Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity
InvokeAI/other/README-CompViz/index.html

2712 lines
65 KiB
HTML
Raw Permalink Blame History

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<meta name="author" content="mauwii">
<link rel="canonical" href="https://invoke-ai.github.io/InvokeAI/other/README-CompViz/">
<link rel="prev" href="../CONTRIBUTORS/">
<link rel="icon" href="../../img/favicon.ico">
<meta name="generator" content="mkdocs-1.6.0, mkdocs-material-9.5.33">
<title>CompViz-Readme - InvokeAI Documentation</title>
<link rel="stylesheet" href="../../assets/stylesheets/main.3cba04c6.min.css">
<link rel="stylesheet" href="../../assets/stylesheets/palette.06af60db.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<link rel="stylesheet" href="../../assets/_mkdocstrings.css">
<link rel="stylesheet" href="../../stylesheets/extra.css">
<script>__md_scope=new URL("../..",location),__md_hash=e=>[...e].reduce((e,_)=>(e<<5)-e+_.charCodeAt(0),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
<script id="__analytics">function __md_analytics(){function n(){dataLayer.push(arguments)}window.dataLayer=window.dataLayer||[],n("js",new Date),n("config","G-2X4JR4S4FB"),document.addEventListener("DOMContentLoaded",function(){document.forms.search&&document.forms.search.query.addEventListener("blur",function(){this.value&&n("event","search",{search_term:this.value})}),document$.subscribe(function(){var a=document.forms.feedback;if(void 0!==a)for(var e of a.querySelectorAll("[type=submit]"))e.addEventListener("click",function(e){e.preventDefault();var t=document.location.pathname,e=this.getAttribute("data-md-value");n("event","feedback",{page:t,data:e}),a.firstElementChild.disabled=!0;e=a.querySelector(".md-feedback__note [data-md-value='"+e+"']");e&&(e.hidden=!1)}),a.hidden=!1}),location$.subscribe(function(e){n("config","G-2X4JR4S4FB",{page_path:e.pathname})})});var e=document.createElement("script");e.async=!0,e.src="https://www.googletagmanager.com/gtag/js?id=G-2X4JR4S4FB",document.getElementById("__analytics").insertAdjacentElement("afterEnd",e)}</script>
<script>"undefined"!=typeof __md_analytics&&__md_analytics()</script>
</head>
<body dir="ltr" data-md-color-scheme="slate" data-md-color-primary="indigo" data-md-color-accent="indigo">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a href="#readme-from-compvizstable-diffusion" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header md-header--shadow md-header--lifted" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href="../.." title="InvokeAI Documentation" class="md-header__button md-logo" aria-label="InvokeAI Documentation" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54Z"/></svg>
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3V6m0 5h18v2H3v-2m0 5h18v2H3v-2Z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
InvokeAI Documentation
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
CompViz-Readme
</span>
</div>
</div>
</div>
<label class="md-header__button md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg>
</label>
<div class="md-search" data-md-component="search" role="dialog">
<label class="md-search__overlay" for="__search"></label>
<div class="md-search__inner" role="search">
<form class="md-search__form" name="search">
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
<label class="md-search__icon md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11h12Z"/></svg>
</label>
<nav class="md-search__options" aria-label="Search">
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41Z"/></svg>
</button>
</nav>
<div class="md-search__suggest" data-md-component="search-suggest"></div>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Initializing search
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
<div class="md-header__source">
<a href="https://github.com/invoke-ai/InvokeAI" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 496 512"><!--! Font Awesome Free 6.6.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6zm-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3zm44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9zM244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8zM97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1zm-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7zm32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1zm-11.4-14.7c-1.6 1-1.6 3.6 0 5.9 1.6 2.3 4.3 3.3 5.6 2.3 1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2z"/></svg>
</div>
<div class="md-source__repository">
invoke-ai/InvokeAI
</div>
</a>
</div>
</nav>
<nav class="md-tabs" aria-label="Tabs" data-md-component="tabs">
<div class="md-grid">
<ul class="md-tabs__list">
<li class="md-tabs__item">
<a href="../.." class="md-tabs__link">
Home
</a>
</li>
<li class="md-tabs__item">
<a href="../../installation/INSTALLATION/" class="md-tabs__link">
Installation
</a>
</li>
<li class="md-tabs__item">
<a href="../../nodes/overview/" class="md-tabs__link">
Workflows & Nodes
</a>
</li>
<li class="md-tabs__item">
<a href="../../nodes/communityNodes/" class="md-tabs__link">
Community Nodes
</a>
</li>
<li class="md-tabs__item">
<a href="../../features/" class="md-tabs__link">
Features
</a>
</li>
<li class="md-tabs__item">
