ComfyUI Node
Smart Painter Long Video
Smart Painter Long Video: long-form WAN video conditioning with optional CLIP Vision reference image and independent strength. Identical execute logic to PainterLongVideo, plus an extra clip_vision_reference_image slot for off-screen subject/style guidance through the model's img_emb cross-attention.
Smart Painter Long Video
- positive
- negative
- vae
- previous_video
- initial_reference_image
- clip_vision_output
- clip_vision_reference_image
- start_image
- end_image
- positive
- negative
- latent
◄width832►
◄height480►
◄length81►
◄batch_size1►
◄motion_frames5►
◄motion_amplitude1.15►
◄cv_reference_strength1.00►
CategorySmartHelperNodes/Wan
Inputs (16)
| Name | Type | Default | Description |
|---|---|---|---|
| positive | CONDITIONING | — | |
| negative | CONDITIONING | — | |
| vae | VAE | — | |
| width | INT | 83216–8192 | — |
| height | INT | 48016–8192 | — |
| length | INT | 811–1000 | — |
| batch_size | INT | 11–4096 | — |
| motion_frames | INT | 51–20 | — |
| motion_amplitude | FLOAT | 1.151–2 | — |
| previous_videoopt | IMAGE | — | |
| initial_reference_imageopt | IMAGE | Optional VAE-encoded reference appended to the conditioning's reference_latents list (zero latent on the negative side). NOTE: Only effective on WAN checkpoints that ship with a ref_conv layer (Fun Control, Animate, SCAIL, HuMo, VACE-merged). Silently ignored by stock WAN 2.2 FLF2V / I2V / T2V and most custom merges. For a reference-image channel that works on any base WAN 2.2 checkpoint, use clip_vision_reference_image below instead. Leave unconnected to keep the original pipeline unchanged. | |
| clip_vision_outputopt | CLIP_VISION_OUTPUT | — | |
| clip_vision_reference_imageopt | CLIP_VISION_OUTPUT | Optional extra CLIP Vision slot for an off-screen reference image (subject identity, clothing, object that isn't in start/end frames). Merged with clip_vision_output by concatenating their token sequences along the token axis. Feeds the model's img_emb cross-attention pathway — the only non-keyframe image-guidance channel available on stock WAN 2.2 base checkpoints (no VACE / no ref_conv required). Provides semantic / style / identity guidance. NOT pixel-faithful — good for 'keep the jacket this color', weak for 'reproduce this exact logo'. Leave unconnected to keep the original pipeline unchanged. | |
| cv_reference_strengthopt | FLOAT | 1.000–3 | Only active when clip_vision_reference_image is connected. Scales the reference image's CLIP token magnitudes before they are merged with clip_vision_output. Higher values make the reference dominate the cross-attention, lower values let the existing CLIP guidance win. 0.0 = reference disabled (same as leaving clip_vision_reference_image unconnected). 1.0 = equal weight with clip_vision_output tokens. 2.0-3.0 = reference boosted (useful if the reference subject is being ignored by the model). Defaults to 1.0. |
| start_imageopt | IMAGE | — | |
| end_imageopt | IMAGE | — |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| positive | CONDITIONING | — |
| negative | CONDITIONING | — |
| latent | LATENT | — |