falImage to imageComing soon

fal-ai/fast-sdxl-controlnet-canny/inpainting

Name: fal-ai/fast-sdxl-controlnet-canny/inpainting
Brand: fal

fal-ai/fast-sdxl-controlnet-canny/inpainting is an image to image tool from fal 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.

Price pending

Pricing

Price pending.

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
`prompt` required	text	—	The prompt to use for generating the image. Be as descriptive as possible for best results.
`control_image_url` required	text	—	The URL of the control image.
`controlnet_conditioning_scale`	number 0 to 1	0.5	The scale of the controlnet conditioning.
`image_url` required	URL or file	—	The URL of the image to use as a starting point for the generation.
`mask_url` required	URL or file	—	The URL of the mask to use for inpainting.
`negative_prompt`	text		The negative prompt to use.Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution).
`image_size`	JSON	null	The size of the generated image. Leave it none to automatically infer from the control image.
`num_inference_steps`	number (whole) 1 to 70	35	The number of inference steps to perform.
`guidance_scale`	number 0 to 20	7.5	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.
`strength`	number 0.01 to 1	0.95	determines how much the generated image resembles the initial image
`seed`	number (whole)	null	The same seed and the same prompt given to the same version of Stable Diffusion will output the same image every time.
`num_images`	number (whole) 1 to 8	1	The number of images to generate.
`loras`	JSON	[]	The list of LoRA weights to use.
`embeddings`	JSON	[]	The list of embeddings to use.
`safety_checker_version`	one of v1, v2	v1	The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.
`expand_prompt`	true or false	false	If set to true, the prompt will be expanded with additional prompts.
`format`	one of jpeg, png	jpeg	The format of the generated image.
`request_id`	text		An id bound to a request, can be used with response to identify the request itself.

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": "fal",
    "model": "fal-ai/fast-sdxl-controlnet-canny/inpainting",
    "input": {
      "prompt": "Ice fortress, aurora skies, polar wildlife, twilight",
      "control_image_url": "https://fal-cdn.batuhan-941.workers.dev/files/rabbit/MiN_j3St9B8esJleCZKMU.jpeg",
      "image_url": "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png",
      "mask_url": "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
    }
  }'