ComfyUI Node
WanAnimatePlus EverAnimate Embeds
EverAnimate conditioning bundle for segmented WanAnimatePlus sampling.
WanAnimatePlus EverAnimate Embeds
- vae
- pose_images
- face_images
- anchor_images
- bg_images
- mask
- image_embeds
◄width832►
◄height480►
◄num_frames734►
◄force_offloadtrue►
◄frame_window_size77►
◄pose_strength1.000►
◄face_strength1.000►
◄num_video_anchor_latents4►
◄num_motion_latents1►
◄num_overlap_frame4►
◄use_pingpongtrue►
◄use_image_anchortrue►
◄use_random_frame_anchortrue►
◄random_anchor_with_user_firsttrue►
◄use_repeat_anchorfalse►
◄tiled_vaefalse►
CategoryWanAnimatePlus
Inputs (22)
| Name | Type | Default | Description |
|---|---|---|---|
| vae | WANVAE | — | |
| width | INT | 83264–8096 | Width of the video to generate |
| height | INT | 48064–8096 | Height of the video to generate |
| num_frames | INT | 7341–10000 | Total output frames. Segment count is computed from this, frame_window_size, and num_overlap_frame. |
| force_offload | BOOLEAN | true | Offload VAE after encoding to save VRAM |
| frame_window_size | INT | 771–10000 | Effective output frames per EverAnimate segment. Must be 1 mod 4, e.g. 77, 81, 85. |
| pose_strength | FLOAT | 1.0000–10 | Additional multiplier for the pose adapter |
| face_strength | FLOAT | 1.0000–10 | Additional multiplier for the face adapter |
| pose_images | IMAGE | Pose control video | |
| face_images | IMAGE | Face control video. Resized to 512x512 internally. | |
| num_video_anchor_latents | INT | 41–4 | Number of anchor latent slots prepended to each EverAnimate segment |
| num_motion_latents | INT | 10–4 | Number of previous-segment motion latents used for continuity |
| num_overlap_frame | INT | 40–10000 | Overlapping output frames between adjacent segments |
| use_pingpong | BOOLEAN | true | Ping-pong extend pose, face, bg, and mask sequences when more frames are needed |
| use_image_anchor | BOOLEAN | true | Use generated frames from the first segment to build later video anchors |
| use_random_frame_anchor | BOOLEAN | true | Randomly sample generated segment-0 frames for later video anchors |
| random_anchor_with_user_first | BOOLEAN | true | In random-anchor mode, reserve the first manual anchor frame as the user anchor |
| use_repeat_anchor | BOOLEAN | false | When fewer manual anchor frames are provided than anchor slots, repeat the provided sequence to fill the missing slots |
| anchor_images | IMAGE | Manual identity/anchor image frames. Video inputs are treated as an anchor-frame sequence, not as source-video conditioning. | |
| bg_imagesopt | IMAGE | Optional background/inpaint video | |
| maskopt | MASK | Optional mask paired with bg_images | |
| tiled_vaeopt | BOOLEAN | false | Use tiled VAE encoding for reduced memory use |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| image_embeds | WANVIDIMAGE_EMBEDS | — |