Use the new ToonCrafter custom-node to create an animation of your choice... You have UNTIL June 23th to participate! Info on the #Challenges Discord Channel. Prize: $50 PayPal Credit! 

ToonCrafter Workflow Challenge !!

liubai

作用，通过提示词控制眼睛、头发、嘴巴等生成进行眨眼说话的动画 用到的自定义节点：BrushNet：https://github.com/nullquant/ComfyUI-BrushNet?tab=readme-ov-fileSegmentAnything：https://github.com/frantic/comfyui_segment_anythingComfyUI-ToonCrafter：https://github.com/AIGODLIKE/ComfyUI-ToonCrafter 思路：通过seg分割出要改变的动画位置，比如眼睛、嘴巴等通过BrushNet实现对分割出的位置进行重绘通过ToonCrafter进行插帧生成动画 ComfySpace： <a href="https://t.zsxq.com/19H0cfM1O" target="_blank">https://t.zsxq.com/19H0cfM1O</a>

可控动画制作

markury

This is my entry for the ToonCrafter contest here on OpenArt. This is the workflow I started with in the video to loop between 3 keyframes using multiple ToonCrafter samplers. Follow along with my YouTube video to add virtually unlimited length to your ToonCrafter video workflows! Download the 4-image version of the workflow here: <a href="https://www.patreon.com/posts/comfyui-multi-105856838" target="_blank">https://www.patreon.com/posts/comfyui-multi-105856838</a> Check out the YouTube video for this workflow: <a href="https://youtu.be/-Fsl_BvfI18" target="_blank">https://youtu.be/-Fsl_BvfI18</a> <div data-w-e-type="video" data-w-e-is-void>
<video poster="https://media.discordapp.net/attachments/1151651773359075331/1249364169971470396/tooncrafter2.png?ex=6667088e&is=6665b70e&hm=bd0fafe0037d3a76045ba85a4e37de40a5c7a0e90419f81aa734ca3d6d4d1390&=&format=webp&quality=lossless&width=1100&height=618" controls="true" width="auto" height="auto"><source src="https://youtu.be/-Fsl_BvfI18" type="video/mp4"/></video>
</div>

Multi-Frame Interpolation with ToonCrafter

Saurabh Swami

<h1 style="text-indent: 2em; text-align: left;">Swamisaur's ToonKrafter Animation workflow </h1><h1 style="text-indent: 2em; text-align: left;">(GPU Optimised)</h1>All notes included in the file, beginner friendly workflow. Simply add the images and hit Run Upscaled exmple: (upscaeld with <a href="https://www.topazlabs.com/" target="_blank">Topaz</a>)<div data-w-e-type="video" data-w-e-is-void>
<video poster="" controls="true" width="auto" height="auto"><source src="https://cdn.openart.ai/wangeditor_uploads/0dylscskWFtRS8A9lmMt/raw/video_FYYmR_cI_1717866028514_raw.mp4" type="video/mp4"/></video>
</div> Workflow screenshot<img src="https://cdn.openart.ai/wangeditor_uploads/0dylscskWFtRS8A9lmMt/compressed/image_0Nab-bp7_1717866112247_512.webp" alt="" data-href="" style=""/> Reach out at @swamisaur on instagram for any queries or questions

A beginner friendly workflow with upto 6 images as input. (GPU Optimised)

Can you make a workflow that creates a creative logo animation? You have UNTIL May 12th to participate! Info on the #Challenges Discord Channel. Prize: $50 PayPal Credit! 

Creative-Logo animations.

wang vince

You can use the animatelcm workflow or the V3 version of animatediff. If you want to achieve the best transition effect, Lora in the workflow must be used

img2vid_Generate transition videos between images with such silky texture

Taras

Animated Logo generation based on logo text, prompt and 4 reference images.

Animated logo generation

Dseditor

1. Enter your logo name in text2. Prepare two pictures (Style1, Style2) for style transfer. You can use Style transfer or Strong Style Transfer, whichever effect you like.3. In Weights Strategy, adjust the special effects you want according to the picture content.4. This workflow uses <a href="https://huggingface.co/ByteDance/AnimateDiff-Lightning/blob/main/animatediff_lightning_8step_comfyui.safetensors" target="_blank">Animatediff Lighting 8Step</a> as the Animatediff model, and uses QRCode Monster, referring to the last picture as QR, to continuously play back the effect of head and tail echoes.==Update : It may be better to keep the logo in LineArt and change it to the LineArt version. If you like the QRMonster version, you can also download the previous one.To keep details in your logo(word in Chinese/Japanese or other type), you'll have the amazing effects when change the first SDXL lineart controlnet to <a href="https://huggingface.co/TheMistoAI/MistoLine/blob/main/mistoLine_rank256.safetensors" target="_blank">mistoline controlnet</a>.