<a href="../../contributing/CONTRIBUTING/" class="md-tabs__link">
Contributing
</a>
</li>
<li class="md-tabs__item">
<a href="../../help/gettingStartedWithAI/" class="md-tabs__link">
Help
</a>
</li>
<li class="md-tabs__item md-tabs__item--active">
<a href="../CONTRIBUTORS/" class="md-tabs__link">
Other
</a>
</li>
</ul>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary md-nav--lifted md-nav--integrated" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href="../.." title="InvokeAI Documentation" class="md-nav__button md-logo" aria-label="InvokeAI Documentation" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54Z"/></svg>
</a>
InvokeAI Documentation
</label>
<div class="md-nav__source">
<a href="https://github.com/invoke-ai/InvokeAI" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 496 512"><!--! Font Awesome Free 6.6.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6zm-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3zm44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9zM244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8zM97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1zm-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7zm32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1zm-11.4-14.7c-1.6 1-1.6 3.6 0 5.9 1.6 2.3 4.3 3.3 5.6 2.3 1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2z"/></svg>
</div>
<div class="md-source__repository">
invoke-ai/InvokeAI
</div>
</a>
</div>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../.." class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2" >
<label class="md-nav__link" for="__nav_2" id="__nav_2_label" tabindex="0">
<span class="md-ellipsis">
Installation
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2">
<span class="md-nav__icon md-icon"></span>
Installation
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../installation/INSTALLATION/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../installation/INSTALL_REQUIREMENTS/" class="md-nav__link">
<span class="md-ellipsis">
Requirements
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../installation/010_INSTALL_AUTOMATED/" class="md-nav__link">
<span class="md-ellipsis">
Automatic Install
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../installation/020_INSTALL_MANUAL/" class="md-nav__link">
<span class="md-ellipsis">
Manual Install
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../installation/INSTALL_DEVELOPMENT/" class="md-nav__link">
<span class="md-ellipsis">
Developer Install
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../installation/040_INSTALL_DOCKER/" class="md-nav__link">
<span class="md-ellipsis">
Docker
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../installation/050_INSTALLING_MODELS/" class="md-nav__link">
<span class="md-ellipsis">
Installing Models
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../installation/060_INSTALL_PATCHMATCH/" class="md-nav__link">
<span class="md-ellipsis">
Installing PyPatchMatch
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3" >
<label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="0">
<span class="md-ellipsis">
Workflows & Nodes
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3">
<span class="md-nav__icon md-icon"></span>
Workflows & Nodes
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../nodes/overview/" class="md-nav__link">
<span class="md-ellipsis">
Nodes Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../nodes/NODES/" class="md-nav__link">
<span class="md-ellipsis">
Workflow Editor Basics
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../nodes/defaultNodes/" class="md-nav__link">
<span class="md-ellipsis">
List of Default Nodes
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../nodes/exampleWorkflows/" class="md-nav__link">
<span class="md-ellipsis">
Example Workflows
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../nodes/comfyToInvoke/" class="md-nav__link">
<span class="md-ellipsis">
ComfyUI to InvokeAI
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../nodes/detailedNodes/faceTools/" class="md-nav__link">
<span class="md-ellipsis">
Facetool Node
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../nodes/contributingNodes/" class="md-nav__link">
<span class="md-ellipsis">
Contributing Nodes
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../nodes/NODES_MIGRATION_V3_V4/" class="md-nav__link">
<span class="md-ellipsis">
Migrating from v3 to v4
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../nodes/INVOCATION_API/" class="md-nav__link">
<span class="md-ellipsis">
Invocation API
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../nodes/communityNodes/" class="md-nav__link">
<span class="md-ellipsis">
Community Nodes
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_5" >
<div class="md-nav__link md-nav__container">
<a href="../../features/" class="md-nav__link ">
<span class="md-ellipsis">
Features
</span>
</a>
<label class="md-nav__link " for="__nav_5" id="__nav_5_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_5">
<span class="md-nav__icon md-icon"></span>
Features
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../help/gettingStartedWithAI/" class="md-nav__link">
<span class="md-ellipsis">
New to InvokeAI?
