GET

/v1/schemas/fal/video/minimax/h3/reference-to-video/lora

Accept:

kind inputactivity videohash 730ce3a8…extracted Nov 7, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `ec9ad0b3c0d90d3f16cfb48016119e5bb1130e90f5e7114b320fbaf50e978cd2` { "fetchedAt": 1794027603, "extractorVersion": "1", "verifiedAt": null }

Request body

13 properties · 2 required · 1 $defs

property	type	description	constraints
loras*	LoRAInput[]	List of LoRA adapters to apply to the transformer.	items ≥ 1 · items ≤ 3
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.	length ≥ 1 · length ≤ 50000
reference_video_urls	string[]	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.	items ≤ 3
resolution	enum	The resolution of the generated video. 480P and 768P are native generation modes; 2K and 4K upscale a 768P base result.	480P \| 768P \| 2K \| 4K · default: "2K"
reference_image_urls	string[]	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.	items ≤ 9
reference_audio_urls	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…	items ≤ 3
sync_mode	boolean	Return the generated video as base64 instead of a CDN URL.	default: false
duration	integer	The duration of the video in seconds.	5 ≤ n ≤ 15 · default: 5
enable_safety_checker	boolean	If set to true, the safety checker will be enabled.	default: true
prompt_expansion_mode	string	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.	nullable
target_audio_url	string	Optional URL of an audio clip at least 2 seconds long (maximum 15 MB) to pin to the generated soundtrack. Cannot be combined with reference audio. Longer clips are trimmed to the generated video's length, keeping the beginning; shorter clips are padded with silence. The clip is resampled to 32 kHz stereo and replaces the output soundtrack without changing playback speed. Accepts an HTTP(S) URL or a base64 data URI.	length ≥ 1 · nullable
aspect_ratio	enum	The aspect ratio of the generated video.	adaptive \| 21:9 \| 16:9 \| 4:3 \| 1:1 \| 3:4 · +1 more · default: "adaptive"
seed	integer	Random seed. A random seed is selected when omitted.	nullable

Types

1 $defs

LoRAInputobject

A single LoRA adapter to apply to the transformer.

path*	string	URL or HuggingFace repo id (owner/repo) of the LoRA weights.
weight_name	string	Name of the LoRA weight file. Only used when `path` is a HuggingFace repo and it holds more than one LoRA.	nullable
scale	number	Strength of the LoRA (0.0 to 4.0).	0 ≤ n ≤ 4 · default: 1

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"minimax/h3/reference-to-video/lora","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}