Style Logo Animation

Dominic Richer

Usin Two image and a Short description or each image, I manage to Morph one image to another using IP Adapter and Weigth Control. Drop two other try using the same Flow... The flow can do much more then Logo animation, and you can trick it to add more image. V2. Add Text Option HOW TO Add your two image in the Input Square, Chose Your ModelIn the first green rectangle : add the pos prompt you want to be evrywere (Quality Prompt)on 1 line do a description of the firsrt imageon the second line, do the same but of the second imageQ See the result If you want to add more image, just link a third, fourth image, and add a description on each line.. be aware that the transition beetween the middle image will be fast.. almost inexistant.

Logo Animation

Can you make a workflow that changes the weather in images? ... You have UNTIL April 28th to participate! Info on the #Challenges Discord Channel. Prize: $50 PayPal Credit! 

Weather Changes

M.D. Programming

Simple and neat weather changer using CLIP Interrogator and a simple Canny ControlNet while staying true to the original composition. I've included 4 different weather conditions in the workflow for test, connect the desired positive prompt and its corresponding negative prompt. You can add more weather conditions, just write a simple prompt with simple keywords and set their weights to 1.3.And also add a few keywords to the negative prompt.

Weather Changer XL (Weekly Challenge)

2 Simple Step, Load the picture you want to changeLoad it again, and mask the backgroundQ You should have 4 wather change

Temperature Changer

VoLLi

Just thrown together as a quick idea. It kinda works and only uses a few nodes.

Quick and dirty weather change. IP Adapter + Control Net

Alessandro Russo

What does it do?This workflow was designed for the "Weather Changing" challenge. It involves uploading an image and describing the desired situation in the dedicated box.For example, typing "Heavy snow" will result in an image depicting heavy snowfall, while typing "lightning storm" will display a powerful thunderstorm. Similarly, entering "sandstorm" will transform the image into a location filled with sand both on the ground and in the air. A unique feature of this workflow is its flexibility: in addition to the predefined weather options required by the challenge, you can input any word to modify the image's situation.For instance, typing "flood" will portray the location in the photo as flooded, adding a dramatic and realistic element to the scene. How does he do it?This process is made possible by using the "<a href="https://huggingface.co/timbrooks/instruct-pix2pix/blob/main/instruct-pix2pix-00-22000.safetensors" target="_blank">instruct pix2pix</a>" checkpoint. To make this checkpoint work on Comfyui, a method combining Controlnet and the new Ipadapter was necessary. The checkpoint is activated through positive requests, specifying the desired change.For example, you can request to change the hair color of a person or add scenic elements to the photo. Additionally, I've used LLM to describe the scene and create the prompt needed to generate a high-resolution image, also leveraging Ultimate SD Upscale to highlight details. Research and InformationFor further insights into using "instruct pix2pix," you can search for information on YouTube or Google. Or go directly to Stable Diffusion's official website at this address: <a href="https://stable-diffusion-art.com/instruct-pix2pix/" target="_blank">https://stable-diffusion-art.com/instruct-pix2pix/</a>the model I used is the older model, but doing a search afterwards I found a newer model, which you can find at <a href="https://civitai.com/models/105817?modelVersionId=116613" target="_blank">CivitAI</a> I tested the most updated model, found on CivitAI, it is lighter, only 2Gb compared to the 7Gb of the old model, I put here some images generated with this model. <img src="https://cdn.openart.ai/wangeditor_uploads/GKn05KJv67VZshfruiy0/compressed/image_EAgxQ7zJ_1713783505891_512.webp" alt="" data-href="" style="">The word "Ligthning Storm" was used. <img src="https://cdn.openart.ai/wangeditor_uploads/GKn05KJv67VZshfruiy0/compressed/image_ZSCZC431_1713785977118_512.webp" alt="" data-href="" style="">The word "flood" was used. In conclusion, this workflow offers a fun and flexible way to modify images according to personal preferences, including simulating natural phenomena such as floods. below some extra challenge imagesgenerated with old model<img src="https://cdn.openart.ai/wangeditor_uploads/GKn05KJv67VZshfruiy0/compressed/image_DaglxDIk_1713771166204_512.webp" alt="" data-href="" style="">The word "Flood" was used. <img src="https://cdn.openart.ai/wangeditor_uploads/GKn05KJv67VZshfruiy0/compressed/image_N4HNGs-v_1713771148937_512.webp" alt="" data-href="" style="">The word "Autumnal" was used. <img src="https://cdn.openart.ai/wangeditor_uploads/GKn05KJv67VZshfruiy0/compressed/image_vaDjWYrb_1713771260570_512.webp" alt="" data-href="" style="">The word "Christmas" was used.