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../features/CONFIGURATION/" class="md-nav__link">
<span class="md-ellipsis">
Configuration
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../features/DATABASE/" class="md-nav__link">
<span class="md-ellipsis">
Database
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../features/CONTROLNET/" class="md-nav__link">
<span class="md-ellipsis">
Control Adapters
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../features/IMG2IMG/" class="md-nav__link">
<span class="md-ellipsis">
Image-to-Image
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../features/LOGGING/" class="md-nav__link">
<span class="md-ellipsis">
Controlling Logging
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../features/LORAS/" class="md-nav__link">
<span class="md-ellipsis">
LoRAs & LCM-LoRAs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../features/MODEL_MERGING/" class="md-nav__link">
<span class="md-ellipsis">
Model Merging
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../nodes/overview" class="md-nav__link">
<span class="md-ellipsis">
Workflows & Nodes
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../features/WATERMARK%2BNSFW/" class="md-nav__link">
<span class="md-ellipsis">
NSFW Checker
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../features/POSTPROCESS/" class="md-nav__link">
<span class="md-ellipsis">
Postprocessing
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../features/PROMPTS/" class="md-nav__link">
<span class="md-ellipsis">
Prompting Features
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_5_14" >
<label class="md-nav__link" for="__nav_5_14" id="__nav_5_14_label" tabindex="0">
<span class="md-ellipsis">
Textual Inversions
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_5_14_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_5_14">
<span class="md-nav__icon md-icon"></span>
Textual Inversions
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../features/TEXTUAL_INVERSIONS/" class="md-nav__link">
<span class="md-ellipsis">
Textual Inversions
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../features/TRAINING/" class="md-nav__link">
<span class="md-ellipsis">
Textual Inversion Training
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../features/UNIFIED_CANVAS/" class="md-nav__link">
<span class="md-ellipsis">
Unified Canvas
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../features/WEB/" class="md-nav__link">
<span class="md-ellipsis">
InvokeAI Web Server
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../features/WEBUIHOTKEYS/" class="md-nav__link">
<span class="md-ellipsis">
WebUI Hotkeys
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../features/UTILITIES/" class="md-nav__link">
<span class="md-ellipsis">
Maintenance Utilities
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../features/OTHER/" class="md-nav__link">
<span class="md-ellipsis">
Other
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_6" >
<label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="0">
<span class="md-ellipsis">
Contributing
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_6">
<span class="md-nav__icon md-icon"></span>
Contributing
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../contributing/CONTRIBUTING/" class="md-nav__link">
<span class="md-ellipsis">
How to Contribute
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../CODE_OF_CONDUCT/" class="md-nav__link">
<span class="md-ellipsis">
InvokeAI Code of Conduct
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_6_3" >
<label class="md-nav__link" for="__nav_6_3" id="__nav_6_3_label" tabindex="0">
<span class="md-ellipsis">
Development
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_6_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_6_3">
<span class="md-nav__icon md-icon"></span>
Development
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../contributing/contribution_guides/development/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../contributing/contribution_guides/newContributorChecklist/" class="md-nav__link">
<span class="md-ellipsis">
New Contributors
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../contributing/MODEL_MANAGER/" class="md-nav__link">
<span class="md-ellipsis">
Model Manager v2
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../contributing/contribution_guides/contributingToFrontend.md" class="md-nav__link">
<span class="md-ellipsis">
Frontend Documentation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../contributing/LOCAL_DEVELOPMENT/" class="md-nav__link">
<span class="md-ellipsis">
Local Development
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../contributing/TESTS/" class="md-nav__link">
<span class="md-ellipsis">
Testing
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_6_3_7" >
<label class="md-nav__link" for="__nav_6_3_7" id="__nav_6_3_7_label" tabindex="0">
<span class="md-ellipsis">
Frontend
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_6_3_7_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_6_3_7">
<span class="md-nav__icon md-icon"></span>
Frontend
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../contributing/frontend/OVERVIEW/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../contributing/frontend/STATE_MGMT/" class="md-nav__link">
<span class="md-ellipsis">
State Management
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../contributing/frontend/WORKFLOWS/" class="md-nav__link">
<span class="md-ellipsis">
Workflows
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../contributing/contribution_guides/documentation/" class="md-nav__link">
<span class="md-ellipsis">
Documentation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../contributing/INVOCATIONS/" class="md-nav__link">
<span class="md-ellipsis">
Nodes
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../contributing/MODEL_MANAGER/" class="md-nav__link">
<span class="md-ellipsis">
Model Manager v2
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../contributing/DOWNLOAD_QUEUE/" class="md-nav__link">
<span class="md-ellipsis">
Download Queue
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../contributing/contribution_guides/translation/" class="md-nav__link">
<span class="md-ellipsis">
Translation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../contributing/contribution_guides/tutorials/" class="md-nav__link">
<span class="md-ellipsis">
Tutorials
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7" >
<label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="0">
<span class="md-ellipsis">
Help
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_7">
<span class="md-nav__icon md-icon"></span>
Help
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../help/gettingStartedWithAI/" class="md-nav__link">
<span class="md-ellipsis">
New to InvokeAI?
