</option>
</select> </select> <label for="width"><small>(width)</small></label>
</li>
<li><label for="height">Height:</label>
<select id="height" name="height" value="512"> <select id="height" name="height" value="512">
<option value="128">128 (*)</option> <option value="128">128 (*)</option>
<option value="192">192</option> <option value="192">192</option>
@ -402,19 +532,27 @@
<option value="1792">1792</option> <option value="1792">1792</option>
<option value="2048">2048</option> <option value="2048">2048</option>
</select> </select>
<label for="height"><small>(height)</small></label>
</li> </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 class="pl-5"><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_slider">Guidance Scale:</label> <input id="guidance_scale_slider" name="guidance_scale_slider" class="editor-slider" value="75" type="range" min="10" max="200"> <input id="guidance_scale" name="guidance_scale" size="4"></li> <li class="pl-5"><label for="guidance_scale_slider">Guidance Scale:</label> <input id="guidance_scale_slider" name="guidance_scale_slider" class="editor-slider" value="75" type="range" min="10" max="500"> <input id="guidance_scale" name="guidance_scale" size="4"></li>
<li><span id="prompt_strength_container"><label for="prompt_strength_slider">Prompt Strength:</label> <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"><br/></span></li> <li class="pl-5"><span id="prompt_strength_container"><label for="prompt_strength_slider">Prompt Strength:</label> <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"><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 <input id="diskPath" name="diskPath" size="40" disabled></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)</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> -->
<br/> <br/>
<li><input id="use_beta_channel" name="use_beta_channel" type="checkbox"> <label for="use_beta_channel">🔥Beta channel. Get the latest features immediately (but could be less stable). Please restart the program after changing this.</label></li>
<li><b class="settings-subheader">Render Settings</b></li>
<li class="pl-5"><input id="stream_image_progress" name="stream_image_progress" type="checkbox"> <label for="stream_image_progress">Show a live preview of the image <small>(consumes more VRAM, slightly slower image generation)</small></label></li>
<li class="pl-5"><input id="use_face_correction" name="use_face_correction" type="checkbox" checked> <label for="use_face_correction">Fix incorrect faces and eyes <small>(uses GFPGAN)</small></label></li>
<li class="pl-5">
<input id="use_upscale" name="use_upscale" type="checkbox"> <label for="use_upscale">Upscale the image to 4x resolution using </label>
<select id="upscale_model" name="upscale_model">
<option value="RealESRGAN_x4plus" selected>RealESRGAN_x4plus</option>
<option value="RealESRGAN_x4plus_anime_6B">RealESRGAN_x4plus_anime_6B</option>
</select>
</li>
<li class="pl-5"><input id="show_only_filtered_image" name="show_only_filtered_image" type="checkbox" checked> <label for="show_only_filtered_image">Show only the corrected/upscaled image</label></li>
<br/>
<li><small>The system-related settings have been moved to the top-right corner.</small></li>
</ul> </ul>
</div> </div>
@ -425,8 +563,12 @@
</div> </div>
</div> </div>
<div id="preview" class="col-50"> <div id="preview" class="col-free">
<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="preview-prompt">
<div id="initial-text">
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>
<div id="outputMsg"></div> <div id="outputMsg"></div>
<div id="progressBar"></div> <div id="progressBar"></div>
@ -492,6 +634,8 @@ let diskPathField = document.querySelector('#diskPath')
let useBetaChannelField = document.querySelector("#use_beta_channel") let useBetaChannelField = document.querySelector("#use_beta_channel")
let promptStrengthSlider = document.querySelector('#prompt_strength_slider') let promptStrengthSlider = document.querySelector('#prompt_strength_slider')
let promptStrengthField = document.querySelector('#prompt_strength') let promptStrengthField = document.querySelector('#prompt_strength')
let samplerField = document.querySelector('#sampler')
let samplerSelectionContainer = document.querySelector("#samplerSelection")
let useFaceCorrectionField = document.querySelector("#use_face_correction") let useFaceCorrectionField = document.querySelector("#use_face_correction")
let useUpscalingField = document.querySelector("#use_upscale") let useUpscalingField = document.querySelector("#use_upscale")
