TRStart creating
Menu

LCM Diffusion

Run SDXL at the speed of light

Input

Fields marked * are required. Review the price before generating.

The URL of the image to use as a starting point for the generation.

Uploading a file needs an account. Create accountJPEG, PNG, WebP · up to 25 MB

The prompt to use for generating the image. Be as descriptive as possible for best results.

The size of the generated image.

The number of images to generate.

Additional settings
Tips and requirements

The negative prompt to use.Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution).

The number of inference steps to perform.

Tips and requirements

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.

determines how much the generated image resembles the initial image

The same seed and the same prompt given to the same version of Stable Diffusion will output the same image every time.

If set to true, the prompt will be expanded with additional prompts.

The format of the generated image.

Tips and requirements

If set to true, the aspect ratio of the generated image will be preserved even if the image size is too large. However, if the image is not a multiple of 32 in width or height, it will be resized to the nearest multiple of 32. By default, this snapping to the nearest multiple of 32 will not preserve the aspect ratio. Set crop_output to True, to crop the output to the proper aspect ratio after generating.

If set to true, the output cropped to the proper aspect ratio after generating.

Price$0.28 / run

You sign up first. Your settings are kept.

API code for this input

Complete the required fields and fix input errors to see API code.

How to use LCM Diffusion

Getting started

Explore broad composition and color ideas before refining small details.

Review your result

Inspect flat textures, softened edges and whether prompt expansion added unwanted objects.

Inputs and settings

The official starting point is six steps with guidance_scale 1.5. Raywake supports 1–32 steps and up to eight images.

Image-to-image requires image_url; inpainting also requires mask_url. Both add strength, while text generation starts from prompt alone.

We use analytics cookies. Privacy policy