jackieyaung/sd-1.5-architect-fastest

Fast and cost-efficient SD 1.5 (LCM) model for interior and architectural image generation.

Public

23 runs

Run jackieyaung/sd-1.5-architect-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 for img2img
prompt	string	modern interior design, minimalist, 8k, photorealistic	Input prompt
negative_prompt	string	worst quality, low quality, normal quality, lowres, monochrome, grayscale, watermark, text, signature, bad anatomy, bad perspective	Negative prompt
strength	number	0.5 Max: 1	Strength of the img2img transformation (0.0 to 1.0)
guidance_scale	number	1.5 Min: 1 Max: 3	Guidance scale (CFG). For LCM, keep this low (1.0 - 2.0)
num_inference_steps	integer	6 Min: 2 Max: 20	Number of inference steps. For LCM, 4-8 is usually sufficient.
seed	integer		Random seed. Leave blank to randomize the seed
output_format	None	png	Format of the output image
output_quality	integer	90 Max: 100	Quality of the output image (0-100)

{
  "type": "object",
  "title": "Input",
  "required": [
    "image"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "x-order": 6,
      "description": "Random seed. Leave blank to randomize the seed"
    },
    "image": {
      "type": "string",
      "title": "Image",
      "format": "uri",
      "x-order": 0,
      "description": "Input image for img2img"
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "default": "modern interior design, minimalist, 8k, photorealistic",
      "x-order": 1,
      "description": "Input prompt"
    },
    "strength": {
      "type": "number",
      "title": "Strength",
      "default": 0.5,
      "maximum": 1,
      "minimum": 0,
      "x-order": 3,
      "description": "Strength of the img2img transformation (0.0 to 1.0)"
    },
    "output_format": {
      "enum": [
        "webp",
        "jpg",
        "png"
      ],
      "type": "string",
      "title": "output_format",
      "description": "Format of the output image",
      "default": "png",
      "x-order": 7
    },
    "guidance_scale": {
      "type": "number",
      "title": "Guidance Scale",
      "default": 1.5,
      "maximum": 3,
      "minimum": 1,
      "x-order": 4,
      "description": "Guidance scale (CFG). For LCM, keep this low (1.0 - 2.0)"
    },
    "output_quality": {
      "type": "integer",
      "title": "Output Quality",
      "default": 90,
      "maximum": 100,
      "minimum": 0,
      "x-order": 8,
      "description": "Quality of the output image (0-100)"
    },
    "negative_prompt": {
      "type": "string",
      "title": "Negative Prompt",
      "default": "worst quality, low quality, normal quality, lowres, monochrome, grayscale, watermark, text, signature, bad anatomy, bad perspective",
      "x-order": 2,
      "description": "Negative prompt"
    },
    "num_inference_steps": {
      "type": "integer",
      "title": "Num Inference Steps",
      "default": 6,
      "maximum": 20,
      "minimum": 2,
      "x-order": 5,
      "description": "Number of inference steps. For LCM, 4-8 is usually sufficient."
    }
  }
}

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"
}