ComfyUI Node Runs on cloud
WanDancerVideo
A ComfyUI node in model/conditioning/wan/dancer with 11 inputs and 3 outputs.
WanDancerVideo
- positive
- negative
- vae
- clip_vision_output
- clip_vision_output_ref
- start_image
- mask
- audio_encoder_output
- positive
- negative
- latent
◄width480►
◄height832►
◄length149►
Categorymodel/conditioning/wan/dancer
Inputs (11)
| Name | Type | Default | Description |
|---|---|---|---|
| positive | CONDITIONING | — | |
| negative | CONDITIONING | — | |
| vae | VAE | — | |
| width | INT | 48016–16384 | — |
| height | INT | 83216–16384 | — |
| length | INT | 1491–16384 | The number of frames in the generated video. Should stay 149 for WanDancer. |
| clip_vision_outputopt | CLIP_VISION_OUTPUT | The CLIP vision embeds for the first frame. | |
| clip_vision_output_refopt | CLIP_VISION_OUTPUT | The CLIP vision embeds for the reference image. | |
| start_imageopt | IMAGE | The initial image(s) to be encoded, can be any number of frames. | |
| maskopt | MASK | Image conditioning mask for the start image(s). White is kept, black is generated. Used for the local generations. | |
| audio_encoder_outputopt | AUDIO_ENCODER_OUTPUT | — |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| positive | CONDITIONING | — |
| negative | CONDITIONING | — |
| latent | LATENT | Empty latent. |