let upscaleModelField = document.querySelector("#upscale_model") let upscaleModelField = document.querySelector("#upscale_model")
@ -645,12 +789,12 @@ function setStatus(statusType, msg, msgType) {
if (msgType == 'error') { if (msgType == 'error') {
// msg = '<span style="color: red">' + msg + '<span>' // msg = '<span style="color: red">' + msg + '<span>'
serverStatusColor.style.backgroundColor = 'red' serverStatusColor.style.color = 'red'
serverStatusMsg.style.color = 'red' serverStatusMsg.style.color = 'red'
serverStatusMsg.innerHTML = 'Stable Diffusion has stopped' serverStatusMsg.innerHTML = 'Stable Diffusion has stopped'
} else if (msgType == 'success') { } else if (msgType == 'success') {
// msg = '<span style="color: green">' + msg + '<span>' // msg = '<span style="color: green">' + msg + '<span>'
serverStatusColor.style.backgroundColor = 'green' serverStatusColor.style.color = 'green'
serverStatusMsg.style.color = 'green' serverStatusMsg.style.color = 'green'
serverStatusMsg.innerHTML = 'Stable Diffusion is ready' serverStatusMsg.innerHTML = 'Stable Diffusion is ready'
serverStatus = 'online' serverStatus = 'online'
@ -761,7 +905,7 @@ async function doMakeImage(reqBody, batchCount) {
if (stepUpdate.step === undefined) { if (stepUpdate.step === undefined) {
finalJSON += jsonStr finalJSON += jsonStr
} else { } else {
let batchSize = parseInt(reqBody['num_inference_steps']) let batchSize = stepUpdate.total_steps
let overallStepCount = stepUpdate.step + batchesDone * batchSize let overallStepCount = stepUpdate.step + batchesDone * batchSize
let totalSteps = batchCount * batchSize let totalSteps = batchCount * batchSize
let percent = 100 * (overallStepCount / totalSteps) let percent = 100 * (overallStepCount / totalSteps)
@ -1011,6 +1155,10 @@ async function makeImage() {
if (maskSetting.checked) { if (maskSetting.checked) {
reqBody['mask'] = inpaintingEditor.getImg() reqBody['mask'] = inpaintingEditor.getImg()
} }
reqBody['sampler'] = 'ddim'
} else {
reqBody['sampler'] = samplerField.value
} }
if (saveToDiskField.checked && diskPathField.value.trim() !== '') { if (saveToDiskField.checked && diskPathField.value.trim() !== '') {
@ -1177,8 +1325,8 @@ function updateGuidanceScale() {
function updateGuidanceScaleSlider() { function updateGuidanceScaleSlider() {
if (guidanceScaleField.value < 0) { if (guidanceScaleField.value < 0) {
guidanceScaleField.value = 0 guidanceScaleField.value = 0
} else if (guidanceScaleField.value > 20) { } else if (guidanceScaleField.value > 50) {
guidanceScaleField.value = 20 guidanceScaleField.value = 50
} }
guidanceScaleSlider.value = guidanceScaleField.value * 10 guidanceScaleSlider.value = guidanceScaleField.value * 10
@ -1278,6 +1426,7 @@ function showInitImagePreview() {
initImagePreviewContainer.style.display = 'block' initImagePreviewContainer.style.display = 'block'
inpaintingEditorContainer.style.display = 'none' inpaintingEditorContainer.style.display = 'none'
promptStrengthContainer.style.display = 'block' promptStrengthContainer.style.display = 'block'
samplerSelectionContainer.style.display = 'none'
// maskSetting.checked = false // maskSetting.checked = false
}) })
@ -1309,6 +1458,7 @@ initImageClearBtn.addEventListener('click', function() {
// maskSetting.style.display = 'none' // maskSetting.style.display = 'none'
promptStrengthContainer.style.display = 'none' promptStrengthContainer.style.display = 'none'
samplerSelectionContainer.style.display = 'block'
}) })
maskSetting.addEventListener('click', function() { maskSetting.addEventListener('click', function() {

3
ui/sd_internal/__init__.py
View File

@ -12,6 +12,7 @@ class Request:
height: int = 512 height: int = 512
seed: int = 42 seed: int = 42
prompt_strength: float = 0.8 prompt_strength: float = 0.8
sampler: str = None # "ddim", "plms", "heun", "euler", "euler_a", "dpm2", "dpm2_a", "lms"
# allow_nsfw: bool = False # allow_nsfw: bool = False
precision: str = "autocast" # or "full" precision: str = "autocast" # or "full"
save_to_disk_path: str = None save_to_disk_path: str = None
@ -36,6 +37,7 @@ class Request:
"height": self.height, "height": self.height,
"seed": self.seed, "seed": self.seed,
"prompt_strength": self.prompt_strength, "prompt_strength": self.prompt_strength,
"sampler": self.sampler,
"use_face_correction": self.use_face_correction, "use_face_correction": self.use_face_correction,
"use_upscale": self.use_upscale, "use_upscale": self.use_upscale,
} }
@ -46,6 +48,7 @@ class Request:
prompt: {self.prompt} prompt: {self.prompt}
seed: {self.seed} seed: {self.seed}
