Blog
Replicate
STABLE

SDXL

A text-to-image generative AI model that creates beautiful images

Inputs
Prompt
Input prompt
Apply Watermark
Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.
Disable Safety Checker
Disable safety checker for generated images. This feature is only available through the API. See https://replicate.com/docs/how-does-replicate-work#safety
Guidance Scale
Scale for classifier-free guidance
Height
Height of output image
High Noise Frac
For expert_ensemble_refiner, the fraction of noise to use
Image
Input image for img2img or inpaint mode
Lora Scale
LoRA additive scale. Only applicable on trained models.
Mask
Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.
Negative Prompt
Input Negative Prompt
Num Inference Steps
Number of denoising steps
Num Outputs
Number of images to output.
Prompt Strength
Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
refine
Which refine style to use
Refine Steps
For base_image_refiner, the number of steps to refine, defaults to num_inference_steps
Replicate Weights
Replicate LoRA weights to use. Leave blank to use the default weights.
scheduler
scheduler
Seed
Random seed. Leave blank to randomize the seed
Width
Width of output image
Outputs
Urls
URLs of the images