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../help/FAQ/" class="md-nav__link">
<span class="md-ellipsis">
FAQ
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../help/diffusion/" class="md-nav__link">
<span class="md-ellipsis">
Diffusion Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../help/SAMPLER_CONVERGENCE/" class="md-nav__link">
<span class="md-ellipsis">
Sampler Convergence
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--active md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_8" checked>
<label class="md-nav__link" for="__nav_8" id="__nav_8_label" tabindex="">
<span class="md-ellipsis">
Other
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_8_label" aria-expanded="true">
<label class="md-nav__title" for="__nav_8">
<span class="md-nav__icon md-icon"></span>
Other
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../CONTRIBUTORS/" class="md-nav__link">
<span class="md-ellipsis">
Contributors
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<label class="md-nav__link md-nav__link--active" for="__toc">
<span class="md-ellipsis">
CompViz-README
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
CompViz-README
</span>
</a>
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#cvpr-22-oral" class="md-nav__link">
<span class="md-ellipsis">
CVPR '22 Oral
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#requirements" class="md-nav__link">
<span class="md-ellipsis">
Requirements
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#stable-diffusion-v1" class="md-nav__link">
<span class="md-ellipsis">
Stable Diffusion v1
</span>
</a>
<nav class="md-nav" aria-label="Stable Diffusion v1">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#weights" class="md-nav__link">
<span class="md-ellipsis">
Weights
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#text-to-image-with-stable-diffusion" class="md-nav__link">
<span class="md-ellipsis">
Text-to-Image with Stable Diffusion
</span>
</a>
<nav class="md-nav" aria-label="Text-to-Image with Stable Diffusion">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#sampling-script" class="md-nav__link">
<span class="md-ellipsis">
Sampling Script
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#diffusers-integration" class="md-nav__link">
<span class="md-ellipsis">
Diffusers Integration
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#image-modification-with-stable-diffusion" class="md-nav__link">
<span class="md-ellipsis">
Image Modification with Stable Diffusion
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#comments" class="md-nav__link">
<span class="md-ellipsis">
Comments
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#bibtex" class="md-nav__link">
<span class="md-ellipsis">
BibTeX
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="readme-from-compvizstable-diffusion"><em>README from <a href="https://github.com/CompVis/stable-diffusion">CompViz/stable-diffusion</a></em><a class="headerlink" href="#readme-from-compvizstable-diffusion" title="Permanent link">#</a></h1>
<p><em>Stable Diffusion was made possible thanks to a collaboration with
<a href="https://stability.ai/">Stability AI</a> and <a href="https://runwayml.com/">Runway</a> and
builds upon our previous work:</em></p>
<p><a href="https://ommer-lab.com/research/latent-diffusion-models/"><strong>High-Resolution Image Synthesis with Latent Diffusion Models</strong></a><br/>
<a href="https://github.com/rromb">Robin Rombach</a>*,
<a href="https://github.com/ablattmann">Andreas Blattmann</a>*,
<a href="https://github.com/qp-qp">Dominik Lorenz</a>\,
<a href="https://github.com/pesser">Patrick Esser</a>,
<a href="https://hci.iwr.uni-heidelberg.de/Staff/bommer">Björn Ommer</a><br/></p>
<h2 id="cvpr-22-oral"><strong>CVPR '22 Oral</strong><a class="headerlink" href="#cvpr-22-oral" title="Permanent link">#</a></h2>
<p>which is available on <a href="https://github.com/CompVis/latent-diffusion">GitHub</a>. PDF
at <a href="https://arxiv.org/abs/2112.10752">arXiv</a>. Please also visit our
<a href="https://ommer-lab.com/research/latent-diffusion-models/">Project page</a>.</p>
<p><img alt="txt2img-stable2" src="../../assets/stable-samples/txt2img/merged-0006.png" />
<a href="#stable-diffusion-v1">Stable Diffusion</a> is a latent text-to-image diffusion
model. Thanks to a generous compute donation from
<a href="https://stability.ai/">Stability AI</a> and support from
<a href="https://laion.ai/">LAION</a>, we were able to train a Latent Diffusion Model on
512x512 images from a subset of the <a href="https://laion.ai/blog/laion-5b/">LAION-5B</a>
database. Similar to Google's <a href="https://arxiv.org/abs/2205.11487">Imagen</a>, this
model uses a frozen CLIP ViT-L/14 text encoder to condition the model on text
prompts. With its 860M UNet and 123M text encoder, the model is relatively
lightweight and runs on a GPU with at least 10GB VRAM. See
<a href="#stable-diffusion-v1">this section</a> below and the
<a href="https://huggingface.co/CompVis/stable-diffusion">model card</a>.</p>
<h2 id="requirements">Requirements<a class="headerlink" href="#requirements" title="Permanent link">#</a></h2>
<p>A suitable <a href="https://conda.io/">conda</a> environment named <code>ldm</code> can be created and
activated with:</p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-0-1" name="__codelineno-0-1" href="#__codelineno-0-1"></a>conda env create
<a id="__codelineno-0-2" name="__codelineno-0-2" href="#__codelineno-0-2"></a>conda activate ldm
</code></pre></div>
<p>Note that the first line may be abbreviated <code>conda env create</code>, since conda will
look for <code>environment.yml</code> by default.</p>
<p>You can also update an existing
<a href="https://github.com/CompVis/latent-diffusion">latent diffusion</a> environment by
running</p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-1-1" name="__codelineno-1-1" href="#__codelineno-1-1"></a>conda<span class="w"> </span>install<span class="w"> </span>pytorch<span class="w"> </span>torchvision<span class="w"> </span>-c<span class="w"> </span>pytorch
<a id="__codelineno-1-2" name="__codelineno-1-2" href="#__codelineno-1-2"></a>pip<span class="w"> </span>install<span class="w"> </span><span class="nv">transformers</span><span class="o">==</span><span class="m">4</span>.19.2
<a id="__codelineno-1-3" name="__codelineno-1-3" href="#__codelineno-1-3"></a>pip<span class="w"> </span>install<span class="w"> </span>-e<span class="w"> </span>.