num_inference_steps: {self.num_inference_steps} num_inference_steps: {self.num_inference_steps}
sampler: {self.sampler}
guidance_scale: {self.guidance_scale} guidance_scale: {self.guidance_scale}
w: {self.width} w: {self.width}
h: {self.height} h: {self.height}

330
ui/sd_internal/ddim_callback.patch
View File

@ -1,5 +1,5 @@
diff --git a/optimizedSD/ddpm.py b/optimizedSD/ddpm.py diff --git a/optimizedSD/ddpm.py b/optimizedSD/ddpm.py
index b967b55..75ddd8b 100644 index b967b55..35ef520 100644
--- a/optimizedSD/ddpm.py --- a/optimizedSD/ddpm.py
+++ b/optimizedSD/ddpm.py +++ b/optimizedSD/ddpm.py
@@ -22,7 +22,7 @@ from ldm.util import exists, default, instantiate_from_config @@ -22,7 +22,7 @@ from ldm.util import exists, default, instantiate_from_config
@ -11,122 +11,312 @@ index b967b55..75ddd8b 100644
def disabled_train(self): def disabled_train(self):
"""Overwrite model.train with this function to make sure train/eval mode """Overwrite model.train with this function to make sure train/eval mode
@@ -485,6 +485,7 @@ class UNet(DDPM): @@ -506,6 +506,8 @@ class UNet(DDPM):
log_every_t=100,
unconditional_guidance_scale=1., x_latent = noise if x0 is None else x0
unconditional_conditioning=None, # sampling
+ streaming_callbacks = False, + if sampler in ('ddim', 'dpm2', 'heun', 'dpm2_a', 'lms') and not hasattr(self, 'ddim_timesteps'):
): + self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=False)
if sampler == "plms":
@@ -523,12 +524,15 @@ class UNet(DDPM): self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=False)
log_every_t=log_every_t, @@ -528,39 +530,46 @@ class UNet(DDPM):
unconditional_guidance_scale=unconditional_guidance_scale,
unconditional_conditioning=unconditional_conditioning,
+ streaming_callbacks=streaming_callbacks
)
elif sampler == "ddim": elif sampler == "ddim":
samples = self.ddim_sampling(x_latent, conditioning, S, unconditional_guidance_scale=unconditional_guidance_scale, samples = self.ddim_sampling(x_latent, conditioning, S, unconditional_guidance_scale=unconditional_guidance_scale,
unconditional_conditioning=unconditional_conditioning, unconditional_conditioning=unconditional_conditioning,
- mask = mask,init_latent=x_T,use_original_steps=False) - mask = mask,init_latent=x_T,use_original_steps=False)
+ mask = mask,init_latent=x_T,use_original_steps=False, + mask = mask,init_latent=x_T,use_original_steps=False,
+ callback=callback, img_callback=img_callback, + callback=callback, img_callback=img_callback)
+ streaming_callbacks=streaming_callbacks)
elif sampler == "euler": elif sampler == "euler":
self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=False) self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=False)
@@ -555,11 +559,15 @@ class UNet(DDPM): samples = self.euler_sampling(self.alphas_cumprod,x_latent, S, conditioning, unconditional_conditioning=unconditional_conditioning,
samples = self.lms_sampling(self.alphas_cumprod,x_latent, S, conditioning, unconditional_conditioning=unconditional_conditioning, - unconditional_guidance_scale=unconditional_guidance_scale)
unconditional_guidance_scale=unconditional_guidance_scale) + unconditional_guidance_scale=unconditional_guidance_scale,
+ img_callback=img_callback)
elif sampler == "euler_a":
self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=False)
samples = self.euler_ancestral_sampling(self.alphas_cumprod,x_latent, S, conditioning, unconditional_conditioning=unconditional_conditioning,
- unconditional_guidance_scale=unconditional_guidance_scale)
+ unconditional_guidance_scale=unconditional_guidance_scale,
+ img_callback=img_callback)
+ if streaming_callbacks: # this line needs to be right after the sampling() call elif sampler == "dpm2":
+ yield from samples samples = self.dpm_2_sampling(self.alphas_cumprod,x_latent, S, conditioning, unconditional_conditioning=unconditional_conditioning,
- unconditional_guidance_scale=unconditional_guidance_scale)
+ unconditional_guidance_scale=unconditional_guidance_scale,
+ img_callback=img_callback)
elif sampler == "heun":
samples = self.heun_sampling(self.alphas_cumprod,x_latent, S, conditioning, unconditional_conditioning=unconditional_conditioning,
- unconditional_guidance_scale=unconditional_guidance_scale)
+ unconditional_guidance_scale=unconditional_guidance_scale,
+ img_callback=img_callback)
elif sampler == "dpm2_a":
samples = self.dpm_2_ancestral_sampling(self.alphas_cumprod,x_latent, S, conditioning, unconditional_conditioning=unconditional_conditioning,
- unconditional_guidance_scale=unconditional_guidance_scale)
