ComfyUI Node
Superside MiniMax H3 Max 3D-to-Video
MiniMax H3 Max 3D-to-Video on fal. Returns a native VIDEO plus the URL, so SaveVideo or PreviewVideo connects straight in. Endpoint: default - minimax/h3-max/3d-to-video fal price (2026-10-30): For every second of video you generate you will be charged $0.05 at 480p, $0.08 at 768p or $0.16 at 1080p (minimum 5 seconds), plus reference token usage for your input video and images, the same as H3 Max Reference to Video.
Superside MiniMax H3 Max 3D-to-Video
- video_url
- reference_image_1
- reference_image_2
- reference_image_3
- reference_image_4
- video
- video_url
◄api_key►
◄prompt►
◄enable_safety_checkertrue►
◄max_generated_reference_images2►
◄resolution768P►
CategorySuperside
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| video_url | VIDEO | Blender video, up to 15 seconds and 32 shots, at a public HTTPS URL. | |
| api_key | STRING | — | |
| promptopt | STRING | Optional clarification of what your proxies represent or how they move, for example: 'The moving block represents a running person.' Camera, trajectories, timing and object count remain defined by the video. | |
| enable_safety_checkeropt | BOOLEAN | true | Authorized callers may set false to request relaxed screening. |
| max_generated_reference_imagesopt | INT | 21–8 | Maximum NEW images to generate when no reference images are supplied. Ignored when reference images are supplied. Uses fewer when enough views are covered. Uncovered shots stay in the video. |
| resolutionopt | COMBO | 768P | Output quality. Duration is taken automatically from the video. |
| reference_image_1opt | IMAGE | Optional environment, subject, interior or detail references. When supplied, uses these images directly without visual planning or generating new images; Scene Intent is optional. Without references, automatically creates appearance references within your new-image limit. Camera and movement always come from the video. | |
| reference_image_2opt | IMAGE | Optional environment, subject, interior or detail references. When supplied, uses these images directly without visual planning or generating new images; Scene Intent is optional. Without references, automatically creates appearance references within your new-image limit. Camera and movement always come from the video. | |
| reference_image_3opt | IMAGE | Optional environment, subject, interior or detail references. When supplied, uses these images directly without visual planning or generating new images; Scene Intent is optional. Without references, automatically creates appearance references within your new-image limit. Camera and movement always come from the video. | |
| reference_image_4opt | IMAGE | Optional environment, subject, interior or detail references. When supplied, uses these images directly without visual planning or generating new images; Scene Intent is optional. Without references, automatically creates appearance references within your new-image limit. Camera and movement always come from the video. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| video | VIDEO | — |
| video_url | STRING | — |