SDXL - Lightning Models

SDXL-Lightning is a lightning-fast text-to-image generation model. It can generate high-quality 1024px images in a few steps. Inference times are faster than regular sdxl models.

SDXL Lightning Model
Community Lightning Models

{
  "model_id": "lightning",
  "scheduler": "EulerDiscreteScheduler", //or DDIMScheduler
  "guidance_scale": 1,
  "num_inference_steps": 10,
  "seed": -1,
  "width": 1024,
  "height": 1024,
  "prompt": "a young girl smiling, curly hair, green eyes, photo, highly detailed",
  "samples": 2,
  "negative_prompt": ""
}

{
  "seed": 56738,
  "width": 1024,
  "height": 1024,
  "prompt": "futuristic fashion portrait shot of an albino female figure of color, skin, black with subtle white spots like a cheetah's coat, red irises and dilated black pupils, hair is vivid pink",
  "samples": 2,
  "model_id": "04b396d1-6d7f-4348-98c4-eabe73a3bed6",
  "scheduler": "DPMSolverMultistepSchedulerSDE",
  "guidance_scale": 1,
  "negative_prompt": "deformed anatomy",
  "num_inference_steps": 10
}

JSON Parameters

Parameter	Permissible values	Notes
model_id	`str`	model_id can be found in models page. Lightning models have the word Lightning in them.
prompt	`str, 75 tokens`	Check our Prompt Guide for tips
negative_prompt	`str, 75 tokens`	Check our Prompt Guide for tips
num_inference_steps	`int, [1-100]`	Lightning models provide best results with just 6-12 steps Ideal value 6-12
strength	`float, [0-1]`	Optional denoise strength
samples	`int, [1-4]`	Generates a maximum of 4 samples per API call
guidance_scale	`float, [1-20]`	Lightning models give best results at low guidance scale values. Ideal value 0.5-2.
width	`int`	Width in pixels. Lower than or equal to 1024 for best results
height	`int`	Height in pixels. Lower than or equal to 1024 for best results
seed	`int`	Controlling the seed can help you generate reproducible images
safety_checker	`boolean`	Checks for NSFW images and filters explicit images

Status

Your response will include a status.

If the status = SUCCESS, you will also have download_urls that will have the links to your generated image based on the number of samples you have entered. The maximum number of samples that can be generated is 4.
If the status = PENDING, you will receive a id. You can use the status endpoint to fetch your image using the id.
If the status = FAILURE, you will receive only an error message.

Endpoint:

https://api.imagepipeline.io/sdxl/text2image/v1/status/{{id}}

Pass the API-Key as the authorization in the header.