falText to imageComing soon

krea/v2/medium/turbo/text-to-image

Name: krea/v2/medium/turbo/text-to-image
Brand: fal

krea/v2/medium/turbo/text-to-image 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.

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	—	Text description of the image to generate.
`aspect_ratio`	one of 1:1, 4:3, 3:2, 16:9, 2.35:1, 4:5, 2:3, 9:16	1:1	Aspect ratio of the generated image.
`creativity`	one of raw, low, medium, high	medium	Controls how loosely the model interprets the prompt. Higher values produce more creative results that may drift from the prompt; lower values stay closer to the prompt.
`seed`	number (whole)	—	Random seed for reproducible generation.
`image_style_references`	JSON	[]	Optional list of reference images that guide the style of the generated image. At most 10 entries.
`styles`	JSON	[]	Optional list of Krea preset styles (LoRA-based) to apply. Each entry references a style by `id` from the Krea styles catalog. At most 10 entries.
`moodboards`	JSON	[]	Optional moodboard to apply to the generation. Krea currently accepts at most one moodboard per request. Each entry references a moodboard by `id` (UUID).

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": "krea/v2/medium/turbo/text-to-image",
    "input": {
      "prompt": "A Van Gogh-tinged Provençal farmhouse under starry nights."
    }
  }'