ComfyUI Node
Hy-Nomas Segment
Conditioning and an empty latent for one segment: its text (Qwen2.5-VL, layer -3), its action masks, and the world so far as history. Sample it with KSampler (euler, simple, 8 steps, cfg 1), then add it to the world with Extend World.
Hy-Nomas Segment
- clip
- script
- world
- camera
- positive
- negative
- latent
◄segment_index0►
◄width832►
◄height480►
◄override_text—►
CategoryHy-Nomas
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| clip | CLIP | Qwen2.5-VL-7B in Load CLIP with type qwen_image | |
| script | HYNOMAS_SCRIPT | — | |
| segment_index | INT | 00–1000 | — |
| width | INT | 83232–4096 | Frame size, a multiple of 32. Tencent's defaults: 1280x704 (their 720p; the latent grid is 40x22) or 832x480. Every segment of a world must use the same size. |
| height | INT | 48032–4096 | Frame size, a multiple of 32. Tencent's defaults: 1280x704 (their 720p; the latent grid is 40x22) or 832x480. Every segment of a world must use the same size. |
| worldopt | HYNOMAS_WORLD | The world holding segments 0..index-1; none for the first segment. | |
| cameraopt | HYNOMAS_CAMERA | — | |
| override_textopt | STRING | A segment prompt string to use instead of the script's. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| positive | CONDITIONING | — |
| negative | CONDITIONING | — |
| latent | LATENT | — |