Home Artists Posts Import Register

Downloads

Content

A new file has been added to the drive link - 2_7) Animate_Anyone_Raw : which utilizes the Animate Anyone Technology is out now for testing. 

https://drive.google.com/drive/folders/1Y7FSlNOy1N2z71r0T91Ty8Yrq5IuwolE 


Refiner and CN Passes extractor:  https://drive.google.com/drive/folders/1HoZxKUX7WAg7ObqP00R4oIv48sXCEryQ



What is Animate Anyone ? 


Here is some information : https://www.youtube.com/watch?v=LK12oC2N87g&ab_channel=SebastianKamph



Workflow Previews :

1) Main Animate Anyone Setup:


1) Background and Exporting Setup

Uploading Reference image Tips:
- Upload Full Body reference ,
- Face should be fully visible ,
- Background should be simple and plain.
- Hands should not be overlapping other body parts,
- Use images in ratio with 512x768, 

If you have A pose images, that's even better.   


Resizing Tips:
- Use 512x768 or closer dimension, images will be resized in this dimension when saving.
- It may stretch or squash a little, it's fine, the refiner pass will nudge the proportions into place, but avoid too much stretch or squash.

Also Keep in mind the , this animate anyone is trained on tiktok video, so they works best in portrait mode...


3) Controlnet:

- You should have OpenPose Pass exported into a directory before hand from the passes exporter file and paste the directory here. 

4) Automatic Processing


Lap Counter: It increases the skip frames after every queue automatically according to the batch range set by you. 


1) Enter Batch Range (10 is good) 

2) After the first run it will tell the number n of queues you need in the Laps Needed Node

3) Change The Control_After_Generate to "Increment" when ready for automation

4) Press the Queue Prompt Button n times till your Queue Size = N in the side menu. Or use Extra's Batch Option.  

It will automatically stop if you by mistakenly entered more laps, with no images found error, which is fine, no need to worry.  


-----------------------------------------------------------------------------------------------------

INSTALLATION


Installation Video Help: https://www.youtube.com/watch?v=4z0wlS0JZ2Q&ab_channel=OlivioSarikas 

GitHub Link: https://github.com/MrForExample/ComfyUI-AnimateAnyone-Evolved 



*Other than this clip vision model will give errors 

  • 5) You can use any SD vae in this. 


__________________________________________________________________________


Also pip install diffusers in the venv if getting 'diffusers.models.embeddings' error 

https://github.com/MrForExample/ComfyUI-AnimateAnyone-Evolved/issues/2#issuecomment-1901089199 


Trouble shooting errors : https://github.com/MrForExample/ComfyUI-AnimateAnyone-Evolved/issues 

 ---------------------------------------------------------------------------

Authors notes:

1) This Animate anyone works bet with simple plain background, when doing complicated, it wobbles a lot. 

2) Video generation is only dependent on Open Pose, and openpose likey have choppy motion which results in choppy animations. So it would be better if the openpose is rendered via some 3D motion tracking or retargeting the openpose rig.

3) This Technology has low training dataset which is very glitchy and Buggy at the moment which also produced weird result for now.... anyways it will improved in the future. Better to dip some legs in it.


--------------------------------------------------------------------------------------------------------

See ya soon, Good Luck Experimenting <3 

My Discord Server : https://discord.gg/z9rgJyfPWJ

- Jerry Davos 

Comments

xiaoyang

Hello, may I ask why most of the pictures I generated are not good, no matter how to adjust the parameters, they are not well controlled, may I ask how to control, is there any other workflow to batch processing,thank you

mingming ye

Why is it that everything runs normally on my end, but the output render images are completely black? Where could the problem be? Thank you for your answer.

Jerry Davos

Are you using mac ? Black frames error is usually seen on mac os I hope this helps: https://github.com/Kosinkadink/ComfyUI-AnimateDiff-Evolved/issues/48