ComfyUI Node
Superside MiniMax H3 Reference-to-Video
MiniMax H3 Reference-to-Video on fal. Returns a native VIDEO plus the URL, so SaveVideo or PreviewVideo connects straight in. Endpoints: h3 - minimax/h3/reference-to-video h3 max - minimax/h3-max/reference-to-video fal price (2026-10-30): h3: Video costs $0.05 per second at 480p, $0.06 per second at 768p, $0.13 per second at 2K and $0.16 per second at 4K; the first 5 reference images are free and each additional image costs $0.08. | h3-max: Billing uses the requested output duration at $0.05 per second for 480p, $0.08 for 768p, and $0.16 for 1080p.
Superside MiniMax H3 Reference-to-Video
- reference_image_1
- reference_image_2
- reference_image_3
- reference_image_4
- reference_video_1
- reference_video_2
- reference_video_3
- reference_video_4
- end_image_url
- middle_image_url
- image_url
- video
- video_url
◄modelh3►
◄prompt►
◄api_key►
◄reference_audio_urls►
◄enable_safety_checkertrue►
◄duration5►
◄seed0►
◄resolution768P►
◄prompt_expansion_modebalanced►
◄aspect_ratioadaptive►
◄reference_conditions►
◄middle_frame_time0.00►
CategorySuperside
Inputs (23)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | h3 | Which endpoint to call. These share one control surface and differ in quality, speed and price: h3 - minimax/h3/reference-to-video h3 max - minimax/h3-max/reference-to-video |
| prompt | STRING | Text prompt for video generation. Refer to reference assets by their modality and order in the reference lists: Image 1, Image 2, Video 1, Audio 1, and so on. | |
| api_key | STRING | — | |
| reference_audio_urlsopt | STRING | URLs of reference audio clips (2-15 seconds each, combined duration at most 15 seconds), referenced in the prompt as Audio 1, Audio 2, and so on. Images, videos, and audio can be provided individually or together. Reference images, videos, and audio clips must add up to at most 12 files. One URL per line. | |
| enable_safety_checkeropt | BOOLEAN | true | If set to true, the safety checker will be enabled. |
| durationopt | INT | 55–15 | The duration of the video in seconds. |
| reference_image_1opt | IMAGE | URLs of subject/style reference images, referenced in the prompt as Image 1, Image 2, and so on. Reference images, videos, and audio clips must add up to at most 12 files. | |
| reference_image_2opt | IMAGE | URLs of subject/style reference images, referenced in the prompt as Image 1, Image 2, and so on. Reference images, videos, and audio clips must add up to at most 12 files. | |
| reference_image_3opt | IMAGE | URLs of subject/style reference images, referenced in the prompt as Image 1, Image 2, and so on. Reference images, videos, and audio clips must add up to at most 12 files. | |
| reference_image_4opt | IMAGE | URLs of subject/style reference images, referenced in the prompt as Image 1, Image 2, and so on. Reference images, videos, and audio clips must add up to at most 12 files. | |
| seedopt | INT | 0-1–2147483647 | Random seed. A random seed is selected when omitted. -1 = let the model choose. |
| resolutionopt | COMBO | 768P | The resolution of the generated video. 480P and 768P are native generation modes; 2K and 4K upscale a 768P base result. Not every model takes every value here: h3 accepts 480P, 768P, 2K, 4K; h3 max accepts 480P, 768P, 1080P. |
| prompt_expansion_modeopt | COMBO | balanced | How much effort to spend rewriting the prompt before generation. 'disabled' skips prompt expansion. 'fast' returns in about a second. 'balanced' picks per request. 'quality' spends up to ~30s on a richer prompt. Not every model takes every value here: h3 accepts disabled, fast, balanced, quality; h3 max accepts disabled, balanced, quality. Required by: h3 max. |
| reference_video_1opt | VIDEO | URLs of motion/reference video clips (2-15 seconds each, combined duration at most 15 seconds), referenced in the prompt as Video 1, Video 2, and so on. Reference images, videos, and audio clips must add up to at most 12 files. | |
| reference_video_2opt | VIDEO | URLs of motion/reference video clips (2-15 seconds each, combined duration at most 15 seconds), referenced in the prompt as Video 1, Video 2, and so on. Reference images, videos, and audio clips must add up to at most 12 files. | |
| reference_video_3opt | VIDEO | URLs of motion/reference video clips (2-15 seconds each, combined duration at most 15 seconds), referenced in the prompt as Video 1, Video 2, and so on. Reference images, videos, and audio clips must add up to at most 12 files. | |
| reference_video_4opt | VIDEO | URLs of motion/reference video clips (2-15 seconds each, combined duration at most 15 seconds), referenced in the prompt as Video 1, Video 2, and so on. Reference images, videos, and audio clips must add up to at most 12 files. | |
| aspect_ratioopt | COMBO | adaptive | The aspect ratio of the generated video. |
| end_image_urlopt | IMAGE | Optional URL of the image to use as the last frame. The video ends exactly on this image. | |
| middle_image_urlopt | IMAGE | Optional image to guide the video at middle_frame_time. Requires start and end images and native 480P or 768P resolution. | |
| reference_conditionsopt | STRING | Ordered reference list; cross-modality order is semantic and is preserved end-to-end. Do not combine with reference_*_urls. JSON, as fal documents this field. | |
| image_urlopt | IMAGE | Optional URL of the image to use as the first frame. The video opens exactly on this image while the references keep the subjects consistent; the output canvas follows this image. | |
| middle_frame_timeopt | FLOAT | 0.00-1–100 | Target time for the middle image, in seconds from the start. Rounded to the nearest frame at 24 fps; it must fall strictly between the first and last frames of the requested duration. Requires middle_image_url. -1 = let the model choose. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| video | VIDEO | — |
| video_url | STRING | — |