<h1 id="introduction">Introduction</h1>You keep seeing all these INCREDIBLE pictures with no descriptions, how do they do that?Enter img2img with Canny Controlnets. Transform ANY image with astounding accuracy.This guide assumes you are using AUTOMATIC1111.<h1 id="what-are-controlnets">What are Controlnets?</h1>Think of control nets like the guide strings on a puppet; they help decide where the puppet (or data) should move. There are several controlnets available for stable diffusion, but this guide is only focusing on the "canny" control net. The official page for canny is available <a target="_blank" rel="ugc" href="https://huggingface.co/lllyasviel/sd-controlnet-canny">here</a>.<h1 id="installing">Installing</h1><ol><li>Install the v1.1 controlnet extension here under the "extensions" tab -&gt; install from URL<ul><li><a target="_blank" rel="ugc" href="https://github.com/Mikubill/sd-webui-controlnet">https://github.com/Mikubill/sd-webui-controlnet</a></li><li>if you already have v1 controlnets installed, delete the folder from <code>stable-diffusion-webui/extensions/&lt;controlnet extension&gt;</code></li></ul></li><li>Download the <code>control_v11p_sd15_canny.pth</code> and <code>control_v11p_sd15_canny.yaml</code> files <a target="_blank" rel="ugc" href="https://huggingface.co/lllyasviel/ControlNet-v1-1/tree/main">here</a>.</li><li>place the files in <code>stable-diffusion-webui\models\ControlNet</code></li><li>Reload the UI. After reloading, you should see a section for "controlnets"</li></ol><h1 id="using-canny-with-img2img">Using Canny with Img2Img</h1><ol><li>Select the "img2img" tab in AUTOMATIC1111</li><li>Enter your prompt and negative prompt</li><li>Select sampler and number of steps</li><li>Put your source image in the img2img field (not the controlnet image field)<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/b3befcc4-d976-4262-bc5a-f2036672edfc/width=525/b3befcc4-d976-4262-bc5a-f2036672edfc.jpeg" /></li><li>Set width &amp; height to same size as input image</li><li>Controlnet settings<ol><li>Enable: Checked</li><li>Guess Mode: Checked (only for pre 1.1)<ul><li>if you are using version 1.1 ControlNet, use the "pixel perfect" checkbox to automatically set annotator resolution and canvas size</li></ul></li><li>Preprocessor: canny</li><li>Model: control_canny-fp16</li><li>annotator resolution: 768</li><li>canvas width/height: same as source image</li><li>high and low threshold: Default<ul><li>these affect how sensitive the annotator is to gradient changes. Usually the default settings are acceptable, but poor lighting may require additional fine tuning. Make changes in increments of 10 on a single slider at a time until you are satisfied with the wireframe.</li></ul></li><li>Higher denoising values will apply the prompt more strongly (only for pre 1.1)<ul><li>this has been simplified in 1.1 to buttons to emphasize Balanced/Prompt/Controlnet</li></ul></li></ol></li></ol><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/33a3d0b3-0eac-4858-9b30-7fb2cff2095c/width=525/33a3d0b3-0eac-4858-9b30-7fb2cff2095c.jpeg" /><ol><li>Generate!</li></ol><h1 id="how-does-this-work">How does this work?</h1>Canny draws outlines around the shapes in the input image. This is connected with the prompt with the controlnet to affect the final diffusion image.<h1 id="txt2img-usage">txt2img usage</h1>This technique works similarly in txt2img by putting the image in the controlnet area, but retains less of the original image in the final result. A comparison of the same prompt/seed/sampler/checkpoint in Img2Img or Text2Img is below:Img2Img:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/bb65842b-229a-4f60-99ec-31526125f3c7/width=525/bb65842b-229a-4f60-99ec-31526125f3c7.jpeg" />Text2Img:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/a133aed4-3316-41c6-9da8-97436d112b3d/width=525/a133aed4-3316-41c6-9da8-97436d112b3d.jpeg" /><h1 id="heading-105">Next Steps</h1>Learn how to use mov2mov to put everything together. Check out the guide <a target="_blank" rel="ugc" href="https://civitai.com/articles/84/ai-videos-in-mov2mov-with-stable-diffusion">here</a>!

df6ec679-e786-4f3c-9369-86eea7ab7250

Using img2img effectively with Canny Controlnets

sexual situations

physical violence

disturbing

male nudity

hanging

hate symbols

nazi party

revealing clothes

weapon violence

female swimwear or underwear

male swimwear or underwear

partial nudity

white supremacy

adult toys

graphic male nudity

illustrated explicit nudity

nudity

graphic violence or gore

graphic female nudity

pg-13

corpses

wide hips

convenient censoring

peeing

oral invitation

emaciated bodies

exposed female nipple

blowjob

female nudity

sexual activity

sexual intent

undressed

male underwear

female swimwear

genitals

female underwear

thick thighs

breasts out

strapless leotard

vore

breast out

one breast out

huge breasts

gigantic breasts

huge butt

covered nipples

hair over breasts

no panties

sitting on face

anal

dildo riding

downblouse

oral

porn

futanari

hentai

nude

lingerie

sexy

nsfw

suggestive

child on child

self injury

extremist

hate speech

diapers

urine

incest

scat

latex clothing

swimwear

bukkake

fellatio

cumshot

implied fellatio

eat_cum

cumdrip

cum in pussy

cum on face

after fellatio

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

triple fellatio

autofellatio

fucked silly

cum on pussy

pov fellatio