Weather Flex Converter

Aderek

Change weather in the photo is not that easy (without destroy oryginal image). This is my version of solution this problem ;) Of course great thanks to &nbsp;<a href="https://github.com/cubiq/ComfyUI_IPAdapter_plus?tab=readme-ov-file" target="_blank">https://github.com/cubiq/ComfyUI_IPAdapter_plus?tab=readme-ov-file</a> &nbsp;(you need do it, if you want to run my WF).<img src="https://cdn.openart.ai/wangeditor_uploads/duzl5tMWa23D5zUP30PB/compressed/image_zQmpszAF_1713389006094_512.webp" alt="" data-href="" style=""/>You can play with<img src="https://cdn.openart.ai/wangeditor_uploads/duzl5tMWa23D5zUP30PB/compressed/image_OcGyMoGr_1713389354332_512.webp" alt="" data-href="" style=""/>or PLUS VIT H.If you dowload all, you should see:<img src="https://cdn.openart.ai/wangeditor_uploads/duzl5tMWa23D5zUP30PB/compressed/image_uye9GnFF_1713389401902_512.webp" alt="" data-href="" style=""/>1. Choose image with weather.<img src="https://cdn.openart.ai/wangeditor_uploads/duzl5tMWa23D5zUP30PB/compressed/image_UzdIQV9k_1713389061483_512.webp" alt="" data-href="" style=""/>2. Select your image.<img src="https://cdn.openart.ai/wangeditor_uploads/duzl5tMWa23D5zUP30PB/compressed/image_pOLc6FEP_1713389077838_512.webp" alt="" data-href="" style=""/>3. Set good prompt ;)<img src="https://cdn.openart.ai/wangeditor_uploads/duzl5tMWa23D5zUP30PB/compressed/image_IV4bnjPW_1713389092691_512.webp" alt="" data-href="" style=""/> <a href="https://ko-fi.com/aderek514" target="_blank">Support Paweł Tomczuk on Ko-fi! ❤️. </a><a href="http://ko-fi.com/aderek514" target="_blank">ko-fi.com/aderek514</a><a href="https://ko-fi.com/aderek514" target="_blank"> - Ko-fi ❤️ Where creators get support from fans through donations, memberships, shop sales and more! The original 'Buy Me a Coffee' Page.</a> Visit my DeviantArt page: <a href="https://www.deviantart.com/aderek" target="_blank">Aderek - Hobbyist, Digital Artist | DeviantArt</a>

Change weather on photo with IPAdapter Plus

This workflow uses Controlnet ip2p to generate weather changes. It's very traditional but simple and easy to use.You can find the model by searching for "p2p" in install models of ComfyUI Manager. After installing it, select your favorite SD1.5 model from Civitai, and then use this workflow to change the weather in the picture.The latest version using BNKTiled+SUPIR has been updated, which can have more kinds of graphic details. If you want a result closer to the original image, you can replace the Tiled Ksampler with a normal Ksampler.There are several kinds of weather that will change randomly in the workflow. If you only want one kind, you can also keep only the weather you want and generate images.

RandomWeatherChanger

Aki Hung Ác

This is a large workflow, so I only use CCSR Upscaler to increase the quality of the input image, you can remove if you already use a good quality input image.Checkpoint: https://civitai.com/models/43977/leosams-helloworld-xl ---------------------------Discord: &nbsp;<a href="https://discordapp.com/users/339415040308412418" target="_blank">https://discordapp.com/users/339415040308412418</a> Any support is appreciated, thank you very much :)patreon.com/akihungachttps://buymeacoffee.com/akihungac<a href="https://www.paypal.com/paypalme/manhtuanphoto" target="_blank">https://www.paypal.com/paypalme/manhtuanphoto</a>

Weather change (AFTERRAIN | THUNDERSTORM | ICE AGE | SAND STORM)

Can you make a workflow that Upscales images wihout quality loss and 're-imagined'  details and artifacts ? ... You have UNTIL April 8th to participate! Info on the #Challenges Discord Channel. Prize: $50 PayPal Credit! 

