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
4d4d0ebd96
InvokeAI/help/FAQ/index.html

2746 lines
65 KiB
HTML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!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/help/FAQ/">
<link rel="prev" href="../gettingStartedWithAI/">
<link rel="next" href="../diffusion/">
<link rel="icon" href="../../img/favicon.ico">
<meta name="generator" content="mkdocs-1.6.0, mkdocs-material-9.5.33">
<title>FAQ - 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="#faq" 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">
FAQ
</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 md-tabs__item--active">
<a href="../gettingStartedWithAI/" class="md-tabs__link">
Help
</a>
</li>
<li class="md-tabs__item">
<a href="../../other/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="../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--active md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7" checked>
<label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="">
<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="true">
<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="../gettingStartedWithAI/" class="md-nav__link">
<span class="md-ellipsis">
New to InvokeAI?
</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">
FAQ
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
FAQ
</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="#how-to-install" class="md-nav__link">
<span class="md-ellipsis">
How to Install
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#downloading-models-and-using-existing-models" class="md-nav__link">
<span class="md-ellipsis">
Downloading models and using existing models
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#missing-models-after-updating-to-v4" class="md-nav__link">
<span class="md-ellipsis">
Missing models after updating to v4
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#slow-generation" class="md-nav__link">
<span class="md-ellipsis">
Slow generation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#shared-gpu-memory-windows" class="md-nav__link">
<span class="md-ellipsis">
Shared GPU Memory (Windows)
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#installer-cannot-find-python-windows" class="md-nav__link">
<span class="md-ellipsis">
Installer cannot find python (Windows)
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#triton-error-on-startup" class="md-nav__link">
<span class="md-ellipsis">
Triton error on startup
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#updated-to-340-and-xformers-cant-load-ccuda" class="md-nav__link">
<span class="md-ellipsis">
Updated to 3.4.0 and xformers can’t load C++/CUDA
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#install-failed-and-says-pip-is-out-of-date" class="md-nav__link">
<span class="md-ellipsis">
Install failed and says pip is out of date
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#replicate-image-found-online" class="md-nav__link">
<span class="md-ellipsis">
Replicate image found online
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#oserrors-on-windows-while-installing-dependencies" class="md-nav__link">
<span class="md-ellipsis">
OSErrors on Windows while installing dependencies
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#huggingface-install-failed-due-to-invalid-access-token" class="md-nav__link">
<span class="md-ellipsis">
HuggingFace install failed due to invalid access token
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#stable-diffusion-xl-generation-fails-after-trying-to-load-unet" class="md-nav__link">
<span class="md-ellipsis">
Stable Diffusion XL generation fails after trying to load UNet
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#package-dependency-conflicts-during-installation-or-update" class="md-nav__link">
<span class="md-ellipsis">
Package dependency conflicts during installation or update
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#invalid-configuration-file" class="md-nav__link">
<span class="md-ellipsis">
Invalid configuration file
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#modulenotfounderror-no-module-named-controlnet_aux" class="md-nav__link">
<span class="md-ellipsis">
ModuleNotFoundError: No module named 'controlnet_aux'
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#out-of-memory-issues" class="md-nav__link">
<span class="md-ellipsis">
Out of Memory Issues
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#memory-leak-linux" class="md-nav__link">
<span class="md-ellipsis">
Memory Leak (Linux)
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../diffusion/" class="md-nav__link">
<span class="md-ellipsis">
Diffusion Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../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--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_8" >
