ComfyUI Node
Hy-Nomas Drive
Explore a world interactively: steer with W/A/S/D and the arrow keys in the node while it generates turn by turn, each turn continuing the world with the keys you held since the previous one. Use the panel's buttons; Queue/Run is not needed. Slower than real time: on an RTX 4090 a 1 s turn takes about 3 s at 832x480.
Hy-Nomas Drive
- model
- clip
- decoder
- encoder
- start_image
◄world_json{
"perspective_view": "third-person observer",
"Style": "CG",
"subject_list": [
{"subject_id": "<|Subject1|>", "display_name": "small orange fox",
"subject_attribute": "A small fox with orange fur, a white chest and a fluffy white-tipped tail, standing on a stone path in side view. The camera films the small orange fox from an external position, and the small orange fox is visible in the video. The framing of the video from the camera is independent of the small orange fox, and does not follow the movement of the small orange fox."}
],
"segments": [
{
"start_time": "00:00.000", "end_time": "00:05.000",
"visual_description_long": "A flagstone path crosses a luminous forest of tall dark trunks under a misty canopy. Lush green grass and low bushes line both sides of the path, with mossy gray rocks scattered along its edge. Small blue fireflies drift and glow between the trees in the soft, hazy light, and the background fades into pale fog.",
"description_change": null,
"contained_actions": [
{"start_time": "00:00.000", "end_time": "00:05.000", "action_description": "<Action1><|Subject1|> walks slowly to the left along the stone path</Action1>."}
]
},
{
"start_time": "00:05.000", "end_time": "00:10.000",
"visual_description_long": null,
"description_change": "Compared to the previous segment, clusters of glowing blue flowers open in the grass beside the path, while the trees, fog and fireflies remain unchanged.",
"contained_actions": [
{"start_time": "00:05.000", "end_time": "00:07.500", "action_description": "<Action1><|Subject1|> stops beside the flowers and turns around to face the camera</Action1>."},
{"start_time": "00:07.500", "end_time": "00:10.000", "action_description": "<Action2><|Subject1|> sniffs the glowing flowers and looks around</Action2>."}
]
}
]
}►
◄width832►
◄height480►
◄turn_seconds1.0►
◄seed42►
◄history_frames18►
◄command►
CategoryHy-Nomas
Inputs (12)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| clip | CLIP | Qwen2.5-VL-7B in Load CLIP with type qwen_image | |
| decoder | HYNOMAS_DECODER | — | |
| world_json | STRING | { "perspective_view": "third-person observer", "Style": "CG", "subject_list": [ {"subject_id": "<|Subject1|>", "display_name": "small orange fox", "subject_attribute": "A small fox with orange fur, a white chest and a fluffy white-tipped tail, standing on a stone path in side view. The camera films the small orange fox from an external position, and the small orange fox is visible in the video. The framing of the video from the camera is independent of the small orange fox, and does not follow the movement of the small orange fox."} ], "segments": [ { "start_time": "00:00.000", "end_time": "00:05.000", "visual_description_long": "A flagstone path crosses a luminous forest of tall dark trunks under a misty canopy. Lush green grass and low bushes line both sides of the path, with mossy gray rocks scattered along its edge. Small blue fireflies drift and glow between the trees in the soft, hazy light, and the background fades into pale fog.", "description_change": null, "contained_actions": [ {"start_time": "00:00.000", "end_time": "00:05.000", "action_description": "<Action1><|Subject1|> walks slowly to the left along the stone path</Action1>."} ] }, { "start_time": "00:05.000", "end_time": "00:10.000", "visual_description_long": null, "description_change": "Compared to the previous segment, clusters of glowing blue flowers open in the grass beside the path, while the trees, fog and fireflies remain unchanged.", "contained_actions": [ {"start_time": "00:05.000", "end_time": "00:07.500", "action_description": "<Action1><|Subject1|> stops beside the flowers and turns around to face the camera</Action1>."}, {"start_time": "00:07.500", "end_time": "00:10.000", "action_description": "<Action2><|Subject1|> sniffs the glowing flowers and looks around</Action2>."} ] } ] } | The world to start from; its first segment is the first turn. Later turns take their text from the panel. |
| width | INT | 83264–2048 | 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 | 48064–2048 | 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. |
| turn_seconds | FLOAT | 1.00.5–5 | Video per turn. Shorter turns answer the keys sooner; longer ones are more efficient. |
| seed | INT | 420–18446744073709550000 | — |
| history_framesopt | INT | 180–1024 | — |
| encoderopt | HYNOMAS_ENCODER | With start_image: Load Encoder's output | |
| start_imageopt | IMAGE | Start the drive from this picture (with an encoder): it becomes the world's first segment, described by world_json's first segment, and the first turn moves on from it | |
| commandopt | STRING | Set by the drive panel. |
Outputs (0)
No outputs