Join our Live-Portrait Challenge NOW ! ... You have UNTIL July 21th to participate! Info on the #Challenges Discord Channel. Prize: $50 PayPal Credit! 

---> Live-Portrait ...

yaqing liang

This is a workflow to make dynamic wallpaper with a specified image, you can change the expression and draw mask to animate specified region;Live Portrait is to control the expression, SVD is to animate specified region you draw,Animatediff is to add details and smooth the animation;With these great nodes, you can make dynamic wallpaper as you want;model links are included in the workflow, feel free to contact me at lyqcuc@foxmail.com<img src="https://cdn.openart.ai/wangeditor_uploads/eGgKFklv9PusP1MyMBDC/compressed/image_zWi5etB0_1722315214489_512.webp" alt="" data-href="" style=""/>

LivePortrait+SVD+AnimateDiff Animate you want 

This work is based on this one <a href="https://openart.ai/workflows/datou/anime-2-movie/lNZElhA85DlfVpagkk7C" target="_blank">https://openart.ai/workflows/datou/anime-2-movie/lNZElhA85DlfVpagkk7C.</a>Add face swap by ReActor and drive the face by Live PortraitThe input is 1) the anime picture 2) the face actor 3) the expression videoThe output is a vertically concatenated videos.You can check the output here: <a href="https://www.bilibili.com/video/BV1MqvWebEcn/?spm_id_from=333.999.0.0&vd_source=8c047eca169534a6946e19f6a99df0b0" target="_blank">https://www.bilibili.com/video/BV1MqvWebEcn/?spm_id_from=333.999.0.0&vd_source=8c047eca169534a6946e19f6a99df0b0</a> liveportrait updated @ 0729 to support crop info and head chosen

Who Cosplay Who (Anime2real + face swap + liveportrait)

Ez易孜

Made by Ez One Piece style WANTED, the workflow will randomly generate an amount to see if you are worth only 50 or 100 million. The amount is for entertainment only, as each generation is random. You can change any facial animation you like, but the WANTED IMAGE suggests using a screenshot of One Piece's image(or u can manually modify the size calculation of the amount mask) If you have anything you want to communicate with me, you can add me on WeChat: Ezz1533

WANTED LivePortrait(海贼王悬赏动画，随机生成金额）

neofuturist

Easy workflow to create animatediff based animation with a Liveportrait. Create a nice prompt, select the subject that should be segmented and let this workflow do the rest.Open this workflow, use Comfyui manager to download the missing nodes and you should be good to go. There are a few models needed for Controlnet but you can use this workflow without them

LivePortrait + AnimateDiff backgrounds V 0.2

SEkIN 

<h3>What this workflow does</h3>👉This workflow Generates Animated Painted portraites using my SDXL Presidential Portriate Painte Workflow and the LivePortrait Node. &nbsp; <h3>How to use this workflow</h3>👉 To use this workflow: &nbsp; &nbsp; &nbsp;- Upload a video of with the facial expressions you would like to apply to your image or choose from the two I have provided in the assets section. &nbsp; &nbsp; &nbsp;- Next use the green text prompt box to Describe or name the character you would like to generate &nbsp; &nbsp; &nbsp;- Next hit Queue prompt and you're all done <h3>Tips about this workflow/Need </h3>👉 <a href="https://github.com/kijai/ComfyUI-LivePortraitKJ" target="" style="text-align: start;">ComfyUI-LivePortraitKJ node:</a> <a href="https://github.com/kijai/ComfyUI-LivePortraitKJ" target="_blank">https://github.com/kijai/ComfyUI-LivePortraitKJ</a> 👉 SDXL Turbo: <a href="https://huggingface.co/stabilityai/sdxl-turbo/blob/main/sd_xl_turbo_1.0_fp16.safetensors" target="_blank">https://huggingface.co/stabilityai/sdxl-turbo/blob/main/sd_xl_turbo_1.0_fp16.safetensors</a> 🎥 Video demo link (optional)👉 Coming Soon -Enjoy-

Living Portrait Generator(SDXL Turbo)

Simon Lee

ComfyDaily by <a href="https://openart.ai/workflows/profile/monkey_voluminous_15?sort=latest" target="_blank" style="text-align: start;">Hyacinth </a>&amp; <a href="https://openart.ai/workflows/profile/ladybird_musty_24" target="_blank" style="text-align: start;">Simon Lee</a> ComfyDaily is a workflow to generate live portraits in Harry Potter style. Update:Add a Single-person poster version. NOTE：1. This workflow is super memory hugry in 1 run. If you run out of CUDA memory, you could split it into 2 steps. 1st generate the photo, 2nd generate the live portrait. <li>2. Ollama is not necessary. If you haven't installed it, you can disable that node and write the prompt yourself.</li><li>3. You can record any facial expression video to replace face.mp4</li> ———————————————— INSTRUCTION： Base Model - RealVisXL V4.0:https://civitai.com/models/139562/realvisxl-v40 LoRA：Harry Potter Style / Uniforms XL Lora:https://civitai.com/models/301881/harry-potter-styleuniforms-xl-lora American Newspaper front paper：https://civitai.com/models/555597/american-newspaper-front-page ———————————————— Ollama:https://ollama.com/https://github.com/stavsap/comfyui-ollama InstantID:https://github.com/cubiq/ComfyUI_InstantID PuLID：https://github.com/cubiq/PuLID_ComfyUI Live Portrait:https://github.com/kijai/ComfyUI-LivePortrait —————————————————— License &copy; Since this workflow was created with InstantID and Pulid, which used Insight Face, this workflow is avaiable for non-commercial research purposes only. ❤ Have Fun! by Hyacinth & Simon Lee

【Update】Comfy Daily | Harry Potter Style Live Newspaper + Single-person poster

Aderek

Recently, we've seen a surge in productions styled as "live paintings." I decided to create a Workflow (WF) for this model as well. <img src="https://cdn.openart.ai/wangeditor_uploads/duzl5tMWa23D5zUP30PB/compressed/image_f_US6ZD2_1720961422753_512.webp" alt="" data-href="" style=""/><img src="https://cdn.openart.ai/wangeditor_uploads/duzl5tMWa23D5zUP30PB/compressed/image_GEDcuz_i_1720961447361_512.webp" alt="" data-href="" style=""/> See video:<a href="https://youtu.be/k4G9yqCRF4I" target="_blank">https://youtu.be/k4G9yqCRF4I</a> <div data-w-e-type="video" data-w-e-is-void>
<video poster="https://youtu.be/k4G9yqCRF4I" controls="true" width="auto" height="auto"><source src="https://youtu.be/k4G9yqCRF4I" type="video/mp4"/></video>
</div> However, I introduced a few modifications: first, my WF is designed to generate two moving faces in one image (if you upload a photo with only one face, my model won't work);second, using kSampler, I reprocess each image to mitigate generation errors as much as possible. Have fun! <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>

OpenArt

Workflows

Active Sessions

Workflow Challenge- ---> Live-Portrait ...
Join our Live-Portrait Challenge NOW ! ... You have UNTIL July 21th to participate! Info on the #Challenges Discord Channel. Prize: $50 PayPal Credit!
7/7/2024-7/21/2024