Stable diffusion xl (beta)

post

https://api.codefromanywhere.com/function/stableDiffusionXl

StabilityAI's flagship model

Recent Requests

Time	Status	User Agent
Retrieving recent requests…

Loading…

Body Params

prompt

string

required

Input prompt

Default value: An astronaut riding a rainbow unicorn

negative_prompt

string

Input Negative Prompt

image

string

Input image for img2img or inpaint mode

mask

string

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

width

number

Width of output image

Default value: 1024

height

number

Height of output image

Default value: 1024

num_outputs

number

Number of images to output.

Default value: 1

scheduler

string

scheduler Allowed values:DDIM, DPMSolverMultistep, HeunDiscrete, KarrasDPM, K_EULER_ANCESTRAL, K_EULER, PNDM

Default value: K_EULER

num_inference_steps

number

Number of denoising steps

Default value: 50

guidance_scale

number

Scale for classifier-free guidance

Default value: 7.5

prompt_strength

number

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

Default value: 0.8

seed

number

Random seed. Leave blank to randomize the seed

refine

string

Which refine style to use

Allowed values:no_refiner, expert_ensemble_refiner, base_image_refiner

Default value: no_refiner

high_noise_frac

number

For expert_ensemble_refiner, the fraction of noise to use

Default value: 0.8

refine_steps

number

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

apply_watermark

boolean

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 value:

lora_scale

number

LoRA additive scale. Only applicable on trained models.

Default value: 0.6

Response

200Standard response