</code></pre></div>
<h2 id="stable-diffusion-v1">Stable Diffusion v1<a class="headerlink" href="#stable-diffusion-v1" title="Permanent link">#</a></h2>
<p>Stable Diffusion v1 refers to a specific configuration of the model architecture
that uses a downsampling-factor 8 autoencoder with an 860M UNet and CLIP
ViT-L/14 text encoder for the diffusion model. The model was pretrained on
256x256 images and then finetuned on 512x512 images.</p>
<p>*Note: Stable Diffusion v1 is a general text-to-image diffusion model and
therefore mirrors biases and (mis-)conceptions that are present in its training
data. Details on the training procedure and data, as well as the intended use of
the model can be found in the corresponding
<a href="https://huggingface.co/CompVis/stable-diffusion">model card</a>. Research into the
safe deployment of general text-to-image models is an ongoing effort. To prevent
misuse and harm, we currently provide access to the checkpoints only for
<a href="https://stability.ai/academia-access-form">academic research purposes upon request</a>.
<strong>This is an experiment in safe and community-driven publication of a capable
and general text-to-image model. We are working on a public release with a more
permissive license that also incorporates ethical considerations.*</strong></p>
<p><a href="https://stability.ai/academia-access-form">Request access to Stable Diffusion v1 checkpoints for academic research</a></p>
<h3 id="weights">Weights<a class="headerlink" href="#weights" title="Permanent link">#</a></h3>
<p>We currently provide three checkpoints, <code>sd-v1-1.ckpt</code>, <code>sd-v1-2.ckpt</code> and
<code>sd-v1-3.ckpt</code>, which were trained as follows,</p>
<ul>
<li><code>sd-v1-1.ckpt</code>: 237k steps at resolution <code>256x256</code> on
<a href="https://huggingface.co/datasets/laion/laion2B-en">laion2B-en</a>. 194k steps at
resolution <code>512x512</code> on
<a href="https://huggingface.co/datasets/laion/laion-high-resolution">laion-high-resolution</a>
(170M examples from LAION-5B with resolution <code>&gt;= 1024x1024</code>).</li>
<li><code>sd-v1-2.ckpt</code>: Resumed from <code>sd-v1-1.ckpt</code>. 515k steps at resolution
<code>512x512</code> on "laion-improved-aesthetics" (a subset of laion2B-en, filtered to
images with an original size <code>&gt;= 512x512</code>, estimated aesthetics score <code>&gt; 5.0</code>,
and an estimated watermark probability <code>&lt; 0.5</code>. The watermark estimate is from
the LAION-5B metadata, the aesthetics score is estimated using an
<a href="https://github.com/christophschuhmann/improved-aesthetic-predictor">improved aesthetics estimator</a>).</li>
<li><code>sd-v1-3.ckpt</code>: Resumed from <code>sd-v1-2.ckpt</code>. 195k steps at resolution
<code>512x512</code> on "laion-improved-aesthetics" and 10\% dropping of the
text-conditioning to improve
<a href="https://arxiv.org/abs/2207.12598">classifier-free guidance sampling</a>.</li>
</ul>
<p>Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0,
5.0, 6.0, 7.0, 8.0) and 50 PLMS sampling steps show the relative improvements of
the checkpoints: <img alt="sd evaluation results" src="../../assets/v1-variants-scores.jpg" /></p>
<h3 id="text-to-image-with-stable-diffusion">Text-to-Image with Stable Diffusion<a class="headerlink" href="#text-to-image-with-stable-diffusion" title="Permanent link">#</a></h3>
<p><img alt="txt2img-stable2" src="../../assets/stable-samples/txt2img/merged-0005.png" />
<img alt="txt2img-stable2" src="../../assets/stable-samples/txt2img/merged-0007.png" /></p>
<p>Stable Diffusion is a latent diffusion model conditioned on the (non-pooled)
text embeddings of a CLIP ViT-L/14 text encoder.</p>
<h4 id="sampling-script">Sampling Script<a class="headerlink" href="#sampling-script" title="Permanent link">#</a></h4>
<p>After <a href="#weights">obtaining the weights</a>, link them</p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-2-1" name="__codelineno-2-1" href="#__codelineno-2-1"></a>mkdir -p models/ldm/stable-diffusion-v1/
<a id="__codelineno-2-2" name="__codelineno-2-2" href="#__codelineno-2-2"></a>ln -s &lt;path/to/model.ckpt&gt; models/ldm/stable-diffusion-v1/model.ckpt
</code></pre></div>
<p>and sample with</p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-3-1" name="__codelineno-3-1" href="#__codelineno-3-1"></a>python scripts/txt2img.py --prompt &quot;a photograph of an astronaut riding a horse&quot; --plms
</code></pre></div>
<p>By default, this uses a guidance scale of <code>--scale 7.5</code>,
<a href="https://github.com/CompVis/latent-diffusion/pull/51">Katherine Crowson's implementation</a>
of the <a href="https://arxiv.org/abs/2202.09778">PLMS</a> sampler, and renders images of
size 512x512 (which it was trained on) in 50 steps. All supported arguments are
