Wan VACE → Video (caps inpaint)
WanVaceToVideoCapsInpaint
conditioning/video_modelsexperimental
WAN VACE cap-stitch inpaint node for hard clip joins. Treats start/end cap frames as preserved known regions and the middle as unknown generated region, with enforced neutral filler to prevent hidden evidence leakage.
Pack: sweet-tea-nodes
custom_nodes.sweet-tea-nodes
Inputs (15)
| Name | Type | Required |
|---|---|---|
| positive | CONDITIONING | required |
| negative | CONDITIONING | required |
| vae | VAE | required |
| width | INT | required |
| height | INT | required |
| length | INT | required |
| batch_size | INT | required |
| strength | FLOAT | required |
| start_control_frames | INT | required |
| end_control_frames | INT | required |
| control_video | IMAGE | optional |
| reference_image | IMAGE | optional |
| ref_strength | FLOAT | optional |
| ctrl_strength | FLOAT | optional |
| ref_noise_std | FLOAT | optional |
Outputs (4)
| Name | Type |
|---|---|
| positive | CONDITIONING |
| negative | CONDITIONING |
| latent | LATENT |
| trim_latent | INT |