A complete workflow to recreate a video using a different person by combining:
Identity from an image (Qwen Image Edit 2511)
Motion and performance from a video (LTX 2.3)
This is not a traditional face swap. Instead of replacing faces frame by frame, the model regenerates the entire video using motion guidance and identity conditioning.
The result is a new clip where the performance stays the same, but the identity changes.
🔧 Workflow + Setup
GitHub repository (workflow + instructions): 👉 https://github.com/ZETALVX/ComfyUI
Youtube Tutorial:
Includes:
ComfyUI workflow
required models
setup instructions
tips for better identity stability
Description
FAQ
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.