A comprehensive list of changes published to the API reference

7th May, 2025

​
Features

Added support for Character Mode in the request body of POST /pub/v1/generations to make the character settings more easier and flexible.

mode is an enum field and can take values:

  • flexible - Ideal for stylized characters and image generations.
  • balanced - Ideal for creating realistic images and more.
  • strong - Character similarity is most important.

weight and enable_facelock are deprecated and will be removed in the future.

​
APIs

  • Added mode to the request body of character in POST /pub/v1/generations.
    Example request
    [
  {
    "character": {
      "character_id": "char_001",
      "mode": "balanced"
    }
  }
]

6th March, 2025

​
Features

Support for Video Anyone Generation.

​
APIs

You can use either a generated image’s media_id or an uploaded image asset’s asset_id as the input image identifier media_id for video generation, eliminating the need to re-upload images as assets.

The input image must have an aspect ratio of either 3:5 or 5:3

  • video_anyone generation support in the request body of POST /pub/v1/generations.
Example request
[
  {
    "video_anyone": {
      "media_id": "ast_xxxxxxxx",
      "prompt": "A person riding a bicycle",
      "duration": 5
    }
  }
]

4th December, 2024

​
Features

Added support for ControlNet/Pose Lock on Flux Models and Styles.

​
APIs

  • Head over to List Controlnets API GET /pub/v1/controlnets?type=flux and you will see new controlnets for the Flux model.
Response
      "data": [
          {
              "base_model": "flux",
              "name": "Canny"
          },
          {
              "base_model": "flux",
              "name": "Depth"
          }
      ]
  • Use the control_net in the request body of POST /pub/v1/generations with flux models and styles to generate images with ControlNet/Pose Lock

When using control_net with Flux Model or Style, please note that the output image’s aspect ratio will automatically match the aspect ratio of the ControlNet reference image (specified by asset_id), regardless of any other aspect ratio settings.

resize_mode and control_mode are not supported for control_net when used with Flux Model or Style.

[
    {
        "batch_size": 1,
        "model": "Flux",
        "prompt": {
            "negative": "",
            "positive": "a man looking into the camera."
        },
        "control_net": {
            "name": "Canny",
            "asset_id": "ast_xxxxxxxx"
        }
    }
]

8th November, 2024

​
Features

Added support for Flux Generation.

​
APIs

  • flux model support in the request body of POST /pub/v1/generations.
    Example request
    [
  {
    "aspect_ratio": "4:5",
    "batch_size": 1,
    "model": "Flux",
    "prompt": {
      "negative": "",
      "positive": "a man looking into the camera."
    }
  }
]
  • flux style in the request body of POST /pub/v1/generations.
    Example request
    [
  {
    "aspect_ratio": "4:5",
    "batch_size": 1,
    "style_detail": {
      "name": "Black & White",
      "base_model": "flux"
    },
    "prompt": {
      "negative": "",
      "positive": "a man looking into the camera."
    }
  }
]
  • Added style_detail field along with style in response body of POST /pub/v1/generations.
    Example response
    {
  "data": {
      "credits_remaining": 100,
      "generation_id": "gen_001",
      "media": [
          {
              "dim": {
                  "height": 1280,
                  "width": 1024
              },
              "id": "img_01",
              "status": "initiated",
              "style": "Black & White",
              "style_detail": {
                  "base_model": "flux",
                  "name": "Black & White"
              },
              "type": "image"
          }
      ],
      "result": "initiated"
  },
  "err": {}
}
  • type support in the query param of GET /pub/v1/models, GET /pub/v1/styles, GET /pub/v1/controlnets and GET /pub/v1/loras.
    Example
    GET /pub/v1/styles?type=flux

4th September, 2024

​
Features

Added support for Narrator Generation.

​
APIs

  • Added narrator to the request body of POST /pub/v1/generations.

    Example request
    "narrator": {
  "image_asset_id": "ast_xxxxxxxx",
  "video_asset_id": "ast_xxxxxxxx",
  "audio_asset_id": "ast_xxxxxxxx",
  "script": "Thank you for trying Narrator",
  "voice": "Rachel"
}

  • Changes to the response in the following existing endpoints:

    1. Generate Media POST /pub/v1/generations
      • images renamed to media
      • image_size renamed to dim under data→media
      • type added under data→media
    {
  "data": [
    {
      "created_at": 1675732000,
      "generation_id": "gen_01",
      "media": [
        {
          "id": "media_01",
          "dim": {
            "height": 512,
            "width": 512
          },
          "type": "image",
          "status": "success",
          "url": "object-url"
        }
      ]
    }
  ],
  "err": {},
  "pagination": {
    "page": 1,
    "page_size": 10,
    "total": 100
  }
}
    1. List Generations GET /pub/v1/generations
      • images renamed to media under data in response.
      • size renamed to dim under data→media in response.
      • type added under data→media in response
      • image_id changed to media_id in Query Parameter
    {
  "data": [
    {
      "created_at": 1675732000,
      "generation_id": "gen_01",
      "media": [
        {
          "id": "media_01",
          "dim": {
            "height": 512,
            "width": 512
          },
          "type": "image",
          "status": "success",
          "url": "object-url"
        }
      ]
    }
  ],
  "err": {},
  "pagination": {
    "page": 1,
    "page_size": 10,
    "total": 100
  }
}