ReplicateImage to imageComing soon

stability-ai/stable-diffusion-3

Name: stability-ai/stable-diffusion-3
Brand: Replicate

stability-ai/stable-diffusion-3 is an image to image tool from Replicate that runs in the background and returns images. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Priced by usage

Pricing

$0.0455 per image.

Limits

Runs: In the background
Returns: image
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`cfg`	number 0 to 20	3.5	The guidance scale tells the model how similar the output should be to the prompt.
`seed`	number (whole)	—	Set a seed for reproducibility. Random by default.
`image`	URL or file	—	Input image for image to image mode. The aspect ratio of your output will match this image.
`steps`	number (whole) 1 to 28	28	Number of steps to run the sampler for.
`prompt`	text
`aspect_ratio`	JSON	1:1	The aspect ratio of your output image. This value is ignored if you are using an input image.
`output_format`	JSON	webp	Format of the output images
`output_quality`	number (whole) 0 to 100	90	Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.
`negative_prompt`	text		Negative prompts do not really work in SD3. Using a negative prompt will change your output in unpredictable ways.
`prompt_strength`	number 0 to 1	0.85	Prompt strength (or denoising strength) when using image to image. 1.0 corresponds to full destruction of information in image.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "replicate",
    "model": "stability-ai/stable-diffusion-3",
    "input": {}
  }'