anotherjesse/ait-sd – API reference

anotherjesse / ait-sd

Compile Stable Diffusion using AIT for A100

Public
24 runs

Run anotherjesse/ait-sd 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
weights	string		Url for weights
width	integer (enum)	512 Options: 384, 512, 640, 768, 896, 1024	Width to bake into model
height	integer (enum)	512 Options: 384, 512, 640, 768, 896, 1024	Height to bake into model
num_outputs	integer	1 Min: 1 Max: 4	Number of images to bake into model
seed	integer	4896	Seed for random number generator
use_fp16_acc	boolean	True	Use FP16 accumulation
convert_conv_to_gemm	boolean	True	Convert convolutions to gemm

{
  "type": "object",
  "title": "Input",
  "required": [
    "weights"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "default": 4896,
      "x-order": 4,
      "description": "Seed for random number generator"
    },
    "width": {
      "enum": [
        384,
        512,
        640,
        768,
        896,
        1024
      ],
      "type": "integer",
      "title": "width",
      "description": "Width to bake into model",
      "default": 512,
      "x-order": 1
    },
    "height": {
      "enum": [
        384,
        512,
        640,
        768,
        896,
        1024
      ],
      "type": "integer",
      "title": "height",
      "description": "Height to bake into model",
      "default": 512,
      "x-order": 2
    },
    "weights": {
      "type": "string",
      "title": "Weights",
      "x-order": 0,
      "description": "Url for weights"
    },
    "num_outputs": {
      "type": "integer",
      "title": "Num Outputs",
      "default": 1,
      "maximum": 4,
      "minimum": 1,
      "x-order": 3,
      "description": "Number of images to bake into model"
    },
    "use_fp16_acc": {
      "type": "boolean",
      "title": "Use Fp16 Acc",
      "default": true,
      "x-order": 5,
      "description": "Use FP16 accumulation"
    },
    "convert_conv_to_gemm": {
      "type": "boolean",
      "title": "Convert Conv To Gemm",
      "default": true,
      "x-order": 6,
      "description": "Convert convolutions to gemm"
    }
  }
}

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"
}