Upscaling Challenge 

Vinod Maskeri

This simple 4x upscaler enlarges the image while keeping the original detail of the image intact,

Classic SD Upscaler 

Michael Knight

This workflow is not meant to be fast, but aim for a VERY HIGH quality output. It outperform anything I know about upscale. Better than Topaz. Better than Magnific. But it have a down side, it is heavy on hardware when using the full workflow with large output size. 👉What it do:It upscale a poor image into something mind-blowing while conserving integrity of the picture. 👉How it work:The workflow look very big at first but is very simple to use. You can start by checking if you have all models in the workflow and can by tested directly. If you have problem, you can try to activate 1 group node at the time and see how it goes before going to next step.1- We crop the image at a SDXL most closest size. This is done with my custom nodes attached in files. Copy FRED_AutoCropImage_SDXL_Ratio.py inside your \ComfyUI\custom_nodes.2- We first upscale the image and clean it before it reach SUPIR. This is very important as SUPIR work best with a clean image, and simple upscale with model or upscale by node doesn't work well all the time. To do that, I use a CCSR upscale method. That upscale the image and keep it integrity and clean it. This mostly work good for noisy picture, with lots of artifacts, but is very hardware dependant and take sometime to load model for the first run.3- If the CCSR upscale didn't worked to clean the picture, we can use StableSR group. Usually not necessary.4- When the image is enough big (around 2x a SDXL standard), SUPIR will do it's magic. Adding skin texture and imperfections, adding detail to a landscape. It have its flaw, like adding hair where there isn't. To work around, we lower the CFGs but the common settings I finely found work very good.5- Don't worry if there was too much skin imperfections as they will be finetune in ultimateSDupscale. I do another 2x here and using realvisXL30Turbo with the upscaler 4xNMKD-Superscale0SP_178000_G it add skin detail at a micro level.6- Saving the picture in 2 different format, 1 with only a watermark at the bottom, and 1 with a compare of the original with automatic text placement. There is also a BEEP sound when the process end.👉Where it work the best:This workflow work so good for portrait image of humain on image around 512x512. So old SD1.5 image here we are for the upscale.It work great on other pictures too, some tweeking maybe required.👉More infos in workflow.This workflow contains around 250 nodes but you can all find them in comfyui_manager except for my custom node that is attached in a zip file. Put it in folder mentionned earlier. You need numpy, cv2, PIL and Torch to run, but most of you will all have that already. If not, then do a pip install numpy, and the other one.It also take a lot of ressouces but the result is worth it. For a normal upscale, it take around 8min/image upscaled on my RTX4090.🔥Help me improving this workflow. If you find a better way to parse data or a better model, please share.🔥Most install problem is not due to the workflow by itself but missing dependency or missing custom nodes or models. Be sur you're all set before posting a bug in the comments.PaintShop was used ONLY to convert image to jpg as the result is around 33mb. No modification was done within that tool.I hope you gonna have fun as much as I have to upscale pictures using this workflow.

Auto Crop -> CCSR -> SUPIR -> UltimateSDupscale -> High quality upscale

L10n.H34r7

📷​SUPIR v2 Photo Upscale📷​ -🔥SUPIR Photo Upscaler🔥- SUPIR ⚡ Copax TimeLessXL Version V11-lightning- Bonus : Upscale by model compare Nodes Info : - https://github.com/kijai/ComfyUI-SUPIR- https://github.com/kijai/ComfyUI-KJNodes- https://github.com/rgthree/rgthree-comfy- https://github.com/pythongosssss/ComfyUI-Custom-Scripts- https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes- https://github.com/ssitu/ComfyUI_UltimateSDUpscale - Find my other worflow there : https://openart.ai/workflows/profile/l10n_h34r7 👉If you liked it please leave a review and a ❤️​👉Enjoy and Have Fun ! 😎

📷​SUPIR Photo Upscale📷​ (Contest entry)

a Fast 4X and 8X uspacler.. It just take the image, past it in 30 little upscale to get a 4X uspacle (Not exact 4X, like 4.32) And passing thru another 15 to get a 8X ish upscale (Exactly 8.98X) Little step to get to the final step :)

