usamaehsan/flux-kontext-fastest

FLUX.1 Kontext dev, int4 + turbo 8-step. Cheapest quality image edits on L40S.

Public

63 runs

Run usamaehsan/flux-kontext-fastest 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
image	string		Input image to edit
prompt	string	Remove the background	Edit instruction
width	integer	0 Max: 2048	Output width (0 = auto from input, ~1MP). Use 512 for cheapest edits
height	integer	0 Max: 2048	Output height (0 = auto from input, ~1MP). Use 512 for cheapest edits
num_inference_steps	integer	Min: 1 Max: 50	Steps. 8 is the Turbo LoRA sweet spot
guidance_scale	number	2.5 Max: 10	Guidance scale (Kontext default 2.5)
seed	integer		Random seed
output_format	None	jpg	Output image format. jpg is faster to encode and smaller

{
  "type": "object",
  "title": "Input",
  "required": [
    "image"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "x-order": 6,
      "description": "Random seed"
    },
    "image": {
      "type": "string",
      "title": "Image",
      "format": "uri",
      "x-order": 0,
      "description": "Input image to edit"
    },
    "width": {
      "type": "integer",
      "title": "Width",
      "default": 0,
      "maximum": 2048,
      "minimum": 0,
      "x-order": 2,
      "description": "Output width (0 = auto from input, ~1MP). Use 512 for cheapest edits"
    },
    "height": {
      "type": "integer",
      "title": "Height",
      "default": 0,
      "maximum": 2048,
      "minimum": 0,
      "x-order": 3,
      "description": "Output height (0 = auto from input, ~1MP). Use 512 for cheapest edits"
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "default": "Remove the background",
      "x-order": 1,
      "description": "Edit instruction"
    },
    "output_format": {
      "enum": [
        "jpg",
        "png"
      ],
      "type": "string",
      "title": "output_format",
      "description": "Output image format. jpg is faster to encode and smaller",
      "default": "jpg",
      "x-order": 7
    },
    "guidance_scale": {
      "type": "number",
      "title": "Guidance Scale",
      "default": 2.5,
      "maximum": 10,
      "minimum": 0,
      "x-order": 5,
      "description": "Guidance scale (Kontext default 2.5)"
    },
    "num_inference_steps": {
      "type": "integer",
      "title": "Num Inference Steps",
      "maximum": 50,
      "minimum": 1,
      "x-order": 4,
      "description": "Steps. 8 is the Turbo LoRA sweet spot"
    }
  }
}

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"
}