listed below (type <code>python scripts/txt2img.py --help</code>).</p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-4-1" name="__codelineno-4-1" href="#__codelineno-4-1"></a>usage: txt2img.py [-h] [--prompt [PROMPT]] [--outdir [OUTDIR]] [--skip_grid] [--skip_save] [--ddim_steps DDIM_STEPS] [--plms] [--laion400m] [--fixed_code] [--ddim_eta DDIM_ETA] [--n_iter N_ITER] [--H H] [--W W] [--C C] [--f F] [--n_samples N_SAMPLES] [--n_rows N_ROWS]
<a id="__codelineno-4-2" name="__codelineno-4-2" href="#__codelineno-4-2"></a> [--scale SCALE] [--from-file FROM_FILE] [--config CONFIG] [--ckpt CKPT] [--seed SEED] [--precision {full,autocast}]
<a id="__codelineno-4-3" name="__codelineno-4-3" href="#__codelineno-4-3"></a>
<a id="__codelineno-4-4" name="__codelineno-4-4" href="#__codelineno-4-4"></a>optional arguments:
<a id="__codelineno-4-5" name="__codelineno-4-5" href="#__codelineno-4-5"></a> -h, --help show this help message and exit
<a id="__codelineno-4-6" name="__codelineno-4-6" href="#__codelineno-4-6"></a> --prompt [PROMPT] the prompt to render
<a id="__codelineno-4-7" name="__codelineno-4-7" href="#__codelineno-4-7"></a> --outdir [OUTDIR] dir to write results to
<a id="__codelineno-4-8" name="__codelineno-4-8" href="#__codelineno-4-8"></a> --skip_grid do not save a grid, only individual samples. Helpful when evaluating lots of samples
<a id="__codelineno-4-9" name="__codelineno-4-9" href="#__codelineno-4-9"></a> --skip_save do not save individual samples. For speed measurements.
<a id="__codelineno-4-10" name="__codelineno-4-10" href="#__codelineno-4-10"></a> --ddim_steps DDIM_STEPS
<a id="__codelineno-4-11" name="__codelineno-4-11" href="#__codelineno-4-11"></a> number of ddim sampling steps
<a id="__codelineno-4-12" name="__codelineno-4-12" href="#__codelineno-4-12"></a> --plms use plms sampling
<a id="__codelineno-4-13" name="__codelineno-4-13" href="#__codelineno-4-13"></a> --laion400m uses the LAION400M model
<a id="__codelineno-4-14" name="__codelineno-4-14" href="#__codelineno-4-14"></a> --fixed_code if enabled, uses the same starting code across samples
<a id="__codelineno-4-15" name="__codelineno-4-15" href="#__codelineno-4-15"></a> --ddim_eta DDIM_ETA ddim eta (eta=0.0 corresponds to deterministic sampling
<a id="__codelineno-4-16" name="__codelineno-4-16" href="#__codelineno-4-16"></a> --n_iter N_ITER sample this often
<a id="__codelineno-4-17" name="__codelineno-4-17" href="#__codelineno-4-17"></a> --H H image height, in pixel space
<a id="__codelineno-4-18" name="__codelineno-4-18" href="#__codelineno-4-18"></a> --W W image width, in pixel space
<a id="__codelineno-4-19" name="__codelineno-4-19" href="#__codelineno-4-19"></a> --C C latent channels
<a id="__codelineno-4-20" name="__codelineno-4-20" href="#__codelineno-4-20"></a> --f F downsampling factor
<a id="__codelineno-4-21" name="__codelineno-4-21" href="#__codelineno-4-21"></a> --n_samples N_SAMPLES
<a id="__codelineno-4-22" name="__codelineno-4-22" href="#__codelineno-4-22"></a> how many samples to produce for each given prompt. A.k.a. batch size
<a id="__codelineno-4-23" name="__codelineno-4-23" href="#__codelineno-4-23"></a> (note that the seeds for each image in the batch will be unavailable)
<a id="__codelineno-4-24" name="__codelineno-4-24" href="#__codelineno-4-24"></a> --n_rows N_ROWS rows in the grid (default: n_samples)
<a id="__codelineno-4-25" name="__codelineno-4-25" href="#__codelineno-4-25"></a> --scale SCALE unconditional guidance scale: eps = eps(x, empty) + scale * (eps(x, cond) - eps(x, empty))
<a id="__codelineno-4-26" name="__codelineno-4-26" href="#__codelineno-4-26"></a> --from-file FROM_FILE
<a id="__codelineno-4-27" name="__codelineno-4-27" href="#__codelineno-4-27"></a> if specified, load prompts from this file
<a id="__codelineno-4-28" name="__codelineno-4-28" href="#__codelineno-4-28"></a> --config CONFIG path to config which constructs model
<a id="__codelineno-4-29" name="__codelineno-4-29" href="#__codelineno-4-29"></a> --ckpt CKPT path to checkpoint of model
<a id="__codelineno-4-30" name="__codelineno-4-30" href="#__codelineno-4-30"></a> --seed SEED the seed (for reproducible sampling)
<a id="__codelineno-4-31" name="__codelineno-4-31" href="#__codelineno-4-31"></a> --precision {full,autocast}
<a id="__codelineno-4-32" name="__codelineno-4-32" href="#__codelineno-4-32"></a> evaluate at this precision
</code></pre></div>
<p>Note: The inference config for all v1 versions is designed to be used with
EMA-only checkpoints. For this reason <code>use_ema=False</code> is set in the
configuration, otherwise the code will try to switch from non-EMA to EMA
weights. If you want to examine the effect of EMA vs no EMA, we provide "full"
checkpoints which contain both types of weights. For these, <code>use_ema=False</code> will
load and use the non-EMA weights.</p>
<h4 id="diffusers-integration">Diffusers Integration<a class="headerlink" href="#diffusers-integration" title="Permanent link">#</a></h4>
