falText to imageComing soon

fal-ai/omnigen-v2

Name: fal-ai/omnigen-v2
Brand: fal

fal-ai/omnigen-v2 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

$0.195 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 or edit an image. Use specific language like 'Add the bird from image 1 to the desk in image 2' for better results.
`input_image_urls`	list	[]	URLs of input images to use for image editing or multi-image generation. Support up to 3 images.
`image_size`	JSON	square_hd	The size of the generated image.
`num_inference_steps`	number (whole) 20 to 50	50	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.
`text_guidance_scale`	number 1 to 8	5	The Text Guidance scale controls how closely the model follows the text prompt. Higher values make the model stick more closely to the prompt.
`image_guidance_scale`	number 1 to 3	2	The Image Guidance scale controls how closely the model follows the input images. For image editing: 1.3-2.0, for in-context generation: 2.0-3.0
`negative_prompt`	text	(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar	Negative prompt to guide what should not be in the image.
`cfg_range_start`	number 0 to 1	0	CFG range start value.
`cfg_range_end`	number 0 to 1	1	CFG range end value.
`scheduler`	one of euler, dpmsolver	euler	The scheduler to use for the diffusion process.
`num_images`	number (whole) 1 to 4	1	The number of images to generate.
`output_format`	one of jpeg, png	jpeg	The format of the generated 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": "fal",
    "model": "fal-ai/omnigen-v2",
    "input": {
      "prompt": "Make the dress blue"
    }
  }'