ComfyUI Node
PainterAI2V
A ComfyUI node in conditioning/video_models with 18 inputs and 6 outputs.
PainterAI2V
- model_high_noise
- model_low_noise
- model_patch
- positive
- negative
- vae
- audio_encoder_output_1
- clip_vision_output
- start_image
- end_image
- previous_frames
- high_model
- low_model
- positive
- negative
- latent
- trim_image
◄mode▾►
◄width832►
◄height480►
◄length81►
◄video_fps20.00►
◄motion_frame9►
◄audio_scale1.00►
Categoryconditioning/video_models
Inputs (18)
| Name | Type | Default | Description |
|---|---|---|---|
| mode | COMBO | 2 options: [object Object], [object Object] | |
| model_high_noise | MODEL | Wan2.2 high noise model (steps 0-2) | |
| model_low_noise | MODEL | Wan2.2 low noise model (steps 2-4) | |
| model_patch | MODEL_PATCH | InfiniteTalk patch model | |
| positive | CONDITIONING | — | |
| negative | CONDITIONING | — | |
| vae | VAE | — | |
| width | INT | 83216–16384 | — |
| height | INT | 48016–16384 | — |
| length | INT | 811–16384 | — |
| video_fps | FLOAT | 20.001–120 | Video output frame rate - audio lip-sync will match this |
| audio_encoder_output_1 | AUDIO_ENCODER_OUTPUT | — | |
| motion_frame | INT | 91–33 | Number of previous frames to use as motion context. |
| audio_scale | FLOAT | 1.00-10–10 | — |
| clip_vision_outputopt | CLIP_VISION_OUTPUT | — | |
| start_imageopt | IMAGE | — | |
| end_imageopt | IMAGE | — | |
| previous_framesopt | IMAGE | — |
Outputs (6)
| Name | Type | Description |
|---|---|---|
| high_model | MODEL | — |
| low_model | MODEL | — |
| positive | CONDITIONING | — |
| negative | CONDITIONING | — |
| latent | LATENT | — |
| trim_image | INT | — |