<p>Another way to download and sample Stable Diffusion is by using the
<a href="https://github.com/huggingface/diffusers/tree/main#new--stable-diffusion-is-now-fully-compatible-with-diffusers">diffusers library</a></p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-5-1" name="__codelineno-5-1" href="#__codelineno-5-1"></a><span class="c1"># make sure you&#39;re logged in with `huggingface-cli login`</span>
<a id="__codelineno-5-2" name="__codelineno-5-2" href="#__codelineno-5-2"></a><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">autocast</span>
<a id="__codelineno-5-3" name="__codelineno-5-3" href="#__codelineno-5-3"></a><span class="kn">from</span> <span class="nn">diffusers</span> <span class="kn">import</span> <span class="n">StableDiffusionPipeline</span><span class="p">,</span> <span class="n">LMSDiscreteScheduler</span>
<a id="__codelineno-5-4" name="__codelineno-5-4" href="#__codelineno-5-4"></a>
<a id="__codelineno-5-5" name="__codelineno-5-5" href="#__codelineno-5-5"></a><span class="n">pipe</span> <span class="o">=</span> <span class="n">StableDiffusionPipeline</span><span class="o">.</span><span class="n">from_pretrained</span><span class="p">(</span>
<a id="__codelineno-5-6" name="__codelineno-5-6" href="#__codelineno-5-6"></a> <span class="s2">&quot;CompVis/stable-diffusion-v1-3-diffusers&quot;</span><span class="p">,</span>
<a id="__codelineno-5-7" name="__codelineno-5-7" href="#__codelineno-5-7"></a> <span class="n">use_auth_token</span><span class="o">=</span><span class="kc">True</span>
<a id="__codelineno-5-8" name="__codelineno-5-8" href="#__codelineno-5-8"></a><span class="p">)</span>
<a id="__codelineno-5-9" name="__codelineno-5-9" href="#__codelineno-5-9"></a>
<a id="__codelineno-5-10" name="__codelineno-5-10" href="#__codelineno-5-10"></a><span class="n">prompt</span> <span class="o">=</span> <span class="s2">&quot;a photo of an astronaut riding a horse on mars&quot;</span>
<a id="__codelineno-5-11" name="__codelineno-5-11" href="#__codelineno-5-11"></a><span class="k">with</span> <span class="n">autocast</span><span class="p">(</span><span class="s2">&quot;cuda&quot;</span><span class="p">):</span>
<a id="__codelineno-5-12" name="__codelineno-5-12" href="#__codelineno-5-12"></a> <span class="n">image</span> <span class="o">=</span> <span class="n">pipe</span><span class="p">(</span><span class="n">prompt</span><span class="p">)[</span><span class="s2">&quot;sample&quot;</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
<a id="__codelineno-5-13" name="__codelineno-5-13" href="#__codelineno-5-13"></a>
<a id="__codelineno-5-14" name="__codelineno-5-14" href="#__codelineno-5-14"></a><span class="n">image</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="s2">&quot;astronaut_rides_horse.png&quot;</span><span class="p">)</span>
</code></pre></div>
<h3 id="image-modification-with-stable-diffusion">Image Modification with Stable Diffusion<a class="headerlink" href="#image-modification-with-stable-diffusion" title="Permanent link">#</a></h3>
<p>By using a diffusion-denoising mechanism as first proposed by
<a href="https://arxiv.org/abs/2108.01073">SDEdit</a>, the model can be used for different
tasks such as text-guided image-to-image translation and upscaling. Similar to
the txt2img sampling script, we provide a script to perform image modification
with Stable Diffusion.</p>
<p>The following describes an example where a rough sketch made in
<a href="https://www.pinta-project.com/">Pinta</a> is converted into a detailed artwork.</p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-6-1" name="__codelineno-6-1" href="#__codelineno-6-1"></a>python scripts/img2img.py --prompt &quot;A fantasy landscape, trending on artstation&quot; --init-img &lt;path-to-img.jpg&gt; --strength 0.8
</code></pre></div>
<p>Here, strength is a value between 0.0 and 1.0, that controls the amount of noise
that is added to the input image. Values that approach 1.0 allow for lots of
variations but will also produce images that are not semantically consistent
with the input. See the following example.</p>
<p><strong>Input</strong></p>
<p><img alt="sketch-in" src="../../assets/stable-samples/img2img/sketch-mountains-input.jpg" /></p>
<p><strong>Outputs</strong></p>
<p><img alt="out3" src="../../assets/stable-samples/img2img/mountains-3.png" />
<img alt="out2" src="../../assets/stable-samples/img2img/mountains-2.png" /></p>
<p>This procedure can, for example, also be used to upscale samples from the base
model.</p>
<h2 id="comments">Comments<a class="headerlink" href="#comments" title="Permanent link">#</a></h2>
<ul>
<li>
<p>Our codebase for the diffusion models builds heavily on
<a href="https://github.com/openai/guided-diffusion">OpenAI's ADM codebase</a> and
<a href="https://github.com/lucidrains/denoising-diffusion-pytorch">https://github.com/lucidrains/denoising-diffusion-pytorch</a>.
