Hi! I'd like to request support for the following ComfyUI custom node pack:
ComfyUI-H3-FaceRefine
https://github.com/Carasibana/ComfyUI-H3-FaceRefine
It provides a temporal face-refinement workflow for already-generated videos: face tracking, stabilized crops, per-frame adaptive denoise, H3-based face regeneration, and temporal stitching back into the original video.
This would be especially useful on SeaArt as a post-processing/refinement stage for videos generated with Wan 2.2 / WanVideo and other video models, particularly for correcting small or distant faces while preserving the original video motion and composition.
Since SeaArt already supports MiniMax H3 and many of the required ComfyUI video/model components, this node pack could provide a very useful video face-detailing/refinement workflow.
Thanks!
Please authenticate to join the conversation.
Awaiting Dev Review
Feedback
ComfyUI
6 days ago

Inspecta Gadget
Get notified by email when there are changes.
Awaiting Dev Review
Feedback
ComfyUI
6 days ago

Inspecta Gadget
Get notified by email when there are changes.