usamaehsan/ernie-image-turbo-fast-h100

ERNIE-Image-Turbo tuned for cost: FP8 + torch.compile + lean forward, 1-8 steps, optional hires refine

Public

361 runs

Run usamaehsan/ernie-image-turbo-fast-h100 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
prompt	string		Text prompt
aspect_ratio	None	1:1	Width:height
resolution	None	1024	Long side in pixels
num_inference_steps	integer	2 Min: 1 Max: 4	Denoising steps
seed	integer		Random seed
output_format	None	jpg	None
output_quality	integer	90 Min: 1 Max: 100	None
dump_compile_cache	boolean	False	Maintenance: compile every size and return the torch.compile cache

{
  "type": "object",
  "title": "Input",
  "required": [
    "prompt"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "x-order": 4,
      "description": "Random seed"
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "x-order": 0,
      "description": "Text prompt"
    },
    "resolution": {
      "enum": [
        768,
        1024
      ],
      "type": "integer",
      "title": "resolution",
      "description": "Long side in pixels",
      "default": 1024,
      "x-order": 2
    },
    "aspect_ratio": {
      "enum": [
        "1:1",
        "4:5",
        "5:4",
        "3:4",
        "4:3",
        "2:3",
        "3:2",
        "9:16",
        "16:9",
        "1:2",
        "2:1",
        "5:7",
        "7:5",
        "3:5",
        "5:3",
        "4:7",
        "7:4",
        "9:21",
        "21:9",
        "1:3",
        "3:1"
      ],
      "type": "string",
      "title": "aspect_ratio",
      "description": "Width:height",
      "default": "1:1",
      "x-order": 1
    },
    "output_format": {
      "enum": [
        "jpg",
        "png",
        "webp"
      ],
      "type": "string",
      "title": "output_format",
      "description": "An enumeration.",
      "default": "jpg",
      "x-order": 5
    },
    "output_quality": {
      "type": "integer",
      "title": "Output Quality",
      "default": 90,
      "maximum": 100,
      "minimum": 1,
      "x-order": 6
    },
    "dump_compile_cache": {
      "type": "boolean",
      "title": "Dump Compile Cache",
      "default": false,
      "x-order": 7,
      "description": "Maintenance: compile every size and return the torch.compile cache"
    },
    "num_inference_steps": {
      "type": "integer",
      "title": "Num Inference Steps",
      "default": 2,
      "maximum": 4,
      "minimum": 1,
      "x-order": 3,
      "description": "Denoising 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"
}