code-and-cakes / sdxl-yuki

  • Public
  • 452 runs
  • L40S
  • SDXL fine-tune

Run code-and-cakes/sdxl-yuki with an API

Input schema

maskuri

Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.

seedinteger

Random seed. Leave blank to randomize the seed

imageuri

Input image for img2img or inpaint mode

widthinteger

Width of output image

Default
1024
heightinteger

Height of output image

Default
1024
promptstring

Input prompt

Default
"An astronaut riding a rainbow unicorn"
refinestring

Which refine style to use

Default
"no_refiner"
schedulerstring

scheduler

Default
"K_EULER"
lora_scalenumber

LoRA additive scale. Only applicable on trained models.

Default
0.6
Maximum
1
num_outputsinteger

Number of images to output.

Default
1
Minimum
1
Maximum
4
refine_stepsinteger

For base_image_refiner, the number of steps to refine, defaults to num_inference_steps

guidance_scalenumber

Scale for classifier-free guidance

Default
7.5
Minimum
1
Maximum
50
apply_watermarkboolean

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.

Default
true
high_noise_fracnumber

For expert_ensemble_refiner, the fraction of noise to use

Default
0.8
Maximum
1
negative_promptstring

Input Negative Prompt

prompt_strengthnumber

Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image

Default
0.8
Maximum
1
num_inference_stepsinteger

Number of denoising steps

Default
50
Minimum
1
Maximum
500
disable_safety_checkerboolean

Disable safety checker for generated images. This feature is only available through the API. See https://replicate.com/docs/how-does-replicate-work#safety

Output schema

Type
uri[]