infery
← All models

H3 Max Reference to Video

minimax/h3-max/reference-to-video

Video generationby MiniMax

Example

Details

Accepts
text

Pricing

Price
0.021 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seedRandom seed. A random seed is selected when omitted.
promptrequiredstringText 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.
durationintegerThe duration of the video in seconds.
sync_modebooleanReturn the generated video as base64 instead of a CDN URL.
resolutionstringenum: 480P, 768PThe native generation resolution of the video.
aspect_ratiostringenum: adaptive, 21:9, 16:9, 4:3, 1:1, 3:4The aspect ratio of the generated video.
reference_audio_urlsarrayURLs 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. Audio cannot be the only reference input; provide at least one reference image or video with it. Reference images, videos, and audio clips must add up to …
reference_image_urlsarrayURLs 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_video_urlsarrayURLs 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.
enable_safety_checkerbooleanIf set to true, the safety checker will be enabled.
prompt_expansion_moderequiredstringHow much effort to spend rewriting the prompt before generation. 'balanced' returns in about a second. 'quality' spends up to ~30s on a richer prompt.

Output

FieldTypeDescription
seedintegerBase seed for reproducing the generation.
videoThe generated video
timingsTiming breakdown in seconds. 'inference' is the DiT denoising time on the GPU backend. Null on routes that do not report backend timings.
expanded_promptThe prompt after expansion, as sent to the model. Null when prompt expansion was disabled, left the prompt unchanged, or was performed internally by MiniMax's hosted API.