Available now

Stable Diffusion XL: text to image

Stable Diffusion XL creates images from a prompt, reworks an image you upload and repaints a masked area, with your own LoRA weights if you have them.

Model ID

Input

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

Be as descriptive as possible for best results.

Example prompt. Edit it or write your own.

Additional settings

The number of inference steps to perform.

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

The list of LoRA weights to use.

The list of embeddings to use.

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

Price$0.60 / run

You sign up first. Your settings are kept.

About this model

Overview

Stable Diffusion XL gives one to eight images per run in square, portrait or landscape presets. A negative prompt lists what to keep out, and the step count and guidance scale (CFG) trade detail against how strictly it follows the prompt.

Two more modes start from your image: image to image redraws it with a strength setting, inpainting changes only the area under your mask. Every mode accepts LoRA weights and embeddings by link.

What you can build

  • Images in a style you trained as a LoRA
  • Sketches or photos redrawn in a new style
  • Objects removed or replaced inside a marked area
  • Large batches of variations for picking favorites

Prompting tips

  • Use the negative prompt for what keeps showing up: blur, extra fingers, text or a color you do not want.
  • Start from the default guidance scale of 7.5; very high values make images harsh.
  • In image to image, a strength near 0.5 keeps the layout; values near 1 replace most of the picture.

What to check

Check anatomy, repeated objects and whether a LoRA overwhelms the intended composition.

Inputs

  • Prompt (required): The prompt to use for generating the image. Be as descriptive as possible for best results.
  • Negative Prompt (optional): 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).
  • Image Size (optional): The size of the generated image. Options: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • Number of Inference Steps (optional): The number of inference steps to perform. From 1 to 50.
  • Seed (optional): The same seed and the same prompt given to the same version of Stable Diffusion will output the same image every time.
  • Guidance scale (CFG) (optional): 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. From 0 to 20.
  • Number of Images (optional): The number of images to generate. From 1 to 8.
  • Loras (optional): The list of LoRA weights to use.
  • Embeddings (optional): The list of embeddings to use.
  • Enable Prompt Expansion (optional): If set to true, the prompt will be expanded with additional prompts.
  • Format (optional): The format of the generated image. Options: jpeg, png.

Output and limits

  • Image sizes: Square HD (1024×1024), Square (512×512), Portrait 4:3 (768×1024), Portrait 16:9 (576×1024), Landscape 4:3 (1024×768), Landscape 16:9 (1024×576).
  • Up to 8 images per run.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • up to: $0.60 / run