simpletuner/advanced-trainer

Train practically any diffusion image/video/audio model with SimpleTuner.

Public

15 runs

License

GitHub

Run simpletuner/advanced-trainer 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
images	string		Zip or tar archive of training images. Not required if dataloader_json points to external data.
config_json	string		Training config: either a JSON string or path to config.json. Defaults to config/config.json if present.
dataloader_json	string		Multidatabackend config: either a JSON string or path to file. If not provided, auto-generated from images.
max_train_steps	integer		Override --max_train_steps for quicker Cog runs.
s3_bucket	string		S3-compatible bucket for publishing checkpoints (overrides config).
s3_region	string		S3 region (optional).
s3_endpoint_url	string		Custom S3 endpoint URL (for non-AWS providers like Backblaze B2, Cloudflare R2).
s3_base_path	string		Prefix inside the bucket (defaults to simpletuner/{job_id}).
s3_public_base_url	string		Public base URL to build shareable links (optional).
s3_access_key	string		S3 access key (leave blank to use IAM/instance roles).
s3_secret_key	string		S3 secret key (leave blank to use IAM/instance roles).
hub_model_id	string		HuggingFace Hub repo ID (e.g., 'username/my-lora') - overrides config.
hf_token	string		Hugging Face token for model downloads and Hub publishing.
lycoris_config	string		LyCORIS config: either a JSON string or path to lycoris_config.json. Required when lora_type is 'lycoris'.
return_logs	boolean	True	Print the tail of debug.log to Cog output.

{
  "type": "object",
  "title": "Input",
  "properties": {
    "images": {
      "type": "string",
      "title": "Images",
      "format": "uri",
      "x-order": 0,
      "description": "Zip or tar archive of training images. Not required if dataloader_json points to external data."
    },
    "hf_token": {
      "type": "string",
      "title": "Hf Token",
      "format": "password",
      "x-order": 12,
      "writeOnly": true,
      "description": "Hugging Face token for model downloads and Hub publishing.",
      "x-cog-secret": true
    },
    "s3_bucket": {
      "type": "string",
      "title": "S3 Bucket",
      "x-order": 4,
      "nullable": true,
      "description": "S3-compatible bucket for publishing checkpoints (overrides config)."
    },
    "s3_region": {
      "type": "string",
      "title": "S3 Region",
      "x-order": 5,
      "nullable": true,
      "description": "S3 region (optional)."
    },
    "config_json": {
      "type": "string",
      "title": "Config Json",
      "x-order": 1,
      "description": "Training config: either a JSON string or path to config.json. Defaults to config/config.json if present."
    },
    "return_logs": {
      "type": "boolean",
      "title": "Return Logs",
      "default": true,
      "x-order": 14,
      "description": "Print the tail of debug.log to Cog output."
    },
    "hub_model_id": {
      "type": "string",
      "title": "Hub Model Id",
      "x-order": 11,
      "nullable": true,
      "description": "HuggingFace Hub repo ID (e.g., 'username/my-lora') - overrides config."
    },
    "s3_base_path": {
      "type": "string",
      "title": "S3 Base Path",
      "x-order": 7,
      "nullable": true,
      "description": "Prefix inside the bucket (defaults to simpletuner/{job_id})."
    },
    "s3_access_key": {
      "type": "string",
      "title": "S3 Access Key",
      "format": "password",
      "x-order": 9,
      "nullable": true,
      "writeOnly": true,
      "description": "S3 access key (leave blank to use IAM/instance roles).",
      "x-cog-secret": true
    },
    "s3_secret_key": {
      "type": "string",
      "title": "S3 Secret Key",
      "format": "password",
      "x-order": 10,
      "nullable": true,
      "writeOnly": true,
      "description": "S3 secret key (leave blank to use IAM/instance roles).",
      "x-cog-secret": true
    },
    "lycoris_config": {
      "type": "string",
      "title": "Lycoris Config",
      "x-order": 13,
      "description": "LyCORIS config: either a JSON string or path to lycoris_config.json. Required when lora_type is 'lycoris'."
    },
    "dataloader_json": {
      "type": "string",
      "title": "Dataloader Json",
      "x-order": 2,
      "description": "Multidatabackend config: either a JSON string or path to file. If not provided, auto-generated from images."
    },
    "max_train_steps": {
      "type": "integer",
      "title": "Max Train Steps",
      "x-order": 3,
      "description": "Override --max_train_steps for quicker Cog runs."
    },
    "s3_endpoint_url": {
      "type": "string",
      "title": "S3 Endpoint Url",
      "x-order": 6,
      "nullable": true,
      "description": "Custom S3 endpoint URL (for non-AWS providers like Backblaze B2, Cloudflare R2)."
    },
    "s3_public_base_url": {
      "type": "string",
      "title": "S3 Public Base Url",
      "x-order": 8,
      "nullable": true,
      "description": "Public base URL to build shareable links (optional)."
    }
  }
}

Output schema

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

Schema

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