+ unconditional_guidance_scale=unconditional_guidance_scale,
+ img_callback=img_callback)
elif sampler == "lms":
samples = self.lms_sampling(self.alphas_cumprod,x_latent, S, conditioning, unconditional_conditioning=unconditional_conditioning,
- unconditional_guidance_scale=unconditional_guidance_scale)
+ unconditional_guidance_scale=unconditional_guidance_scale,
+ img_callback=img_callback)
+ +
+ yield from samples
if(self.turbo): if(self.turbo):
self.model1.to("cpu") self.model1.to("cpu")
self.model2.to("cpu") self.model2.to("cpu")
- return samples - return samples
+ if not streaming_callbacks: -
+ return samples
@torch.no_grad() @torch.no_grad()
def plms_sampling(self, cond,b, img, def plms_sampling(self, cond,b, img,
@@ -567,7 +575,8 @@ class UNet(DDPM): ddim_use_original_steps=False,
callback=None, quantize_denoised=False, @@ -599,10 +608,10 @@ class UNet(DDPM):
mask=None, x0=None, img_callback=None, log_every_t=100,
temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
- unconditional_guidance_scale=1., unconditional_conditioning=None,):
+ unconditional_guidance_scale=1., unconditional_conditioning=None,
+ streaming_callbacks=False):
device = self.betas.device
timesteps = self.ddim_timesteps
@@ -599,10 +608,21 @@ class UNet(DDPM):
old_eps.append(e_t) old_eps.append(e_t)
if len(old_eps) >= 4: if len(old_eps) >= 4:
old_eps.pop(0) old_eps.pop(0)
- if callback: callback(i) - if callback: callback(i)
- if img_callback: img_callback(pred_x0, i) - if img_callback: img_callback(pred_x0, i)
- + if callback: yield from callback(i)
+ if img_callback: yield from img_callback(pred_x0, i)
- return img - return img
+ if callback: + yield from img_callback(img, len(iterator)-1)
+ if streaming_callbacks:
+ yield from callback(i)
+ else:
+ callback(i)
+ if img_callback:
+ if streaming_callbacks:
+ yield from img_callback(pred_x0, i)
+ else:
+ img_callback(pred_x0, i)
+
+ if streaming_callbacks and img_callback:
+ yield from img_callback(img, len(iterator)-1)
+ else:
+ return img
@torch.no_grad() @torch.no_grad()
def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False, def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
@@ -706,7 +726,9 @@ class UNet(DDPM): @@ -706,7 +715,8 @@ class UNet(DDPM):
@torch.no_grad() @torch.no_grad()
def ddim_sampling(self, x_latent, cond, t_start, unconditional_guidance_scale=1.0, unconditional_conditioning=None, def ddim_sampling(self, x_latent, cond, t_start, unconditional_guidance_scale=1.0, unconditional_conditioning=None,
- mask = None,init_latent=None,use_original_steps=False): - mask = None,init_latent=None,use_original_steps=False):
+ mask = None,init_latent=None,use_original_steps=False, + mask = None,init_latent=None,use_original_steps=False,
+ callback=None, img_callback=None, + callback=None, img_callback=None):
+ streaming_callbacks=False):
timesteps = self.ddim_timesteps timesteps = self.ddim_timesteps
timesteps = timesteps[:t_start] timesteps = timesteps[:t_start]
@@ -730,10 +752,24 @@ class UNet(DDPM): @@ -730,10 +740,13 @@ class UNet(DDPM):
unconditional_guidance_scale=unconditional_guidance_scale, unconditional_guidance_scale=unconditional_guidance_scale,
unconditional_conditioning=unconditional_conditioning) unconditional_conditioning=unconditional_conditioning)
+ if callback: + if callback: yield from callback(i)
+ if streaming_callbacks: + if img_callback: yield from img_callback(x_dec, i)
+ yield from callback(i)
+ else:
+ callback(i)
+ if img_callback:
+ if streaming_callbacks:
+ yield from img_callback(x_dec, i)
+ else:
+ img_callback(x_dec, i)
+ +
if mask is not None: if mask is not None:
- return x0 * mask + (1. - mask) * x_dec - return x0 * mask + (1. - mask) * x_dec
+ x_dec = x0 * mask + (1. - mask) * x_dec + x_dec = x0 * mask + (1. - mask) * x_dec
- return x_dec - return x_dec
+ if streaming_callbacks and img_callback: + yield from img_callback(x_dec, len(iterator)-1)
+ yield from img_callback(x_dec, len(iterator)-1)
+ else:
+ return x_dec
@torch.no_grad() @torch.no_grad()
@@ -779,13 +792,16 @@ class UNet(DDPM):
@torch.no_grad()
- def euler_sampling(self, ac, x, S, cond, unconditional_conditioning = None, unconditional_guidance_scale = 1,extra_args=None,callback=None, disable=None, s_churn=0., s_tmin=0., s_tmax=float('inf'), s_noise=1.):
+ def euler_sampling(self, ac, x, S, cond, unconditional_conditioning = None, unconditional_guidance_scale = 1,extra_args=None,callback=None, disable=None, s_churn=0., s_tmin=0., s_tmax=float('inf'), s_noise=1.,
+ img_callback=None):
"""Implements Algorithm 2 (Euler steps) from Karras et al. (2022)."""
