ComfyUI Node
Comfy EverAnimate
Native WanAnimate conditioning node with EverAnimate anchor and latent motion memory.
Comfy EverAnimate
- positive
- negative
- vae
- clip_vision_output
- reference_image
- face_video
- pose_video
- background_video
- character_mask
- continue_motion
- prev_samples
- video_anchor_latent
- positive
- negative
- latent
- trim_latent
- trim_image
- video_frame_offset
◄width832►
◄height480►
◄length77►
◄batch_size1►
◄num_video_anchor_latents4►
◄num_motion_latents1►
◄video_frame_offset0►
◄pose_strength1.000►
◄face_strength1.000►
◄motion_handoff_strength1.00►
◄continue_motion_max_frames5►
Categorymodel/conditioning/video_models
Inputs (23)
| Name | Type | Default | Description |
|---|---|---|---|
| positive | CONDITIONING | — | |
| negative | CONDITIONING | — | |
| vae | VAE | — | |
| width | INT | 83216–16384 | — |
| height | INT | 48016–16384 | — |
| length | INT | 771–16384 | — |
| batch_size | INT | 11–4096 | — |
| num_video_anchor_latents | INT | 41–16 | EverAnimate N. The paper/LoRA default is 4 identity anchor latent slots. |
| num_motion_latents | INT | 10–16 | EverAnimate M. Number of previous sampler latents to carry into the next chunk. |
| video_frame_offset | INT | 00–16384 | Connect this from the previous Comfy EverAnimate video_frame_offset output. |
| pose_strength | FLOAT | 1.0000–10 | Multiplier for native WanAnimate pose latents. 0 disables pose influence. |
| face_strength | FLOAT | 1.0000–10 | Strength for native WanAnimate face guide. 0 sends a neutral face guide. |
| motion_handoff_strength | FLOAT | 1.000–1 | How strongly the previous chunk's motion latents are locked into the next chunk. 1.0 is the original hard handoff; 0.6-0.8 is usually smoother for low-step distill runs. |
| continue_motion_max_frames | INT | 51–16384 | When continue_motion images are connected, carry this many final RGB frames into the next chunk. This matches native WanAnimate's image carry-over behavior. |
| clip_vision_outputopt | CLIP_VISION_OUTPUT | — | |
| reference_imageopt | IMAGE | — | |
| face_videoopt | IMAGE | — | |
| pose_videoopt | IMAGE | — | |
| background_videoopt | IMAGE | — | |
| character_maskopt | MASK | — | |
| continue_motionopt | IMAGE | Native-style image carry-over. Connect the previous chunk's final decoded images here. When connected, this takes priority over prev_samples. | |
| prev_samplesopt | LATENT | Previous native Wan sampler output. The node takes the last M latents as motion memory. | |
| video_anchor_latentopt | LATENT | Advanced: prebuilt N anchor latents. Leave empty to repeat the reference image latent. |
Outputs (6)
| Name | Type | Description |
|---|---|---|
| positive | CONDITIONING | — |
| negative | CONDITIONING | — |
| latent | LATENT | — |
| trim_latent | INT | — |
| trim_image | INT | — |
| video_frame_offset | INT | — |