Nodes/Wan22FirstLastFrameToVideoLatent for ComfyUI/Wan22FirstLastFrameToVideoLatent (Tiled VAE encode)
ComfyUI Node
Wan22FirstLastFrameToVideoLatent (Tiled VAE encode)
A ComfyUI node in conditioning/video_models with 11 inputs and 1 output.
Wan22FirstLastFrameToVideoLatent (Tiled VAE encode)
- vae
- start_image
- end_image
- latent
◄width832►
◄height480►
◄length81►
◄batch_size1►
◄tile_size512►
◄overlap64►
◄temporal_size64►
◄temporal_overlap8►
Categoryconditioning/video_models
Inputs (11)
| Name | Type | Default | Description |
|---|---|---|---|
| vae | VAE | — | |
| width | INT | 83216–16384 | — |
| height | INT | 48016–16384 | — |
| length | INT | 811–16384 | — |
| batch_size | INT | 11–4096 | — |
| tile_size | INT | 512128–4096 | — |
| overlap | INT | 640–4096 | — |
| temporal_size | INT | 648–4096 | Amount of frames to encode at a time. |
| temporal_overlap | INT | 84–4096 | Amount of frames to overlap. |
| start_imageopt | IMAGE | — | |
| end_imageopt | IMAGE | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| latent | LATENT | — |