ComfyUI Node
WanAnimatePlus AnimateEmbeds
A ComfyUI node in WanAnimatePlus with 22 inputs and 1 output.
WanAnimatePlus AnimateEmbeds
- vae
- clip_embeds
- ref_images
- pose_images
- face_images
- bg_images
- mask
- start_ref_image
- transition_video
- prefix_frames
- image_embeds
◄width832►
◄height480►
◄num_frames81►
◄force_offloadtrue►
◄frame_window_size77►
◄colormatchdisabled►
◄pose_strength1.000►
◄face_strength1.000►
◄tiled_vaefalse►
◄transition modetrue►
◄single_frame_prefix_encodingfalse►
◄Prefix & Transition Video by wuwukasi(bilibili)true►
CategoryWanAnimatePlus
Inputs (22)
| Name | Type | Default | Description |
|---|---|---|---|
| vae | WANVAE | — | |
| width | INT | 83264–8096 | Width of the image to encode |
| height | INT | 48064–8096 | Height of the image to encode |
| num_frames | INT | 811–10000 | Number of frames to encode |
| force_offload | BOOLEAN | true | — |
| frame_window_size | INT | 771–10000 | Number of frames to use for temporal attention window |
| colormatch | COMBO | disabled | Color matching method to use between the windows |
| pose_strength | FLOAT | 1.0000–10 | Additional multiplier for the pose |
| face_strength | FLOAT | 1.0000–10 | Additional multiplier for the face |
| clip_embedsopt | WANVIDIMAGE_CLIPEMBEDS | Clip vision encoded image | |
| ref_imagesopt | IMAGE | Image to encode | |
| pose_imagesopt | IMAGE | end frame | |
| face_imagesopt | IMAGE | end frame | |
| bg_imagesopt | IMAGE | background images | |
| maskopt | MASK | mask | |
| start_ref_imageopt | IMAGE | start ref image | |
| transition_videoopt | IMAGE | Transition video frames (32 images, encoded to 8 latent frames). Acts as hard conditioning guide for seamless connection. | |
| prefix_framesopt | IMAGE | Up to 5 prefix images. Image 0 is used once; images 1-4 are repeated 4 times each, for a max 17-frame prefix. | |
| tiled_vaeopt | BOOLEAN | false | Use tiled VAE encoding for reduced memory use |
| transition modeopt | BOOLEAN | true | Transition mode: 37-frame layout (17 prefix + 20 transition). Outfit mode: 45-frame layout (17 prefix + 8 reserve + 20 transition). |
| single_frame_prefix_encodingopt | BOOLEAN | false | Encode prefix images as individual reference latents instead of expanding the beginning of the canvas. |
| Prefix & Transition Video by wuwukasi(bilibili)opt | BOOLEAN | true | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| image_embeds | WANVIDIMAGE_EMBEDS | — |