ComfyUI Node
CS Video Segment (SeC-4B)
A ComfyUI node in 😺dzNodes/CineStyle/Video with 11 inputs and 3 outputs.
CS Video Segment (SeC-4B)
- model
- images
- video_input
- proxy_video
- MASK
- anchor_mask
- video_info
◄anchor_frame0►
◄tracking_directionbidirectional►
◄max_frames_to_track-1►
◄mllm_memory_size12►
◄offload_video_to_cpufalse►
◄auto_unload_modeltrue►
◄prompt_data{"version":2,"objects":[]}►
Category😺dzNodes/CineStyle/Video
Inputs (11)
| Name | Type | Default | Description |
|---|---|---|---|
| model | SEC_MODEL | Loaded SeC-4B model. | |
| anchor_frame | INT | 00–10000000 | — |
| tracking_direction | COMBO | bidirectional | 3 options: forward, backward, bidirectional |
| max_frames_to_track | INT | -1-1–10000000 | — |
| mllm_memory_size | INT | 121–20 | — |
| offload_video_to_cpu | BOOLEAN | false | — |
| auto_unload_model | BOOLEAN | true | — |
| imagesopt | IMAGE | Video frames as an IMAGE batch. | |
| video_inputopt | VIDEO | Optional VIDEO input. | |
| proxy_videoopt | VIDEO | Optional VIDEO used only by Selector preview. | |
| prompt_dataopt | STRING | {"version":2,"objects":[]} | Selector multi-object mask, bbox, and point prompts. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| MASK | MASK | — |
| anchor_mask | MASK | — |
| video_info | DICT | — |