falImage to imageComing soon

bytedance/seedream/v5/lite/edit

Name: bytedance/seedream/v5/lite/edit
Brand: fal

bytedance/seedream/v5/lite/edit 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.

Priced by usage

Pricing

$0.0455 per image. 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 text prompt used to edit the image
`image_size`	JSON	auto_2K	The size of the generated image. Custom dimensions within the provider's pixel and aspect limits are sent unchanged. Other sizes use compatible scaling. The provider's native pixel range is 2560x1440 to 4096x4096, with aspect ratio between 1/16 and 16.
`num_images`	number (whole) 1 to 6	1	Number of separate model generations to be run with the prompt.
`max_images`	number (whole) 1 to 15	1	Maximum images per generation in sequential mode. Ignored when sequential generation is disabled. Combined input references and outputs per generation cannot exceed 15.
`output_format`	one of jpeg, png	jpeg	The file format of the generated images.
`watermark`	true or false	false	Whether to add the provider's visible watermark.
`image_passthrough`	true or false	false	Preserve original reference and output image bytes, formats, and dimensions without resizing or re-encoding.
`sequential_image_generation`	one of auto, disabled	—	Generate related images with `auto`, or one image per generation with `disabled`. When omitted, values of `max_images` above one enable `auto`.
`image_urls` required	URLs or files	—	List of URLs of input images for editing. By default, when more than 10 references are provided, only the last 10 are used. With image_passthrough enabled, all references are preserved, supporting up to 14; combined references and outputs per generation cannot exceed 15.

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": "bytedance/seedream/v5/lite/edit",
    "input": {
      "prompt": "Replace the product in Figure 1 with that in Figure 2. Seamlessly render logo in Figure 3 into the product design, in frosted glass texture. Remove any extra…",
      "image_urls": [
        "<image_urls>"
      ]
    }
  }'