<label class="md-nav__link" for="__nav_8" id="__nav_8_label" tabindex="0">
<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="false">
<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="../../other/CONTRIBUTORS/" class="md-nav__link">
<span class="md-ellipsis">
Contributors
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../other/README-CompViz/" class="md-nav__link">
<span class="md-ellipsis">
CompViz-README
</span>
</a>
</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="faq">FAQ<a class="headerlink" href="#faq" title="Permanent link">#</a></h1>
<div class="admonition info">
<p class="admonition-title">How to Reinstall</p>
<p>Many issues can be resolved by re-installing the application. You won't lose any data by re-installing. We suggest downloading the <a href="https://github.com/invoke-ai/InvokeAI/releases/latest">latest release</a> and using it to re-install the application. Consult the <a href="../../installation/010_INSTALL_AUTOMATED/">installer guide</a> for more information.</p>
<p>When you run the installer, you'll have an option to select the version to install. If you aren't ready to upgrade, you choose the current version to fix a broken install.</p>
</div>
<p>If the troubleshooting steps on this page don't get you up and running, please either <a href="https://github.com/invoke-ai/InvokeAI/issues">create an issue</a> or hop on <a href="https://discord.gg/ZmtBAhwWhy">discord</a> for help.</p>
<h2 id="how-to-install">How to Install<a class="headerlink" href="#how-to-install" title="Permanent link">#</a></h2>
<p>You can download the latest installers <a href="https://github.com/invoke-ai/InvokeAI/releases">here</a>.</p>
<p>Note that any releases marked as <em>pre-release</em> are in a beta state. You may experience some issues, but we appreciate your help testing those! For stable/reliable installations, please install the <a href="https://github.com/invoke-ai/InvokeAI/releases/latest">latest release</a>.</p>
<h2 id="downloading-models-and-using-existing-models">Downloading models and using existing models<a class="headerlink" href="#downloading-models-and-using-existing-models" title="Permanent link">#</a></h2>
<p>The Model Manager tab in the UI provides a few ways to install models, including using your already-downloaded models. You'll see a popup directing you there on first startup. For more information, see the <a href="../../installation/050_INSTALLING_MODELS/">model install docs</a>.</p>
<h2 id="missing-models-after-updating-to-v4">Missing models after updating to v4<a class="headerlink" href="#missing-models-after-updating-to-v4" title="Permanent link">#</a></h2>
<p>If you find some models are missing after updating to v4, it's likely they weren't correctly registered before the update and didn't get picked up in the migration.</p>
<p>You can use the <code>Scan Folder</code> tab in the Model Manager UI to fix this. The models will either be in the old, now-unused <code>autoimport</code> folder, or your <code>models</code> folder.</p>
<ul>
<li>Find and copy your install's old <code>autoimport</code> folder path, install the main install folder.</li>
<li>Go to the Model Manager and click <code>Scan Folder</code>.</li>
<li>Paste the path and scan.</li>
<li>IMPORTANT: Uncheck <code>Inplace install</code>.</li>
<li>Click <code>Install All</code> to install all found models, or just install the models you want.</li>
</ul>
<p>Next, find and copy your install's <code>models</code> folder path (this could be your custom models folder path, or the <code>models</code> folder inside the main install folder).</p>
<p>Follow the same steps to scan and import the missing models.</p>
<h2 id="slow-generation">Slow generation<a class="headerlink" href="#slow-generation" title="Permanent link">#</a></h2>
<ul>
<li>Check the <a href="../../installation/INSTALL_REQUIREMENTS/">system requirements</a> to ensure that your system is capable of generating images.</li>
<li>Check the <code>ram</code> setting in <code>invokeai.yaml</code>. This setting tells Invoke how much of your system RAM can be used to cache models. Having this too high or too low can slow things down. That said, it's generally safest to not set this at all and instead let Invoke manage it.</li>
<li>Check the <code>vram</code> setting in <code>invokeai.yaml</code>. This setting tells Invoke how much of your GPU VRAM can be used to cache models. Counter-intuitively, if this setting is too high, Invoke will need to do a lot of shuffling of models as it juggles the VRAM cache and the currently-loaded model. The default value of 0.25 is generally works well for GPUs without 16GB or more VRAM. Even on a 24GB card, the default works well.</li>
