You're looking at a specific version of this model. Jump to the model overview.
stimqq /minimax-h3-lite:ac8653aa
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| prompt |
string
|
What should happen in the clip. Refer to reference images as Picture 1, Picture 2, ... and to audio clips as Audio 1, Audio 2, ...
|
|
| api_key |
string
|
Your apimodels.app API key (create one at https://apimodels.app/console/api-keys). The generation is billed to your apimodels.app balance: 480p $0.01/s, 768p $0.02/s; failed generations are not charged.
|
|
| duration |
integer
|
5
Min: 1 Max: 15 |
Length in whole seconds.
|
| resolution |
None
|
768p
|
Output resolution.
|
| aspect_ratio |
None
|
16:9
|
16:9 (landscape), 9:16 (portrait) or adaptive (follow the reference image).
|
| reference_images |
array
|
Up to 9 reference images (character, outfit, product, scene) to keep consistent in the clip.
|
|
| reference_audio |
array
|
Up to 3 audio clips (a voice line for lip-sync, or music to move to). Needs at least one reference image.
|
|
| first_frame |
string
|
Optional first frame. Used alone it acts as a reference image; together with last_frame it is first/last-frame mode, which cannot be combined with reference images or audio.
|
|
| last_frame |
string
|
Optional last frame. Requires first_frame.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}