Nodes/comfyui-superside-nodes/Superside MiniMax H3 Image-to-Video
ComfyUI Node

Superside MiniMax H3 Image-to-Video

MiniMax H3 Image-to-Video on fal. Returns a native VIDEO plus the URL, so SaveVideo or PreviewVideo connects straight in. Endpoints: h3 - minimax/h3/image-to-video h3 max - minimax/h3-max/image-to-video h3 max turbo - minimax/h3-max-turbo/image-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. | h3-max: Video costs $0.0325 per second at 480p, $0.052 per second at 768p, and $0.104 per second at 1080p. Note: these are promotional rates, 35% off for a limited time. The discount ends October 31, after which 480p is $0.05/second, 768p is $0.08/second, and 1080p is $0.16/second. | h3-max-turbo: Video costs $0.01625 per second at 480p, $0.026 per second at 768p, and $0.052 per second at 1080p. Note: these are promotional rates, 35% off for a limited time. The discount ends October 31, after which 480p is $0.025/second, 768p is $0.04/second, and 1080p is $0.08/second.

By Superside·Created 4 months ago·Updated a day ago· 1
Superside MiniMax H3 Image-to-Video
  • image_url
  • end_image_url
  • video
  • video_url
◄modelh3►
◄prompt►
◄api_key►
◄enable_safety_checkertrue►
◄duration5►
◄target_audio_url►
◄seed0►
◄resolution768P►
◄prompt_expansion_modebalanced►
CategorySuperside

Inputs (11)

NameTypeDefaultDescription
modelCOMBOh3Which endpoint to call. These share one control surface and differ in quality, speed and price: h3 - minimax/h3/image-to-video h3 max - minimax/h3-max/image-to-video h3 max turbo - minimax/h3-max-turbo/image-to-video
promptSTRINGText prompt for video generation
api_keySTRING—
image_urloptIMAGEOptional URL of the image to use as the first frame. When provided, the output canvas follows this image. If only end_image_url is provided, the canvas follows that last frame instead. If both images are omitted, the request is handled as text-to-video (16:9 by default).
end_image_urloptIMAGEOptional URL of the image to use as the last frame. It may be provided alone for end-only keyframe generation; in that case the output canvas follows this image.
enable_safety_checkeroptBOOLEANtrueIf set to true, the safety checker will be enabled.
durationoptINT55–15The duration of the video in seconds.
target_audio_urloptSTRINGOptional URL of an audio clip at least 2 seconds long (maximum 15 MB) to pin to the generated soundtrack. Longer clips are trimmed to the generated video's length, keeping the beginning. The original audio replaces the output soundtrack, padded with silence if shorter than the video, without changing playback speed. Exceptionally high sample rates may be resampled to 96 kHz. Accepts an HTTP(S) URL or a base64 data URI.
seedoptINT0-1–2147483647Random seed. A random seed is selected when omitted. -1 = let the model choose.
resolutionoptCOMBO768PThe 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; h3 max turbo accepts 480P, 768P, 1080P.
prompt_expansion_modeoptCOMBObalancedHow 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; h3 max turbo accepts disabled, balanced, quality. Required by: h3 max, h3 max turbo.

Outputs (2)

NameTypeDescription
videoVIDEO—
video_urlSTRING—