Thanks for open-sourcing!</p>
</li>
<li>
<p>The implementation of the transformer encoder is from
<a href="https://github.com/lucidrains/x-transformers">x-transformers</a> by
<a href="https://github.com/lucidrains?tab=repositories">lucidrains</a>.</p>
</li>
</ul>
<h2 id="bibtex">BibTeX<a class="headerlink" href="#bibtex" title="Permanent link">#</a></h2>
<div class="highlight"><pre><span></span><code><a id="__codelineno-7-1" name="__codelineno-7-1" href="#__codelineno-7-1"></a>@misc{rombach2021highresolution,
<a id="__codelineno-7-2" name="__codelineno-7-2" href="#__codelineno-7-2"></a> title={High-Resolution Image Synthesis with Latent Diffusion Models},
<a id="__codelineno-7-3" name="__codelineno-7-3" href="#__codelineno-7-3"></a> author={Robin Rombach and Andreas Blattmann and Dominik Lorenz and Patrick Esser and Björn Ommer},
<a id="__codelineno-7-4" name="__codelineno-7-4" href="#__codelineno-7-4"></a> year={2021},
<a id="__codelineno-7-5" name="__codelineno-7-5" href="#__codelineno-7-5"></a> eprint={2112.10752},
<a id="__codelineno-7-6" name="__codelineno-7-6" href="#__codelineno-7-6"></a> archivePrefix={arXiv},
<a id="__codelineno-7-7" name="__codelineno-7-7" href="#__codelineno-7-7"></a> primaryClass={cs.CV}
<a id="__codelineno-7-8" name="__codelineno-7-8" href="#__codelineno-7-8"></a>}
</code></pre></div>
<aside class="md-source-file">
<span class="md-source-file__fact">
<span class="md-icon" title="Last update">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M21 13.1c-.1 0-.3.1-.4.2l-1 1 2.1 2.1 1-1c.2-.2.2-.6 0-.8l-1.3-1.3c-.1-.1-.2-.2-.4-.2m-1.9 1.8-6.1 6V23h2.1l6.1-6.1-2.1-2M12.5 7v5.2l4 2.4-1 1L11 13V7h1.5M11 21.9c-5.1-.5-9-4.8-9-9.9C2 6.5 6.5 2 12 2c5.3 0 9.6 4.1 10 9.3-.3-.1-.6-.2-1-.2s-.7.1-1 .2C19.6 7.2 16.2 4 12 4c-4.4 0-8 3.6-8 8 0 4.1 3.1 7.5 7.1 7.9l-.1.2v1.8Z"/></svg>
</span>
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date">August 29, 2024</span>
</span>
<span class="md-source-file__fact">
<span class="md-icon" title="Created">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M14.47 15.08 11 13V7h1.5v5.25l3.08 1.83c-.41.28-.79.62-1.11 1m-1.39 4.84c-.36.05-.71.08-1.08.08-4.42 0-8-3.58-8-8s3.58-8 8-8 8 3.58 8 8c0 .37-.03.72-.08 1.08.69.1 1.33.32 1.92.64.1-.56.16-1.13.16-1.72 0-5.5-4.5-10-10-10S2 6.5 2 12s4.47 10 10 10c.59 0 1.16-.06 1.72-.16-.32-.59-.54-1.23-.64-1.92M18 15v3h-3v2h3v3h2v-3h3v-2h-3v-3h-2Z"/></svg>
</span>
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date">August 29, 2024</span>
</span>
</aside>
</article>
</div>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
<div class="md-copyright__highlight">
Copyright &copy; 2023 InvokeAI Team
</div>
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"base": "../..", "features": ["navigation.instant", "navigation.tabs", "navigation.tabs.sticky", "navigation.tracking", "navigation.indexes", "navigation.path", "search.highlight", "search.suggest", "toc.integrate"], "search": "../../assets/javascripts/workers/search.b8dbb3d2.min.js", "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}}</script>
<script src="../../assets/javascripts/bundle.af256bd8.min.js"></script>
<script src="https://unpkg.com/tablesort@5.3.0/dist/tablesort.min.js"></script>
<script src="../../javascripts/tablesort.js"></script>
<script src="../../javascript/init_kapa_widget.js"></script>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink