New Update v2.1 !!! Available Here :  https://www.patreon.com/posts/update-v2-1-lcm-95056616

.

.

A series of 5 workflows, for easy understanding, usage, and more clarity.

The Workflow is divided into 5 parts :

• Part 1 - ControlNet Passes Export
• Part 2 - Animation Raw - LCM
• Part 3 - AnimateDiff Refiner - LCM
• Part 4 - AnimateDiff Face Fix - LCM
• Part 5 - Batch Face Swap - ReActor [Optional] [Experimental]

[Experimental workflow, may produce blurry results ... will try to fix this till the next update]

HOW TO USE:

1) Enter the Input Folder path you want to swap faces with.

2) Enter the Output path for saving them.

3) Batch Range and Skip Frames Works as Usual. (Keep range to 0 and skip frame to 0 to render all frames)

4) Input Face Image to swap with. (Make sure you use front profile and close up pic of the face)

*Note: The input images in the folder should all have the same dimensions else it will give Dimension error.

* This workflow can give blurry/lowres face result in closeups...

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

Installation:

https://github.com/Gourieff/comfyui-reactor-node

https://github.com/Gourieff/sd-webui-reactor#insightfacebuild

Custom Nodes:

https://github.com/YMC-GitHub/ymc-node-suite-comfyui

https://github.com/Stability-AI/stability-ComfyUI-nodes

https://github.com/WASasquatch/was-node-suite-comfyui

https://github.com/pythongosssss/ComfyUI-Custom-Scripts

https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes

https://github.com/Kosinkadink/ComfyUI-Advanced-ControlNet

https://github.com/Kosinkadink/ComfyUI-AnimateDiff-Evolved

https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite

https://github.com/kijai/ComfyUI-KJNodes

---------

*After Installing all nodes, drag and drop the workflow again, some nodes set back to default which will give errors.

*Do not put space in the end of folder path inputs nodes, it will give error.

*It can take longer time to replace faces, test for 10 frames (Batch Range :10) and note time, then you can batch all.

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

This workflow was originally made to test face fixing for animatediff - https://youtu.be/HbfDjAMFi6w

but it could work as a batch face fixing / swapper for other images.

It is observed that it can also swap bad faces with good ones to some extent. Which can be an alternative way to fix faces for animatediff outputs.

Caution : Images have different Sizes in the Input can give you dimension error.

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

If you need Cloud GPU : https://www.runcomfy.com/?ref=jerrydavos