extra_args = {} if extra_args is None else extra_args
cvd = CompVisDenoiser(ac)
sigmas = cvd.get_sigmas(S)
x = x*sigmas[0]
+ print(f"Running Euler Sampling with {len(sigmas) - 1} timesteps")
+
s_in = x.new_ones([x.shape[0]]).half()
for i in trange(len(sigmas) - 1, disable=disable):
gamma = min(s_churn / (len(sigmas) - 1), 2 ** 0.5 - 1) if s_tmin <= sigmas[i] <= s_tmax else 0.
@@ -807,13 +823,18 @@ class UNet(DDPM):
d = to_d(x, sigma_hat, denoised)
if callback is not None:
callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigma_hat, 'denoised': denoised})
+
+ if img_callback: yield from img_callback(x, i)
+
dt = sigmas[i + 1] - sigma_hat
# Euler method
x = x + d * dt
- return x
+
+ yield from img_callback(x, len(sigmas)-1)
@torch.no_grad()
- def euler_ancestral_sampling(self,ac,x, S, cond, unconditional_conditioning = None, unconditional_guidance_scale = 1,extra_args=None, callback=None, disable=None):
+ def euler_ancestral_sampling(self,ac,x, S, cond, unconditional_conditioning = None, unconditional_guidance_scale = 1,extra_args=None, callback=None, disable=None,
+ img_callback=None):
"""Ancestral sampling with Euler method steps."""
extra_args = {} if extra_args is None else extra_args
@@ -822,6 +843,8 @@ class UNet(DDPM):
sigmas = cvd.get_sigmas(S)
x = x*sigmas[0]
+ print(f"Running Euler Ancestral Sampling with {len(sigmas) - 1} timesteps")
+
s_in = x.new_ones([x.shape[0]]).half()
for i in trange(len(sigmas) - 1, disable=disable):
@@ -837,17 +860,22 @@ class UNet(DDPM):
sigma_down, sigma_up = get_ancestral_step(sigmas[i], sigmas[i + 1])
if callback is not None:
callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigmas[i], 'denoised': denoised})
+
+ if img_callback: yield from img_callback(x, i)
+
d = to_d(x, sigmas[i], denoised)
# Euler method
dt = sigma_down - sigmas[i]
x = x + d * dt
x = x + torch.randn_like(x) * sigma_up
- return x
+
+ yield from img_callback(x, len(sigmas)-1)
@torch.no_grad()
- def heun_sampling(self, ac, x, S, cond, unconditional_conditioning = None, unconditional_guidance_scale = 1, extra_args=None, callback=None, disable=None, s_churn=0., s_tmin=0., s_tmax=float('inf'), s_noise=1.):
+ def heun_sampling(self, ac, x, S, cond, unconditional_conditioning = None, unconditional_guidance_scale = 1, extra_args=None, callback=None, disable=None, s_churn=0., s_tmin=0., s_tmax=float('inf'), s_noise=1.,
+ img_callback=None):
"""Implements Algorithm 2 (Heun steps) from Karras et al. (2022)."""
extra_args = {} if extra_args is None else extra_args
@@ -855,6 +883,8 @@ class UNet(DDPM):
sigmas = cvd.get_sigmas(S)
x = x*sigmas[0]
+ print(f"Running Heun Sampling with {len(sigmas) - 1} timesteps")
+
s_in = x.new_ones([x.shape[0]]).half()
for i in trange(len(sigmas) - 1, disable=disable):
@@ -876,6 +906,9 @@ class UNet(DDPM):
d = to_d(x, sigma_hat, denoised)
if callback is not None:
callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigma_hat, 'denoised': denoised})
+
+ if img_callback: yield from img_callback(x, i)
+
dt = sigmas[i + 1] - sigma_hat
if sigmas[i + 1] == 0:
# Euler method
@@ -895,11 +928,13 @@ class UNet(DDPM):
d_2 = to_d(x_2, sigmas[i + 1], denoised_2)
d_prime = (d + d_2) / 2
x = x + d_prime * dt
- return x
+
+ yield from img_callback(x, len(sigmas)-1)
@torch.no_grad()
- def dpm_2_sampling(self,ac,x, S, cond, unconditional_conditioning = None, unconditional_guidance_scale = 1,extra_args=None, callback=None, disable=None, s_churn=0., s_tmin=0., s_tmax=float('inf'), s_noise=1.):
+ def dpm_2_sampling(self,ac,x, S, cond, unconditional_conditioning = None, unconditional_guidance_scale = 1,extra_args=None, callback=None, disable=None, s_churn=0., s_tmin=0., s_tmax=float('inf'), s_noise=1.,
+ img_callback=None):
"""A sampler inspired by DPM-Solver-2 and Algorithm 2 from Karras et al. (2022)."""
extra_args = {} if extra_args is None else extra_args
@@ -907,6 +942,8 @@ class UNet(DDPM):
sigmas = cvd.get_sigmas(S)
x = x*sigmas[0]
+ print(f"Running DPM2 Sampling with {len(sigmas) - 1} timesteps")
+
s_in = x.new_ones([x.shape[0]]).half()
for i in trange(len(sigmas) - 1, disable=disable):
gamma = min(s_churn / (len(sigmas) - 1), 2 ** 0.5 - 1) if s_tmin <= sigmas[i] <= s_tmax else 0.
@@ -924,7 +961,7 @@ class UNet(DDPM):
e_t_uncond, e_t = (x_in + eps * c_out).chunk(2)
denoised = e_t_uncond + unconditional_guidance_scale * (e_t - e_t_uncond)
-
+ if img_callback: yield from img_callback(x, i)
d = to_d(x, sigma_hat, denoised)
# Midpoint method, where the midpoint is chosen according to a rho=3 Karras schedule
@@ -945,11 +982,13 @@ class UNet(DDPM):
d_2 = to_d(x_2, sigma_mid, denoised_2)
x = x + d_2 * dt_2
- return x
+
+ yield from img_callback(x, len(sigmas)-1)
@torch.no_grad()
- def dpm_2_ancestral_sampling(self,ac,x, S, cond, unconditional_conditioning = None, unconditional_guidance_scale = 1, extra_args=None, callback=None, disable=None):
+ def dpm_2_ancestral_sampling(self,ac,x, S, cond, unconditional_conditioning = None, unconditional_guidance_scale = 1, extra_args=None, callback=None, disable=None,
+ img_callback=None):
"""Ancestral sampling with DPM-Solver inspired second-order steps."""
extra_args = {} if extra_args is None else extra_args
@@ -957,6 +996,8 @@ class UNet(DDPM):
sigmas = cvd.get_sigmas(S)
x = x*sigmas[0]
+ print(f"Running DPM2 Ancestral Sampling with {len(sigmas) - 1} timesteps")
+
s_in = x.new_ones([x.shape[0]]).half()
for i in trange(len(sigmas) - 1, disable=disable):
@@ -973,6 +1014,9 @@ class UNet(DDPM):
sigma_down, sigma_up = get_ancestral_step(sigmas[i], sigmas[i + 1])
if callback is not None:
callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigmas[i], 'denoised': denoised})
+
+ if img_callback: yield from img_callback(x, i)
+
d = to_d(x, sigmas[i], denoised)
# Midpoint method, where the midpoint is chosen according to a rho=3 Karras schedule
sigma_mid = ((sigmas[i] ** (1 / 3) + sigma_down ** (1 / 3)) / 2) ** 3
@@ -993,11 +1037,13 @@ class UNet(DDPM):
d_2 = to_d(x_2, sigma_mid, denoised_2)
x = x + d_2 * dt_2
x = x + torch.randn_like(x) * sigma_up
- return x
+
+ yield from img_callback(x, len(sigmas)-1)
@torch.no_grad()
- def lms_sampling(self,ac,x, S, cond, unconditional_conditioning = None, unconditional_guidance_scale = 1, extra_args=None, callback=None, disable=None, order=4):
+ def lms_sampling(self,ac,x, S, cond, unconditional_conditioning = None, unconditional_guidance_scale = 1, extra_args=None, callback=None, disable=None, order=4,
+ img_callback=None):
extra_args = {} if extra_args is None else extra_args
s_in = x.new_ones([x.shape[0]])
@@ -1005,6 +1051,8 @@ class UNet(DDPM):
sigmas = cvd.get_sigmas(S)
x = x*sigmas[0]
+ print(f"Running LMS Sampling with {len(sigmas) - 1} timesteps")
+
ds = []
for i in trange(len(sigmas) - 1, disable=disable):
@@ -1017,6 +1065,7 @@ class UNet(DDPM):
e_t_uncond, e_t = (x_in + eps * c_out).chunk(2)
denoised = e_t_uncond + unconditional_guidance_scale * (e_t - e_t_uncond)
+ if img_callback: yield from img_callback(x, i)
d = to_d(x, sigmas[i], denoised)
ds.append(d)
@@ -1027,4 +1076,5 @@ class UNet(DDPM):
cur_order = min(i + 1, order)
coeffs = [linear_multistep_coeff(cur_order, sigmas.cpu(), i, j) for j in range(cur_order)]
x = x + sum(coeff * d for coeff, d in zip(coeffs, reversed(ds)))
- return x
+
+ yield from img_callback(x, len(sigmas)-1)
