ComfyUI Node
Wan22 Animate To Video (Tiled VAE Encode)
A ComfyUI node in conditioning/video_models with 20 inputs and 6 outputs.
Wan22 Animate To Video (Tiled VAE Encode)
- positive
- negative
- vae
- clip_vision_output
- reference_image
- face_video
- pose_video
- background_video
- character_mask
- continue_motion
- positive
- negative
- latent
- trim_latent
- trim_image
- video_frame_offset
◄width832►
◄height480►
◄length77►
◄batch_size1►
◄continue_motion_max_frames5►
◄tile_size512►
◄overlap64►
◄temporal_size64►
◄temporal_overlap8►
◄video_frame_offset0►
Categoryconditioning/video_models
Inputs (20)
| Name | Type | Default | Description |
|---|---|---|---|
| positive | CONDITIONING | — | |
| negative | CONDITIONING | — | |
| vae | VAE | — | |
| width | INT | 83216–16384 | — |
| height | INT | 48016–16384 | — |
| length | INT | 771–16384 | — |
| batch_size | INT | 11–4096 | — |
| continue_motion_max_frames | INT | 51–16384 | — |
| tile_size | INT | 51264–4096 | Tile size for VAE encoding (X and Y). |
| overlap | INT | 640–4096 | Overlap between spatial tiles. |
| temporal_size | INT | 648–4096 | Number of frames to encode per temporal tile. |
| temporal_overlap | INT | 84–4096 | Overlap between temporal tiles. |
| clip_vision_outputopt | CLIP_VISION_OUTPUT | — | |
| reference_imageopt | IMAGE | — | |
| face_videoopt | IMAGE | — | |
| pose_videoopt | IMAGE | — | |
| background_videoopt | IMAGE | — | |
| character_maskopt | MASK | — | |
| continue_motionopt | IMAGE | — | |
| video_frame_offsetopt | INT | 00–16384 | — |
Outputs (6)
| Name | Type | Description |
|---|---|---|
| positive | CONDITIONING | — |
| negative | CONDITIONING | — |
| latent | LATENT | — |
| trim_latent | INT | — |
| trim_image | INT | — |
| video_frame_offset | INT | — |