ComfyUI Node
XB-BOX - 🎵 语音转视频分块
A ComfyUI node in XB_ToolBox/Pipeline with 21 inputs and 5 outputs.
XB-BOX - 🎵 语音转视频分块
- model
- model_patch
- positive
- negative
- vae
- audio_encoder_output_1
- audio_encoder_output_2
- clip_vision_output
- start_image
- previous_frames
- mask_1
- mask_2
- model
- positive
- negative
- latent
- trim_image
◄modesingle_speaker►
◄width832►
◄height480►
◄length81►
◄motion_frame_count9►
◄audio_scale1.00►
◄vae_tile_size256►
◄scale_methodlanczos►
◄crop_modecenter►
CategoryXB_ToolBox/Pipeline
Inputs (21)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| model_patch | MODEL_PATCH | — | |
| positive | CONDITIONING | — | |
| negative | CONDITIONING | — | |
| vae | VAE | — | |
| mode | COMBO | single_speaker | 2 options: single_speaker, two_speakers |
| width | INT | 83216–8192 | — |
| height | INT | 48016–8192 | — |
| length | INT | 811–8192 | — |
| audio_encoder_output_1 | AUDIO_ENCODER_OUTPUT | — | |
| motion_frame_count | INT | 91–33 | — |
| audio_scale | FLOAT | 1.00-10–10 | — |
| vae_tile_size | INT | 25664–3840 | — |
| audio_encoder_output_2opt | AUDIO_ENCODER_OUTPUT | — | |
| clip_vision_outputopt | CLIP_VISION_OUTPUT | — | |
| start_imageopt | IMAGE | — | |
| previous_framesopt | IMAGE | — | |
| mask_1opt | MASK | — | |
| mask_2opt | MASK | — | |
| scale_methodopt | COMBO | lanczos | 5 options: lanczos, bilinear, bicubic, nearest-exact, area |
| crop_modeopt | COMBO | center | 2 options: center, disabled |
Outputs (5)
| Name | Type | Description |
|---|---|---|
| model | MODEL | — |
| positive | CONDITIONING | — |
| negative | CONDITIONING | — |
| latent | LATENT | — |
| trim_image | INT | — |