<li>Check that your generations are happening on your GPU (if you have one). InvokeAI will log what is being used for generation upon startup. If your GPU isn't used, re-install to ensure the correct versions of torch get installed.</li>
<li>If you are on Windows, you may have exceeded your GPU's VRAM capacity and are using slower <a href="#shared-gpu-memory-windows">shared GPU memory</a>. There's a guide to opt out of this behaviour in the linked FAQ entry.</li>
</ul>
<h2 id="shared-gpu-memory-windows">Shared GPU Memory (Windows)<a class="headerlink" href="#shared-gpu-memory-windows" title="Permanent link">#</a></h2>
<div class="admonition tip">
<p class="admonition-title">Nvidia GPUs with driver 536.40</p>
<p>This only applies to current Nvidia cards with driver 536.40 or later, released in June 2023.</p>
</div>
<p>When the GPU doesn't have enough VRAM for a task, Windows is able to allocate some of its CPU RAM to the GPU. This is much slower than VRAM, but it does allow the system to generate when it otherwise might no have enough VRAM.</p>
<p>When shared GPU memory is used, generation slows down dramatically - but at least it doesn't crash.</p>
<p>If you'd like to opt out of this behavior and instead get an error when you exceed your GPU's VRAM, follow <a href="https://nvidia.custhelp.com/app/answers/detail/a_id/5490">this guide from Nvidia</a>.</p>
<p>Here's how to get the python path required in the linked guide:</p>
<ul>
<li>Run <code>invoke.bat</code>.</li>
<li>Select option 2 for developer console.</li>
<li>At least one python path will be printed. Copy the path that includes your invoke installation directory (typically the first).</li>
</ul>
<h2 id="installer-cannot-find-python-windows">Installer cannot find python (Windows)<a class="headerlink" href="#installer-cannot-find-python-windows" title="Permanent link">#</a></h2>
<p>Ensure that you checked <strong>Add python.exe to PATH</strong> when installing Python. This can be found at the bottom of the Python Installer window. If you already have Python installed, you can re-run the python installer, choose the Modify option and check the box.</p>
<h2 id="triton-error-on-startup">Triton error on startup<a class="headerlink" href="#triton-error-on-startup" title="Permanent link">#</a></h2>
<p>This can be safely ignored. InvokeAI doesn't use Triton, but if you are on Linux and wish to dismiss the error, you can install Triton.</p>
<h2 id="updated-to-340-and-xformers-cant-load-ccuda">Updated to 3.4.0 and xformers can’t load C++/CUDA<a class="headerlink" href="#updated-to-340-and-xformers-cant-load-ccuda" title="Permanent link">#</a></h2>
<p>An issue occurred with your PyTorch update. Follow these steps to fix :</p>
<ol>
<li>Launch your invoke.bat / invoke.sh and select the option to open the developer console</li>
<li>Run:<code>pip install ".[xformers]" --upgrade --force-reinstall --extra-index-url https://download.pytorch.org/whl/cu121</code></li>
<li>If you run into an error with <code>typing_extensions</code>, re-open the developer console and run: <code>pip install -U typing-extensions</code></li>
</ol>
<p>Note that v3.4.0 is an old, unsupported version. Please upgrade to the <a href="https://github.com/invoke-ai/InvokeAI/releases/latest">latest release</a>.</p>
<h2 id="install-failed-and-says-pip-is-out-of-date">Install failed and says <code>pip</code> is out of date<a class="headerlink" href="#install-failed-and-says-pip-is-out-of-date" title="Permanent link">#</a></h2>
<p>An out of date <code>pip</code> typically won't cause an installation to fail. The cause of the error can likely be found above the message that says <code>pip</code> is out of date.</p>
<p>If you saw that warning but the install went well, don't worry about it (but you can update <code>pip</code> afterwards if you'd like).</p>
<h2 id="replicate-image-found-online">Replicate image found online<a class="headerlink" href="#replicate-image-found-online" title="Permanent link">#</a></h2>
<p>Most example images with prompts that you'll find on the internet have been generated using different software, so you can't expect to get identical results. In order to reproduce an image, you need to replicate the exact settings and processing steps, including (but not limited to) the model, the positive and negative prompts, the seed, the sampler, the exact image size, any upscaling steps, etc.</p>
<h2 id="oserrors-on-windows-while-installing-dependencies">OSErrors on Windows while installing dependencies<a class="headerlink" href="#oserrors-on-windows-while-installing-dependencies" title="Permanent link">#</a></h2>
<p>During a zip file installation or an update, installation stops with an error like this:</p>
<p><img alt="broken-dependency-screenshot" src="../../assets/troubleshooting/broken-dependency.png" width="800px" /></p>
<p>To resolve this, re-install the application as described above.</p>