4x and 8x Photo upscale 

I love make very easy, clear and fast WF. Enjoy! <img src="https://cdn.openart.ai/wangeditor_uploads/duzl5tMWa23D5zUP30PB/compressed/image_hDuy2-pH_1711561109662_512.webp" alt="" data-href="" style=""/> <img src="https://cdn.openart.ai/wangeditor_uploads/duzl5tMWa23D5zUP30PB/compressed/image_YiqgSLqh_1711561140431_512.webp" alt="" data-href="" style=""/> <img src="https://cdn.openart.ai/wangeditor_uploads/duzl5tMWa23D5zUP30PB/compressed/image_UOcOZdVZ_1711561170636_512.webp" alt="" data-href="" style=""/>

Ultra fast real photo upscaler x4

#NeuraLunk

More info will be added soon ;)NOT usable on human subjects !#NeuraLunk &nbsp;

Real Photo Upscaler 4x

akihungac

SUPIR upscaler is the highest quality, but it is very slow, requires high hardware/configuration and has a few exceptions that cause the image to be blurry than the original (like the gem image). So I added the 4x/16x quick upscaler option with high speed, which doesn't require much vram. I have carefully selected Upscale Models, download them at: https://openmodeldb.info/-4xLSDIRplusC.pth-16x-ESRGAN.pth-1x_Plants_400000_G.pth ---------------------------Discord: &nbsp;<a href="https://discordapp.com/users/339415040308412418" target="_blank">https://discordapp.com/users/339415040308412418</a> Any support is appreciated, thank you very much :)patreon.com/akihungacbuymeacoffee.com/akihungacpaypalme/manhtuanphoto

Hybrid Upscaler Workflow 

Can you make a workflow that generates a Product presentation Animation... You have UNTIL March 25th to participate! Info on the #Challenges Discord Channel. Prize: $50 PayPal Credit! 

Product presentation Animation.

diSty

Re-uploaded for Product Presentation entry This workflow meant to generate some kind of cool splash screen animations/morphs. Quick installation video tutorial:https://youtu.be/sqHG7w60Gh0

Splash - Guided Motion - Product Presentation

<img src="https://cdn.openart.ai/wangeditor_uploads/duzl5tMWa23D5zUP30PB/compressed/image_WKWO_YKg_1711217024549_512.webp" alt="" data-href="" style=""/>Workflow creates a simple video of a hand pointing at an advertising product.You dont need Top GPU, you dont need Model. Only one video and image ;)You need to upload the attached video of the hand. The script removes the background from it, then applies it to the product image. It finally adds the text "You need this!"<img src="https://cdn.openart.ai/wangeditor_uploads/duzl5tMWa23D5zUP30PB/compressed/image_2OAmHdwz_1711217583365_512.webp" alt="" data-href="" style=""/><img src="https://cdn.openart.ai/wangeditor_uploads/duzl5tMWa23D5zUP30PB/compressed/image_hTfAGHra_1711217621182_512.webp" alt="" data-href="" style=""/>

You need this! Simple Product Presentation :)

Using Multiple of Flow and Method to product a Produce Presentation Animation I am not use with one of the 2 concept i did are the best.. il choose the first one i Upload if I have to chose one, but both are good. Note : Made with a 6Vram Computer

Product Presentation (All in One Flow)

Can you make a workflow that generates a Pet portrait illustration from a photo.. You have UNTIL SUNDAY NEXT WEEK to participate! 
Info on the #Challenges Discord Channel. Prize: $50 PayPal Credit! 

Artistic Pet Portraits - CLOSED

pfloyd

Pet portrait using &nbsp;ip-adapter-faceid-portrait<table style="width: 100%;"><tbody><tr style="text-align: left;"></tr></tbody></table>

ipetAdapter

A very simple workflow using the Layer Diffusion model that changes the background.Enter the type of pet in the prompt word, such as cat or dog, and the place you want to teleport to, such as an office full of fruits.The pet will be transported from the original photo to the scene you describe.Note: Because this workflow only uses the Layer Diffusion prompt word method to obtain the subject image, sometimes the subject won’t be found, and can't be used for people portraits (portraits of people will get poor image quality).Pictures of pets or items require a definite description in the prompt word.(03/11)Update for using new layerdiffusion nodes

LayerDiffusion Pet Teleport

Abdallah Alswaiti

<div data-w-e-type="video" data-w-e-is-void>
<video poster="" controls="true" width="auto" height="auto"><source src="https://cdn.openart.ai/wangeditor_uploads/c5qLphZHmzChYXmpmmV7/raw/video_Xei50eBa_1709728030348_raw.mp4" type="video/mp4"/></video>
</div>to have excellent result try my latest model <a href="https://civitai.com/models/130664/davinci" target="_blank">https://civitai.com/models/130664/davinci</a>

Stylish your Pet

Just put a photo, Chose the Style and Go, work on almost every picture, some style a better then other

Change Style

Abhay singh

Pet styler

I invite you to have fun in creating portraits of your beloved pets in an unusual painting style ;) Mention Gotye and Kimbra :)Just upload photo, set name and click ;) <a href="https://civitai.com/articles/3955/gotye-with-kimbra-with-outline-xl" target="_blank">Gotye with Kimbra with Outline XL | Civitai</a>Have fun!Use with this: <a href="https://civitai.com/models/237678?modelVersionId=274367" target="_blank">Aderek SDXL - v1.5 DPO | Stable Diffusion Checkpoint | Civitai</a> <a href="https://ko-fi.com/aderek514" target="_blank">Support Paweł Tomczuk on Ko-fi! ❤️. </a><a href="http://ko-fi.com/aderek514" target="_blank">ko-fi.com/aderek514</a><a href="https://ko-fi.com/aderek514" target="_blank"> - Ko-fi ❤️ Where creators get support from fans through donations, memberships, shop sales and more! The original 'Buy Me a Coffee' Page.</a> Visit my DeviantArt page: <a href="https://www.deviantart.com/aderek" target="_blank">Aderek - Hobbyist, Digital Artist | DeviantArt</a>

Pets in Gotye-feat-Kimbra-Somebody style

Use prompt styler to choose art style you want. ---------------------------Discord: &nbsp;<a href="https://discordapp.com/users/339415040308412418" target="_blank">https://discordapp.com/users/339415040308412418</a> Any support is appreciated, thank you very much :)patreon.com/akihungacbuymeacoffee.com/akihungacpaypalme/manhtuanphoto

Artistic Pet Portraits

Can you make a workflow that generates consistent characters in different poses? You have UNTIL SUNDAY to participate ! 
Info on the #Challenges Discord Channel. WIN an Amazon Gift-Card! 

Full Character Consistancy! - CLOSED

My attempt at Full Character Consistancy...Although 100% consistency may be almost impossible to achieve with SD (yet).A work in progress ;) I generated 4 portrait faces with another basic workflow.These are then all fed into IPAdapter FaceID plus v2 SDXL.(See resource download links on the right of this page)To Keep the same Character in different poses consistant,you need to keep the seed and prompt fixed when you have found a good prompt with good results.Then you can change the character's pose with an image and the OpenPose controlnet... (I will add this soon)... #NeuraLunk

An attempt at Full-Character Consistancy. (Using SDXL model with Lightning 8-step lora)

It's not easy to create several photos with the same character... This version works with SDXL models (recommended &nbsp;<a href="https://civitai.com/models/237678?modelVersionId=351046" target="_blank">https://civitai.com/models/237678?modelVersionId=351046</a> ) on an RTX 3060ti GPU or better. At the beginning, you upload a startup image (size about 1024x1024) and enter the path to a folder with six images, from which the system will load poses. The system will then create six images and proceed to try to apply identical outfits to the character. The better models you have access to detect items of clothing, the better the effect will be. This set only creates images in the basic form, i.e. if you want to get better results, you need to add e.g. a face detailer. Have fun with this PE. Financial support welcome ;) <a href="https://ko-fi.com/aderek514" target="_blank">Support Paweł Tomczuk on Ko-fi! ❤️. </a><a href="http://ko-fi.com/aderek514" target="_blank">ko-fi.com/aderek514</a><a href="https://ko-fi.com/aderek514" target="_blank"> - Ko-fi ❤️ Where creators get support from fans through donations, memberships, shop sales and more! The original 'Buy Me a Coffee' Page.</a> Visit my DeviantArt page: <a href="https://www.deviantart.com/aderek" target="_blank">Aderek - Hobbyist, Digital Artist | DeviantArt</a>

IP Adapter Character Consistancy, part II

aigc101

This is a instant id workflow, I put controlnet, ipadapter, visualised prompt in. Thank you matt3o, you can find all models you need in :<a href="https://github.com/cubiq/ComfyUI_InstantID/tree/main" target="_blank">https://github.com/cubiq/ComfyUI_InstantID/tree/main</a> Have fun!

