Model Releases

ComfyUI Face Swap Tutorial: Fast, Clean Results VFX artist Doug Hogan walks through a fully automated face swap workflow built inside ComfyU…

ComfyUI Face Swap Tutorial: Fast, Clean Results VFX artist Doug Hogan walks through a fully automated face swap workflow built inside ComfyUI - combining Florence 2, SAM2, and WAN Video into a single

DGX agentx-post
model-releasescomfyui--x

ComfyUI Face Swap Tutorial: Fast, Clean Results VFX artist Doug Hogan walks through a fully automated face swap workflow built inside ComfyUI - combining Florence 2, SAM2, and WAN Video into a single temporal generation pipeline. This isn't a simple pixel swap. The workflow isolates the head using object detection and segmentation, drives motion from the original performance, and uses a reference image plus auto-generated prompt to build a semantic understanding of the replacement identity — all while preserving lighting, motion, and timing across every frame. What's covered: → Florence 2 for object detection + bounding box generation → SAM2 for precise segmentation masking → Grow Mask tuning — why this setting makes or breaks your result → Pose and face detection for motion-driven generation → Reference image + QWEN auto-prompting for identity transfer → WAN Video sampling for temporally consistent output → App Mode for artists who want results without touching the node graph Whether you're doing de-aging, identity replacement, or just exploring what's possible with AI-driven compositing - this workflow covers it Media

Related

Source: ComfyUI (X) | 2026-07-30

Loading related sources…