diff --git a/optimizedSD/openaimodelSplit.py b/optimizedSD/openaimodelSplit.py diff --git a/optimizedSD/openaimodelSplit.py b/optimizedSD/openaimodelSplit.py
index abc3098..7a32ffe 100644 index abc3098..7a32ffe 100644
--- a/optimizedSD/openaimodelSplit.py --- a/optimizedSD/openaimodelSplit.py

40
ui/sd_internal/runtime.py
View File

@ -275,6 +275,7 @@ def do_mk_img(req: Request):
opt_use_upscale = req.use_upscale opt_use_upscale = req.use_upscale
opt_show_only_filtered = req.show_only_filtered_image opt_show_only_filtered = req.show_only_filtered_image
opt_format = 'png' opt_format = 'png'
opt_sampler_name = req.sampler
print(req.to_string(), '\n device', device) print(req.to_string(), '\n device', device)
@ -368,7 +369,8 @@ def do_mk_img(req: Request):
partial_x_samples = x_samples partial_x_samples = x_samples
if req.stream_progress_updates: if req.stream_progress_updates:
progress = {"step": i, "total_steps": opt_ddim_steps} n_steps = opt_ddim_steps if req.init_image is None else t_enc
progress = {"step": i, "total_steps": n_steps}
if req.stream_image_progress and i % 5 == 0: if req.stream_image_progress and i % 5 == 0:
partial_images = [] partial_images = []
@ -399,12 +401,11 @@ def do_mk_img(req: Request):
# run the handler # run the handler
try: try:
if handler == _txt2img: if handler == _txt2img:
x_samples = _txt2img(opt_W, opt_H, opt_n_samples, opt_ddim_steps, opt_scale, None, opt_C, opt_f, opt_ddim_eta, c, uc, opt_seed, img_callback, req.stream_progress_updates, mask) x_samples = _txt2img(opt_W, opt_H, opt_n_samples, opt_ddim_steps, opt_scale, None, opt_C, opt_f, opt_ddim_eta, c, uc, opt_seed, img_callback, mask, opt_sampler_name)
else: else:
x_samples = _img2img(init_latent, t_enc, batch_size, opt_scale, c, uc, opt_ddim_steps, opt_ddim_eta, opt_seed, img_callback, req.stream_progress_updates, mask) x_samples = _img2img(init_latent, t_enc, batch_size, opt_scale, c, uc, opt_ddim_steps, opt_ddim_eta, opt_seed, img_callback, mask)
if req.stream_progress_updates: yield from x_samples
yield from x_samples
x_samples = partial_x_samples x_samples = partial_x_samples
except UserInitiatedStop: except UserInitiatedStop:
@ -443,7 +444,7 @@ def do_mk_img(req: Request):
if return_orig_img: if return_orig_img:
save_image(img, img_out_path) save_image(img, img_out_path)
save_metadata(meta_out_path, prompts, opt_seed, opt_W, opt_H, opt_ddim_steps, opt_scale, opt_strength, opt_use_face_correction, opt_use_upscale) save_metadata(meta_out_path, prompts, opt_seed, opt_W, opt_H, opt_ddim_steps, opt_scale, opt_strength, opt_use_face_correction, opt_use_upscale, opt_sampler_name)
if return_orig_img: if return_orig_img:
img_data = img_to_base64_str(img) img_data = img_to_base64_str(img)
@ -496,10 +497,7 @@ def do_mk_img(req: Request):
print('Task completed') print('Task completed')
if req.stream_progress_updates: yield json.dumps(res.json())
yield json.dumps(res.json())
else:
return res
def save_image(img, img_out_path): def save_image(img, img_out_path):
try: try:
@ -507,8 +505,8 @@ def save_image(img, img_out_path):
except: except:
print('could not save the file', traceback.format_exc()) print('could not save the file', traceback.format_exc())
def save_metadata(meta_out_path, prompts, opt_seed, opt_W, opt_H, opt_ddim_steps, opt_scale, opt_prompt_strength, opt_correct_face, opt_upscale): def save_metadata(meta_out_path, prompts, opt_seed, opt_W, opt_H, opt_ddim_steps, opt_scale, opt_prompt_strength, opt_correct_face, opt_upscale, sampler_name):