<h2 id="huggingface-install-failed-due-to-invalid-access-token">HuggingFace install failed due to invalid access token<a class="headerlink" href="#huggingface-install-failed-due-to-invalid-access-token" title="Permanent link">#</a></h2>
<p>Some HuggingFace models require you to authenticate using an <a href="https://huggingface.co/docs/hub/security-tokens#how-to-manage-user-access-tokens">access token</a>.</p>
<p>Invoke doesn't manage this token for you, but it's easy to set it up:</p>
<ul>
<li>Follow the instructions in the link above to create an access token. Copy it.</li>
<li>Run the launcher script.</li>
<li>Select option 2 (developer console).</li>
<li>Paste the following command:</li>
</ul>
<div class="highlight"><pre><span></span><code><a id="__codelineno-0-1" name="__codelineno-0-1" href="#__codelineno-0-1"></a>python<span class="w"> </span>-c<span class="w"> </span><span class="s2">&quot;import huggingface_hub; huggingface_hub.login()&quot;</span>
</code></pre></div>
<ul>
<li>Paste your access token when prompted and press Enter. You won't see anything when you paste it.</li>
<li>Type <code>n</code> if prompted about git credentials.</li>
</ul>
<p>If you get an error, try the command again - maybe the token didn't paste correctly.</p>
<p>Once your token is set, start Invoke and try downloading the model again. The installer will automatically use the access token.</p>
<p>If the install still fails, you may not have access to the model.</p>
<h2 id="stable-diffusion-xl-generation-fails-after-trying-to-load-unet">Stable Diffusion XL generation fails after trying to load UNet<a class="headerlink" href="#stable-diffusion-xl-generation-fails-after-trying-to-load-unet" title="Permanent link">#</a></h2>
<p>InvokeAI is working in other respects, but when trying to generate
images with Stable Diffusion XL you get a "Server Error". The text log
in the launch window contains this log line above several more lines of
error messages:</p>
<p><code>INFO --&gt; Loading model:D:\LONG\PATH\TO\MODEL, type sdxl:main:unet</code></p>
<p>This failure mode occurs when there is a network glitch during
downloading the very large SDXL model.</p>
<p>To address this, first go to the Model Manager and delete the
Stable-Diffusion-XL-base-1.X model. Then, click the HuggingFace tab,
paste the Repo ID stabilityai/stable-diffusion-xl-base-1.0 and install
the model.</p>
<h2 id="package-dependency-conflicts-during-installation-or-update">Package dependency conflicts during installation or update<a class="headerlink" href="#package-dependency-conflicts-during-installation-or-update" title="Permanent link">#</a></h2>
<p>If you have previously installed InvokeAI or another Stable Diffusion
package, the installer may occasionally pick up outdated libraries and
either the installer or <code>invoke</code> will fail with complaints about
library conflicts.</p>
<p>To resolve this, re-install the application as described above.</p>
<h2 id="invalid-configuration-file">Invalid configuration file<a class="headerlink" href="#invalid-configuration-file" title="Permanent link">#</a></h2>
<p>Everything seems to install ok, you get a <code>ValidationError</code> when starting up the app.</p>
<p>This is caused by an invalid setting in the <code>invokeai.yaml</code> configuration file. The error message should tell you what is wrong.</p>
<p>Check the <a href="../../features/CONFIGURATION/">configuration docs</a> for more detail about the settings and how to specify them.</p>
<h2 id="modulenotfounderror-no-module-named-controlnet_aux"><code>ModuleNotFoundError: No module named 'controlnet_aux'</code><a class="headerlink" href="#modulenotfounderror-no-module-named-controlnet_aux" title="Permanent link">#</a></h2>
<p><code>controlnet_aux</code> is a dependency of Invoke and appears to have been packaged or distributed strangely. Sometimes, it doesn't install correctly. This is outside our control.</p>
<p>If you encounter this error, the solution is to remove the package from the <code>pip</code> cache and re-run the Invoke installer so a fresh, working version of <code>controlnet_aux</code> can be downloaded and installed:</p>
<ul>
<li>Run the Invoke launcher</li>
<li>Choose the developer console option</li>
<li>Run this command: <code>pip cache remove controlnet_aux</code></li>
<li>Close the terminal window</li>
<li>Download and run the <a href="https://github.com/invoke-ai/InvokeAI/releases/latest">installer</a>, selecting your current install location</li>
</ul>
<h2 id="out-of-memory-issues">Out of Memory Issues<a class="headerlink" href="#out-of-memory-issues" title="Permanent link">#</a></h2>
<p>The models are large, VRAM is expensive, and you may find yourself
faced with Out of Memory errors when generating images. Here are some
tips to reduce the problem:</p>
<div class="admonition info">
