Which open, local ComfyUI workflows give explicit camera control, point-trajectory motion, audio-driven lip-sync and motion transfer, and what do they need?
ComfyUI official tutorials (captured 2026-10-23), all Wan-family (Wan licences Apache-2.0 for 2.x per C3-B370-03; check each repo): (1) Wan2.2 Fun Camera Control (alibaba-pai/Wan2.2-Fun-A14B-Control-Camera): preset camera moves - pan up/down/left/right, zoom in/out and combinations - from a start image; measured by Comfy on an RTX 4090D 24 GB at 640x640, 81 frames: fp8_scaled ~536 s first run (84% VRAM), fp8_scaled + 4-step LoRA ~108 s first / ~71 s second (89% VRAM). (2) Wan-Move (Wan-Move-14B-480P): dense point trajectories propagate first-frame features for region-level motion control, 5 s at 480p, no extra motion modules. (3) Wan2.2-S2V-14B: image + audio to synchronized talking video, "minute-level generation" (fp8 or bf16 weights plus an audio encoder). (4) InfiniteTalk (on Wan2.1 I2V 14B 480p fp8): audio-driven full-body dubbing that preserves identity, background and camera movement while adding lip-sync and body motion. (5) Wan Animate 2: motion transfer from a driving vide...
Structured fields
{
"citations": [
{
"url": "https://docs.comfy.org/tutorials/video/wan/wan2-2-fun-camera.md",
"note": "timing table; Model Highlights; Model Highlights; features"
},
{
"url": "https://docs.comfy.org/tutorials/video/wan/wan-move.md",
"note": "timing table; Model Highlights; Model Highlights; features"
},
{
"url": "https://docs.comfy.org/tutorials/video/wan/wan-animate-2.md",
"note": "timing table; Model Highlights; Model Highlights; features"
},
{
"url": "https://docs.comfy.org/tutorials/video/wan/wan-infinitetalk.md",
"note": "timing table; Model Highlights; Model Highlights; features"
}
]
}Evidence claims
- [sourced_fact] ComfyUI official tutorials (captured 2026-10-23), all Wan-family (Wan licences Apache-2.0 for 2.x per C3-B370-03; check each repo): (1) Wan2.2 Fun Camera Control (alibaba-pai/Wan2.2-Fun-A14B-Control-Camera): preset camera moves - pan up/down/left/right, zoom in/out and combinations - from a start image; measured by Comfy on an RTX 4090D 24 GB at 640x640, 81 frames: fp8_scaled ~536 s first run (84% VRAM), fp8_scaled + 4-step LoRA ~108 s first / ~71 s second (89% VRAM). (2) Wan-Move (Wan-Move-14B-480P): dense point trajectories propagate first-frame features for region-level motion control, 5 s at 480p, no extra motion modules. (3) Wan2.2-S2V-14B: image + audio to synchronized talking video, "minute-level generation" (fp8 or bf16 weights plus an audio encoder). (4) InfiniteTalk (on Wan2.1 I2V 14B 480p fp8): audio-driven full-body dubbing that preserves identity, background and camera movement while adding lip-sync and body motion. (5) Wan Animate 2: motion transfer from a driving video directly to a still character without pose extraction, plus text-driven viewpoint control that decouples output camera from the driving video (int8_convrot default, BF16 and distilled variants). Many use the LightX2V 4-step distill LoRA for speed. These are the local counterparts to hosted keyframe/reference features (Kling, Seedance) and complement TTM stick puppeteering (C3-B339-02). · locator: timing table; Model Highlights; Model Highlights; features source
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| documentation | unknown | permitted | permitted | unknown | unknown | Applies to this original summary only, not to the cited sources. |