falImage to videoComing soon

bytedance/lynx

Name: bytedance/lynx
Brand: fal

bytedance/lynx is an image to video tool from fal that runs in the background and returns video. 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: video
Longest queue wait: 3600s
Run deadline: 3600s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`image_url` required	URL or file	—	The URL of the subject image to be used for video generation
`prompt` required	text	—	Text prompt to guide video generation
`negative_prompt`	text	Bright tones, overexposed, blurred background, static, subtitles, style, works, paintings, images, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards	Negative prompt to guide what should not appear in the generated video
`num_inference_steps`	number (whole) 1 to 75	50	Number of inference steps for sampling. Higher values give better quality but take longer.
`seed`	number (whole)	—	Random seed for reproducibility. If None, a random seed is chosen.
`resolution`	one of 480p, 580p, 720p	720p	Resolution of the generated video (480p, 580p, or 720p)
`aspect_ratio`	one of 16:9, 9:16, 1:1	16:9	Aspect ratio of the generated video (16:9, 9:16, or 1:1)
`ip_scale`	number 0 to 2	1	Identity preservation scale. Controls how closely the generated video preserves the subject's identity from the reference image.
`strength`	number 0 to 2	1	Reference image scale. Controls the influence of the reference image on the generated video.
`frames_per_second`	number (whole) 5 to 30	16	Frames per second of the generated video. Must be between 5 to 30.
`guidance_scale`	number 1 to 20	5	Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.
`guidance_scale_2`	number 0 to 10	2	Image guidance scale. Controls how closely the generated video follows the reference image. Higher values increase adherence to the reference image but may decrease quality.
`num_frames`	number (whole) 9 to 81	81	Number of frames in the generated video. Must be between 9 to 100.

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/lynx",
    "input": {
      "image_url": "https://storage.googleapis.com/falserverless/example_inputs/lynx/example_in.png",
      "prompt": "A person carves a pumpkin on a porch in the evening. The camera captures their upper body as they draw a face with a marker, carefully cut along the lines, then…"
    }
  }'