Author: Gabriel Jiménez
Workflow source: https://openart.ai/workflows/beaver_absolute_68/jboogx-ultimatelcm-animatediff-vid2vid-workflow/DrlmwkcBsCjUBjdAe5VH
Here is a workflow for creating incredible vid2vid animations that use alpha masks to separate your subject and background via two separate IPAdapters! Check out the video walkthrough below!
The main point here is to keep the workflow clean and simple. I've noticed a trend towards over-engineered workflows and wanted to update/share something to help you guys get back to the most important part... creating!
This workflow includes:
• x2 Video Loaders (Main Video + Alpha Mask)
• x2 IPAdapters (x2 Subject Image References + 2 Background Image References)
• High Resolution Channels
Native output resolutions of 512x896, 768x1344• If you need to make some alpha masks, check out the Segment Anything 2 workflow I shared which also has a video tutorial on the Civitai YouTube page! This will help you get clean masks without rotoscoping! Find that workflow here:
https://civitai.com/models/746889/sam2-easy-comfyui-alphamattes-rotoscope
Sign In