MiniMax H3 Reference to Video LoRA

h3-reference-to-video-lora

Video generationby MiniMax

References into video with synchronized audio using MiniMax H3

Example

Prices in credits (1 credit = $0.01).

Field	Type	Description
seed	—	Random seed. A random seed is selected when omitted.
lorasrequired	array	List of LoRA adapters to apply to the transformer.
promptrequired	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.
duration	integer	The duration of the video in seconds.
sync_mode	boolean	Return the generated video as base64 instead of a CDN URL.
resolution	stringenum: 480P, 768P, 2K, 4K	The resolution of the generated video. 480P and 768P are native generation modes; 2K and 4K upscale a 768P base result.
aspect_ratio	stringenum: adaptive, 21:9, 16:9, 4:3, 1:1, 3:4…	The aspect ratio of the generated video.
reference_audio_urls	array
reference_image_urls	array	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_video_urls	array	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.
enable_safety_checker	boolean	If set to true, the safety checker will be enabled.
prompt_expansion_mode	—	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.

Field	Type	Description
video	—	The generated video
expanded_prompt	—	The 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.