metadata = f"{prompts[0]}\nWidth: {opt_W}\nHeight: {opt_H}\nSeed: {opt_seed}\nSteps: {opt_ddim_steps}\nGuidance Scale: {opt_scale}\nPrompt Strength: {opt_prompt_strength}\nUse Face Correction: {opt_correct_face}\nUse Upscaling: {opt_upscale}" metadata = f"{prompts[0]}\nWidth: {opt_W}\nHeight: {opt_H}\nSeed: {opt_seed}\nSteps: {opt_ddim_steps}\nGuidance Scale: {opt_scale}\nPrompt Strength: {opt_prompt_strength}\nUse Face Correction: {opt_correct_face}\nUse Upscaling: {opt_upscale}\nSampler: {sampler_name}"
try: try:
with open(meta_out_path, 'w') as f: with open(meta_out_path, 'w') as f:
@ -516,7 +514,7 @@ def save_metadata(meta_out_path, prompts, opt_seed, opt_W, opt_H, opt_ddim_steps
except: except:
print('could not save the file', traceback.format_exc()) print('could not save the file', traceback.format_exc())
def _txt2img(opt_W, opt_H, opt_n_samples, opt_ddim_steps, opt_scale, start_code, opt_C, opt_f, opt_ddim_eta, c, uc, opt_seed, img_callback, streaming_callbacks, mask): def _txt2img(opt_W, opt_H, opt_n_samples, opt_ddim_steps, opt_scale, start_code, opt_C, opt_f, opt_ddim_eta, c, uc, opt_seed, img_callback, mask, sampler_name):
shape = [opt_n_samples, opt_C, opt_H // opt_f, opt_W // opt_f] shape = [opt_n_samples, opt_C, opt_H // opt_f, opt_W // opt_f]
if device != "cpu": if device != "cpu":
@ -536,17 +534,13 @@ def _txt2img(opt_W, opt_H, opt_n_samples, opt_ddim_steps, opt_scale, start_code,
eta=opt_ddim_eta, eta=opt_ddim_eta,
x_T=start_code, x_T=start_code,
img_callback=img_callback, img_callback=img_callback,
streaming_callbacks=streaming_callbacks,
mask=mask, mask=mask,
sampler = 'plms', sampler = sampler_name,
) )
if streaming_callbacks: yield from samples_ddim
yield from samples_ddim
else:
return samples_ddim
def _img2img(init_latent, t_enc, batch_size, opt_scale, c, uc, opt_ddim_steps, opt_ddim_eta, opt_seed, img_callback, streaming_callbacks, mask): def _img2img(init_latent, t_enc, batch_size, opt_scale, c, uc, opt_ddim_steps, opt_ddim_eta, opt_seed, img_callback, mask):
# encode (scaled latent) # encode (scaled latent)
z_enc = model.stochastic_encode( z_enc = model.stochastic_encode(
init_latent, init_latent,
@ -565,16 +559,12 @@ def _img2img(init_latent, t_enc, batch_size, opt_scale, c, uc, opt_ddim_steps, o
unconditional_guidance_scale=opt_scale, unconditional_guidance_scale=opt_scale,
unconditional_conditioning=uc, unconditional_conditioning=uc,
img_callback=img_callback, img_callback=img_callback,
streaming_callbacks=streaming_callbacks,
mask=mask, mask=mask,
x_T=x_T, x_T=x_T,
sampler = 'ddim' sampler = 'ddim'
) )
if streaming_callbacks: yield from samples_ddim
yield from samples_ddim
else:
return samples_ddim
def move_fs_to_cpu(): def move_fs_to_cpu():
if device != "cpu": if device != "cpu":

2
ui/server.py
View File

@ -57,6 +57,7 @@ class ImageRequest(BaseModel):
height: int = 512 height: int = 512
seed: int = 42 seed: int = 42
prompt_strength: float = 0.8 prompt_strength: float = 0.8
sampler: str = None # "ddim", "plms", "heun", "euler", "euler_a", "dpm2", "dpm2_a", "lms"
# allow_nsfw: bool = False # allow_nsfw: bool = False
save_to_disk_path: str = None save_to_disk_path: str = None
turbo: bool = True turbo: bool = True
@ -130,6 +131,7 @@ def image(req : ImageRequest):
r.height = req.height r.height = req.height
r.seed = req.seed r.seed = req.seed
r.prompt_strength = req.prompt_strength r.prompt_strength = req.prompt_strength
r.sampler = req.sampler
# r.allow_nsfw = req.allow_nsfw # r.allow_nsfw = req.allow_nsfw
r.turbo = req.turbo r.turbo = req.turbo
r.use_cpu = req.use_cpu r.use_cpu = req.use_cpu