falImage to imageComing soon

fal-ai/ip-adapter-face-id

Name: fal-ai/ip-adapter-face-id
Brand: fal

fal-ai/ip-adapter-face-id 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
`model_type`	one of 1_5-v1, 1_5-v1-plus, 1_5-v2-plus, SDXL-v1, SDXL-v2-plus, 1_5-auraface-v1	1_5-v1	The model type to use. 1_5 is the default and is recommended for most use cases.
`prompt` required	text	—	The prompt to use for generating the image. Be as descriptive as possible for best results.
`face_image_url`	text	—	An image of a face to match. If an image with a size of 640x640 is not provided, it will be scaled and cropped to that size.
`face_images_data_url`	text	—	URL to zip archive with images of faces. The images embedding will be averaged to create a more accurate face id.
`negative_prompt`	text	blurry, low resolution, bad, ugly, low quality, pixelated, interpolated, compression artifacts, noisey, grainy	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).
`seed`	number (whole)	—	The same seed and the same prompt given to the same version of Stable Diffusion will output the same image every time.
`guidance_scale`	number 0 to 16	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.
`num_inference_steps`	number (whole) 1 to 200	50	The number of inference steps to use for generating the image. The more steps the better the image will be but it will also take longer to generate.
`num_samples`	number (whole) 1 to 4	4	The number of samples for face id. The more samples the better the image will be but it will also take longer to generate. Default is 4.
`width`	number (whole) 512 to 1024	512	The width of the generated image.
`height`	number (whole) 512 to 1024	512	The height of the generated image.
`face_id_det_size`	number (whole) 64 to 640	640	The size of the face detection model. The higher the number the more accurate the detection will be but it will also take longer to run. The higher the number the more likely it will fail to find a face as well. Lower it if you are having trouble finding a face in the image.
`base_1_5_model_repo`	text	SG161222/Realistic_Vision_V4.0_noVAE	The URL to the base 1.5 model. Default is SG161222/Realistic_Vision_V4.0_noVAE
`base_sdxl_model_repo`	text	SG161222/RealVisXL_V3.0	The URL to the base SDXL model. Default is SG161222/RealVisXL_V3.0

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/ip-adapter-face-id",
    "input": {
      "prompt": "Man cyberpunk, synthwave night city, futuristic, high quality, highly detailed, high resolution, sharp, hyper realistic, extremely detailed"
    }
  }'