<p class="admonition-title">Optimizing for GPU VRAM</p>
<div class="tabbed-set tabbed-alternate" data-tabs="1:3"><input checked="checked" id="__tabbed_1_1" name="__tabbed_1" type="radio" /><input id="__tabbed_1_2" name="__tabbed_1" type="radio" /><input id="__tabbed_1_3" name="__tabbed_1" type="radio" /><div class="tabbed-labels"><label for="__tabbed_1_1">4GB VRAM GPU</label><label for="__tabbed_1_2">6GB VRAM GPU</label><label for="__tabbed_1_3">12GB VRAM GPU</label></div>
<div class="tabbed-content">
<div class="tabbed-block">
<p>This should be adequate for 512x512 pixel images using Stable Diffusion 1.5
and derived models, provided that you do not use the NSFW checker. It won't be loaded unless you go into the UI settings and turn it on.</p>
<p>If you are on a CUDA-enabled GPU, we will automatically use xformers or torch-sdp to reduce VRAM requirements, though you can explicitly configure this. See the <a href="../../features/CONFIGURATION/">configuration docs</a>.</p>
</div>
<div class="tabbed-block">
<p>This is a border case. Using the SD 1.5 series you should be able to
generate images up to 640x640 with the NSFW checker enabled, and up to
1024x1024 with it disabled.</p>
<p>If you run into persistent memory issues there are a series of
environment variables that you can set before launching InvokeAI that
alter how the PyTorch machine learning library manages memory. See
<a href="https://pytorch.org/docs/stable/notes/cuda.html#memory-management">https://pytorch.org/docs/stable/notes/cuda.html#memory-management</a> for
a list of these tweaks.</p>
</div>
<div class="tabbed-block">
<p>This should be sufficient to generate larger images up to about 1280x1280.</p>
</div>
</div>
</div>
</div>
<h2 id="memory-leak-linux">Memory Leak (Linux)<a class="headerlink" href="#memory-leak-linux" title="Permanent link">#</a></h2>
<p>If you notice a memory leak, it could be caused to memory fragmentation as models are loaded and/or moved from CPU to GPU.</p>
<p>A workaround is to tune memory allocation with an environment variable:</p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-1-1" name="__codelineno-1-1" href="#__codelineno-1-1"></a><span class="c1"># Force blocks &gt;1MB to be allocated with `mmap` so that they are released to the system immediately when they are freed.</span>
<a id="__codelineno-1-2" name="__codelineno-1-2" href="#__codelineno-1-2"></a><span class="nv">MALLOC_MMAP_THRESHOLD_</span><span class="o">=</span><span class="m">1048576</span>
</code></pre></div>
<div class="admonition warning">
<p class="admonition-title">Speed vs Memory Tradeoff</p>
<p>Your generations may be slower overall when setting this environment variable.</p>
</div>
<div class="admonition info">
<p class="admonition-title">Possibly dependent on <code>libc</code> implementation</p>
<p>It's not known if this issue occurs with other <code>libc</code> implementations such as <code>musl</code>.</p>
<p>If you encounter this issue and your system uses a different implementation, please try this environment variable and let us know if it fixes the issue.</p>
</div>
<h3>Detailed Discussion</h3>
<p>Python (and PyTorch) relies on the memory allocator from the C Standard Library (<code>libc</code>). On linux, with the GNU C Standard Library implementation (<code>glibc</code>), our memory access patterns have been observed to cause severe memory fragmentation.</p>
<p>This fragmentation results in large amounts of memory that has been freed but can't be released back to the OS. Loading models from disk and moving them between CPU/CUDA seem to be the operations that contribute most to the fragmentation.</p>
<p>This memory fragmentation issue can result in OOM crashes during frequent model switching, even if <code>ram</code> (the max RAM cache size) is set to a reasonable value (e.g. a OOM crash with <code>ram=16</code> on a system with 32GB of RAM).</p>
<p>This problem may also exist on other OSes, and other <code>libc</code> implementations. But, at the time of writing, it has only been investigated on linux with <code>glibc</code>.</p>
<p>To better understand how the <code>glibc</code> memory allocator works, see these references:</p>
<ul>
<li>Basics: <a href="https://www.gnu.org/software/libc/manual/html_node/The-GNU-Allocator.html">https://www.gnu.org/software/libc/manual/html_node/The-GNU-Allocator.html</a></li>
<li>Details: <a href="https://sourceware.org/glibc/wiki/MallocInternals">https://sourceware.org/glibc/wiki/MallocInternals</a></li>
</ul>
<p>Note the differences between memory allocated as chunks in an arena vs. memory allocated with <code>mmap</code>. Under <code>glibc</code>'s default configuration, most model tensors get allocated as chunks in an arena making them vulnerable to the problem of fragmentation.</p>
<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