ComfyUI Node
WanAnimatePlus ClipVisionEncode
A ComfyUI node in WanAnimatePlus with 11 inputs and 1 output.
WanAnimatePlus ClipVisionEncode
- clip_vision
- image_1
- image_2
- negative_image
- image_embeds
◄strength_11.000►
◄strength_21.000►
◄cropcenter►
◄combine_embedsaverage►
◄force_offloadtrue►
◄tiles0►
◄ratio0.50►
CategoryWanAnimatePlus
Inputs (11)
| Name | Type | Default | Description |
|---|---|---|---|
| clip_vision | CLIP_VISION | — | |
| image_1 | IMAGE | Image to encode | |
| strength_1 | FLOAT | 1.0000–10 | Additional clip embed multiplier |
| strength_2 | FLOAT | 1.0000–10 | Additional clip embed multiplier |
| crop | COMBO | center | Crop image to 224x224 before encoding |
| combine_embeds | COMBO | average | Method to combine multiple clip embeds |
| force_offload | BOOLEAN | true | — |
| image_2opt | IMAGE | — | |
| negative_imageopt | IMAGE | image to use for uncond | |
| tilesopt | INT | 00–16 | Use matteo's tiled image encoding for improved accuracy |
| ratioopt | FLOAT | 0.500–1 | Ratio of the tile average |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| image_embeds | WANVIDIMAGE_CLIPEMBEDS | — |