instantid-ult

Lord Lethris

<h2>What this workflow does</h2> This workflow will create a number of Character Concept Images that you can then save off and use in your own workflows. This workflow also includes an example of how you can use and maintain some form of Consistency of your character. &nbsp;Costumes will never be 100% as AI will always have creative freedom, but it's as close as I can get it. <h2>How to use this workflow</h2> This workflow requires <a href="https://github.com/comfyanonymous/ComfyUI/tree/8dc19e40d129c8ee049be7be2657458509717ba5" target="_blank">ComfyUI Revision: 2144 [8dc19e40]</a> or higher as it makes use of the Grouping feature to minimise the "Mess". 🟪 ComfyUI IPAdapter plus FaceID 2 Setup 🟪 This workflow makes use of the new FaceID 2 Models from ComfyUI IPAdapter plus - which can be found here → <a href="https://github.com/cubiq/ComfyUI_IPAdapter_plus" target="_blank">https://github.com/cubiq/ComfyUI_IPAdapter_plus</a> ← and may need setting up in a handful of Nodes 🟦 Other Settings 🟦 All other custom configuration is in 🟦 Blue 🟦.Most of these are self explanatory, especially if you are ComfyUI Savvy.However I do recommend the following settings (I've highlighted with a 🟡) as this is what the workflow was optimised using: 🟡 BBOX / SEGM - Face Models: &nbsp; &nbsp; Model_Name &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;= face_yolov8n_v2.pt &nbsp; &nbsp; SEGM Face Model = face_yolov8n_seg2_60.pt 🟡 SAM &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; = sam_vit_h_4b8939pth🟡 Face Restore Model &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;= codeformer.pth or RestoreFormer.pth🟡 Load InsightFace &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;= CPU preferred, but whatever 😉🟡 IP-Adapter Encoder (Clip Vision) = IP_Adapter_Encoder_SD.safetensors🟡 IPAdapter Plus Model &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; = ip-adapter_sd15.bin 🟡 IP-Adapter Face Plus v2 Model &nbsp; &nbsp; &nbsp;Preset &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; = FACEID PLUS V2 &nbsp; &nbsp; &nbsp;lora_Strength = 0.80 -&gt; 0.90 &nbsp; &nbsp; &nbsp;Provider &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;= CPU preferred, but whatever floats Your Boat 😉 There are a few switches laying about (I've highlighted with a ⚪) that you can use to switch between random content and your own prompt, and a style switch that helps define reality from Anime.The Concept Art Face Fixer Node will take a while - this step helps improve the facial Consistency of the character.I have added Clothing Tweaks. &nbsp;The Default Settings should be good, but feel free to play around with this. 🟪 DEBUG Switch 🟪 Debugging Switch - Set This to "2", and then "Right click -&gt; Bypass" on Both Upscale Quality Fix and Concept Art Face Fixer - To speed up workflow but compromise quality. 🟫 Concept Art Pose 🟫 Here you need to load the Open Pose imageYou can download this from the Resource section on the left. <img src="https://cdn.openart.ai/wangeditor_uploads/MFnwda4rIljJ8vgEAFMu/compressed/image_0t5GW8rD_1708637287686_512.webp" alt="" data-href="" style=""/> <h2>Tips about this workflow</h2> Try to keep custom prompts to a minimum, as the workflow will add extra "stuff" to the prompts for optimal Character creation. I have found this workflow to work really well in Anime mode switched on, and with Complementary Anime based Checkpoints and with a "CLIP Skip" of -2 and "steps" of about 15-20. <img src="https://cdn.openart.ai/wangeditor_uploads/MFnwda4rIljJ8vgEAFMu/compressed/image_7OX5TXFh_1708642708250_512.webp" alt="" data-href="" style=""/> I will, at some point, create a companion workflow to work along side this one, and possibly create a lite version of this workflow, with just the Concept Character Creator portion. <h2>Version Changes</h2> v1.6<ul><li>Rebuilt IP Adapter Processes due to update</li><li>Removed Re-Actor Nodes as they are now redundant due to quality of IP Adapter Nodes</li><li>Added access to DEBUG Switch (It was hidden in previous versions, but I thought it maybe useful to you lot)</li><li>Removed Fix Seed node - it wasn't working right. &nbsp;You can use the debugger now anyway.</li></ul> v1.5<ul><li>Adjusted IP Adapter for Clothing</li><li>Added Green Chroma Key ( works better 90% of the time - May bleed into clothes - I'll remove if big issue)</li><li>Added Manual Clothing Influence Tweakers</li><li>Adjusted Woman / Man influence in random Character Generator (it was heavily focused on Girl/Woman)</li></ul> v1.4<ul><li>Added over 2000 Character Generations (Credit to <a href="https://civitai.com/user/Atryda" target="_blank">Atryda</a>)</li><li>Fixed issue where Random Prompt Wasn't being "Random".</li><li>Added a more intrusive Face Fix Node, as I though the old one was a little blurry.</li></ul> v1.3<ul><li>Fixed yet Another issue with Character Concept Build Node. &nbsp;This should be it..!</li></ul> v1.2<ul><li>Fixed Another issue with Character Concept Build Node - Basically Rebuilt it.</li></ul> v1.2<ul><li>Fixed issue with Character Concept Build Node</li></ul> v1.0<ul><li>Launch Version</li></ul>

