falText to imageComing soon

fal-ai/z-image/turbo/tiling/lora

Name: fal-ai/z-image/turbo/tiling/lora
Brand: fal

fal-ai/z-image/turbo/tiling/lora is a text 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.

Priced by usage

Pricing

$0.0325 per megapixel. Each image_size preset counts as 1 MP, and a custom width × height rounds up to whole megapixels. Billed on num_images, default 1. The final charge comes from usage.

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 generate an image from.
`image_size`	JSON	square_hd	The size of the generated image. Use 'auto' to match the input image size (or 1024x1024 if no image).
`num_inference_steps`	number (whole) 1 to 8	8	The number of inference steps to perform.
`seed`	number (whole)	—	The same seed and the same prompt given to the same version of the model will output the same image every time.
`num_images`	number (whole) 1 to 4	1	The number of images to generate.
`output_format`	one of jpeg, png, webp	png	The format of the generated image.
`acceleration`	one of none, regular, high	regular	The acceleration level to use.
`enable_prompt_expansion`	true or false	false	Whether to enable prompt expansion. Note: this will increase the price by 0.0025 credits per request.
`image_url`	URL or file	—	URL of an image for image-to-image or inpainting. When provided without mask_image_url, performs image-to-image; with mask_image_url, performs inpainting.
`mask_image_url`	text	—	URL of a mask image for inpainting. White regions are regenerated, black regions are preserved. Requires image_url.
`strength`	number … to 1	0.6	How much to transform the input image. Only used when image_url is provided.
`tile_size`	number (whole) 32 to 256	128	Tile size in latent space. Must be even (divisible by 2) for patchification. Automatically capped to the generated image dimensions on tiled axes. (64 = 512px, 128 = 1024px, 256 = 2048px).
`tile_stride`	number (whole) 16 to 128	64	Tile stride in latent space. Must be even (divisible by 2). Automatically capped to half the effective tile size. (32 = 256px, 64 = 512px, 128 = 1024px).
`tiling_mode`	one of both, horizontal, vertical	both	Tiling direction: 'both' (omnidirectional), 'horizontal' (left-right only), 'vertical' (top-bottom only).
`loras`	JSON	[]	List of LoRA weights to apply (maximum 3).

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/z-image/turbo/tiling/lora",
    "input": {
      "prompt": "A hyper-realistic, high-resolution 4k texture of an ancient weathered brick wall heavily overgrown with lush green moss and soft lichens. The bricks are aged,…"
    }
  }'