sd1.5
1min
Models supported
sd1.5-inpainting, sd1.5-img2img
POST https://{base-url}/sd1.5-{model}
Request body
# Prompt to render, eg. "Stormtrooper giving a lecture"
prompt: str
# Prompts to exclude, eg. "bad anatomy, bad hands, missing fingers"
# Default: None
negative_prompt: str
# Number of output images
# Default: 1
samples: int
# Type of scheduler.
# Options: ["DDIM", "DPM Multi", "DPM Single", "Euler a", "Euler", "Heun", "DPM2 a Karras", "DPM2 Karras", "LMS", "PNDM", "DDPM"]
# Default: DDIM
scheduler: enum
# Number of denoising steps.
# Default: 20; Max: 50
num_inference_steps: int
# Scale for classifier-free guidance
# Default: 7.5
guidance_scale: float
# Seed for image generation.
# Default: Random
seed: int
# How much to transform the reference image
# Default: 1; Range: 0 to 1
strength: float
# Input reference image URL, alternatively, use an image in base64 as shown below.
imageUrl: str
# Base64 encoding of the input reference image.
image: str
# Base64 encoding of the output image.
# Optional
# Default: false
base64: boolean
# Input mask image URL, alternatively, use an image in base64 as shown below. Only required for sd1.5-inpainting
maskUrl: str
# Base64 encoding of the mask image. Only required for sd1.5-inpainting.
mask: str


Updated 03 Jun 2023
Did this page help you?
Yes
No