Random Character Concept Creator With Image Consistency Examples V1.6

I made a workflow to be able to do consistent character in different scene, including action pose. Using IP Adapter, i could manage to have a good consistent to the character. It's far from being perfect, but it closed enough. Some Time you have to cheat it, and use you own pose reference image, sometime you have to play a little with the mask, cause IP doesn't understand it well with interaction.. but somehow, it still work very well :) Devlopper note : You better use Green Background for character ref. It work better.. all the token IP adaptor will read will be your character and maybe 1 or 2 token &nbsp;for the green background. Green is better then white in my experience. you have to have a simple promt to help the workflow.. ex for the male character the prompt is : 1 bald man with brown apron.. for 2 character it will be : 1 Bald man with brown apron and 1 blond girl with blue dress. CLOUD SETUP There is some model you will have to change to make it work, fallow the line, when it block, just try out some model were it bug... for SD1.5 use Model.psytorch for clipmodel, FacePlus V2 for Face, IP Plus for the model for BG and Character extraction. Future plan : I plan to add more character to the scene, I don t know what is the limit..Note : Your pose picture will guide the latent image to produce your image, so use 512x512 pose picture, or the size you want the result. V3 Update all the flow, but it does the same thing.. 1 Character, 2 Character or 3 Character (Din t test the 3 character) Think are more automaticFaster..

Consistant Character Maker (Comics Strip) V3

DESRYOO

This is a face changing attempt based on <a href="https://huggingface.co/ByteDance/SDXL-Lightning/blob/main/sdxl_lightning_4step_lora.pth" target="" style="text-align: left;">sdxl_lightning_4step_lora、InstantID and IPA.</a>I think a rating below 0.4 would preserve good Facial features, but this requires some manual experimentation.I hope you can gain new inspiration from it. <a href="https://huggingface.co/ByteDance/SDXL-Lightning/blob/main/sdxl_lightning_4step_lora.pth" target="" style="text-align: left;">sdxl_lightning_4step_lora:</a> <a href="https://huggingface.co/ByteDance/SDXL-Lightning/tree/main" target="_blank" style="text-align: start;">https://huggingface.co/ByteDance/SDXL-Lightning/tree/main</a>Instantid Node: <a href="https://github.com/cubiq/ComfyUI_InstantID" target="_blank" style="text-align: start;">https://github.com/cubiq/ComfyUI_InstantID</a>Instantid Model: <a href="https://huggingface.co/InstantX/InstantID/resolve/main/ip-adapter.bin?download=true" target="_blank">https://huggingface.co/InstantX/InstantID/resolve/main/ip-adapter.bin?download=true</a><a href="https://github.com/cubiq/ComfyUI_FaceAnalysis" target="_blank" style="text-align: start;">FaceAnalysis</a> node: <a href="https://github.com/cubiq/ComfyUI_FaceAnalysis" target="_blank" style="text-align: start;">https://github.com/cubiq/ComfyUI_FaceAnalysis</a> <img src="https://cdn.openart.ai/wangeditor_uploads/od7M2Ed2nXLWaSte4WXw/compressed/image_PGZTfszN_1708614439090_512.webp" alt="" data-href="" style="">

Test For Fast Stylized Faceswap

This is a workflow for change character &nbsp;pose and youyou can adjust change in cloth happen or not by increasing or decreasing ipadapter weight

OpenArt

Workflows

Challenges

Active Sessions

Workflow Challenges

.css-14dnqna{margin:0;font-weight:400;line-height:1.5;font-size:1rem;font-family:Inter,sans-serif;font-size:25px;font-weight:700;}ToonCrafter Workflow Challenge !!