Face Swap with Qwen + LTX 2.3 (V2V Identity + Motion Transfer Explained) ComfyUI
詳細
ファイルをダウンロード (1)
モデル説明
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