ComfyUI Node
IAMCCS Wan-Animate-2 Extends
Long-video wrapper for native WanAnimate2ToVideo. It samples 4n+1 chunks, passes the previous generated frame through continue_motion, advances the raw driving-video offset, trims native latent/image anchors, and optionally composites the generated character over a masked background plate.
IAMCCS Wan-Animate-2 Extends
- model
- positive
- negative
- vae
- sampler
- sigmas
- reference_image
- pose_video
- positive_pose
- clip_vision_output
- clip_vision_output_pose
- reference_character_mask
- composite_mask
- background_image
- background_video
- images
- native_images
- frame_count
- source_frames
- trimmed_frames
- chunk_plan
◄width832►
◄height480►
◄target_frames0►
◄chunk_length81►
◄noise_seed0►
◄seed_modefixed►
◄cfg1.0►
◄reference_image_strength1.00►
◄pose_strength1.00►
◄pose_start_percent0.00►
◄pose_end_percent1.00►
◄add_noisetrue►
◄enable_context_windowstrue►
◄context_length_latents21►
◄context_overlap_latents8►
◄context_schedulestandard_static►
◄context_fuse_methodpyramid►
◄enable_pose_cachetrue►
◄cache_devicecpu►
◄cache_dtypeint8►
◄reference_background_modekeep_reference_background►
◄output_background_modenative_generated►
◄live_chunk_previewmiddle_frame►
◄empty_cache_each_chunkfalse►
CategoryIAMCCS/video/WanAnimate-2
Inputs (39)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| positive | CONDITIONING | — | |
| negative | CONDITIONING | — | |
| vae | VAE | — | |
| sampler | SAMPLER | — | |
| sigmas | SIGMAS | — | |
| reference_image | IMAGE | — | |
| pose_video | IMAGE | Raw driving-video frames. Wan-Animate-2 does not require a DWPose render here. | |
| width | INT | 83216–8192 | — |
| height | INT | 48016–8192 | — |
| target_frames | INT | 00–100000 | 0 uses the complete driving-video frame count. |
| chunk_length | INT | 815–1025 | Wan-Animate-2 official workflow default is 81 frames. |
| noise_seed | INT | 00–18446744073709550000 | — |
| seed_mode | COMBO | fixed | 2 options: fixed, increment |
| cfg | FLOAT | 1.00–100 | — |
| reference_image_strength | FLOAT | 1.000–10 | — |
| pose_strength | FLOAT | 1.000–10 | — |
| pose_start_percent | FLOAT | 0.000–1 | — |
| pose_end_percent | FLOAT | 1.000–1 | — |
| add_noise | BOOLEAN | true | — |
| enable_context_windows | BOOLEAN | true | — |
| context_length_latents | INT | 211–1024 | — |
| context_overlap_latents | INT | 80–1023 | — |
| context_schedule | COMBO | standard_static | 4 options: standard_static, standard_uniform, looped_uniform, batched |
| context_fuse_method | COMBO | pyramid | 4 options: pyramid, relative, flat, overlap-linear |
| enable_pose_cache | BOOLEAN | true | — |
| cache_device | COMBO | cpu | 2 options: cpu, gpu |
| cache_dtype | COMBO | int8 | 3 options: int8, int4, default |
| reference_background_mode | COMBO | keep_reference_background | 2 options: keep_reference_background, isolate_character |
| output_background_mode | COMBO | native_generated | 4 options: native_generated, source_video_composite, reference_image_composite, custom_background_composite |
| live_chunk_preview | COMBO | middle_frame | 4 options: off, first_frame, middle_frame, last_frame |
| empty_cache_each_chunk | BOOLEAN | false | — |
| positive_poseopt | CONDITIONING | — | |
| clip_vision_outputopt | CLIP_VISION_OUTPUT | — | |
| clip_vision_output_poseopt | CLIP_VISION_OUTPUT | — | |
| reference_character_maskopt | MASK | White character mask used only by isolate_character. | |
| composite_maskopt | MASK | White selects generated character; black selects the background plate. | |
| background_imageopt | IMAGE | — | |
| background_videoopt | IMAGE | — |
Outputs (6)
| Name | Type | Description |
|---|---|---|
| images | IMAGE | — |
| native_images | IMAGE | — |
| frame_count | INT | — |
| source_frames | INT | — |
| trimmed_frames | INT | — |
| chunk_plan | STRING | — |