simpletuner/minimax-h3 | API reference

Public

10 runs

Run simpletuner/minimax-h3 with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

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
train_data	string		ZIP or tar containing either paired audio triplets or captioned videos
trigger_word	string		Optional instance prompt used instead of per-video captions
max_train_steps	integer	1000 Min: 1 Max: 5000	Optimizer steps
checkpoint_interval	integer	250 Min: 10 Max: 1000	Save every N steps
lora_rank	None	16	LoRA rank
learning_rate	number	0.00006 Min: 0.000001 Max: 0.0005	Learning rate
resolution	None	480	Video pixel-area resolution
video_frames	None	39	Frames sampled from video datasets
seed	integer	42	Training seed

{
  "type": "object",
  "title": "Input",
  "required": [
    "train_data"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "default": 42,
      "minimum": 0,
      "x-order": 8,
      "description": "Training seed"
    },
    "lora_rank": {
      "enum": [
        8,
        16,
        32,
        64
      ],
      "type": "integer",
      "title": "lora_rank",
      "description": "LoRA rank",
      "default": 16,
      "x-order": 4
    },
    "resolution": {
      "enum": [
        256,
        384,
        480
      ],
      "type": "integer",
      "title": "resolution",
      "description": "Video pixel-area resolution",
      "default": 480,
      "x-order": 6
    },
    "train_data": {
      "type": "string",
      "title": "Train Data",
      "format": "uri",
      "x-order": 0,
      "description": "ZIP or tar containing either paired audio triplets or captioned videos"
    },
    "trigger_word": {
      "type": "string",
      "title": "Trigger Word",
      "default": "",
      "x-order": 1,
      "description": "Optional instance prompt used instead of per-video captions"
    },
    "video_frames": {
      "enum": [
        5,
        22,
        39
      ],
      "type": "integer",
      "title": "video_frames",
      "description": "Frames sampled from video datasets",
      "default": 39,
      "x-order": 7
    },
    "learning_rate": {
      "type": "number",
      "title": "Learning Rate",
      "default": 6e-05,
      "maximum": 0.0005,
      "minimum": 1e-06,
      "x-order": 5,
      "description": "Learning rate"
    },
    "max_train_steps": {
      "type": "integer",
      "title": "Max Train Steps",
      "default": 1000,
      "maximum": 5000,
      "minimum": 1,
      "x-order": 2,
      "description": "Optimizer steps"
    },
    "checkpoint_interval": {
      "type": "integer",
      "title": "Checkpoint Interval",
      "default": 250,
      "maximum": 1000,
      "minimum": 10,
      "x-order": 3,
      "description": "Save every N steps"
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "string",
  "title": "Output",
  "format": "uri"
}