falVideo to videoComing soon

fal-ai/ltx-2.3-quality/outpaint

Name: fal-ai/ltx-2.3-quality/outpaint
Brand: fal

fal-ai/ltx-2.3-quality/outpaint is a video 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: 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 guide the outpainted video generation.
`video_url` required	URL or file	—	The source video to spatially outpaint.
`aspect_ratio`	one of 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21	16:9	Target aspect ratio for the outpainted video. Choose a different ratio than the input video to extend the frame cleanly, e.g. use 16:9 for a 4:3 source.
`output_resolution`	one of 480p, 720p, 1080p	720p	Output resolution tier. 480p is faster, 720p is the default balance, and 1080p gives a larger canvas when it fits LTX limits.
`resolution`	JSON	landscape_16_9	Legacy exact target canvas size. For new requests, prefer aspect_ratio with output_resolution; this field remains supported for backwards compatibility.
`source_scale`	number 0.25 to 1	1	Scale of the source video inside the target canvas before outpainting. 1.0 uses the largest source size that fits the target canvas, which is recommended for true aspect-ratio outpainting such as 4:3 to 16:9. Lower values create a zoom-out border around the source and are less stable.
`video_strength`	number 0 to 1	1	Strength of the IC-LoRA video guide for the original content. Higher values preserve the source video more strongly inside the outpainted canvas.
`num_frames`	number (whole) 9 to 481	121	The number of frames to generate.
`frames_per_second`	number 1 to 60	24	Frames per second of the generated video.
`num_inference_steps`	number (whole) 8 to 30	15	Number of inference steps. Defaults to 15 and can be increased up to 30.
`guidance_scale`	number 1 to 20	1	Classifier-free guidance scale. The default is tuned for fast, high-quality generation.
`generate_audio`	true or false	true	Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.
`negative_prompt`	text	color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards	The negative prompt to steer generation away from.
`seed`	number (whole)	—	Random seed for reproducibility. If None, a random seed is chosen.
`enable_prompt_expansion`	true or false	true	Whether to enable prompt expansion.
`video_quality`	one of low, medium, high, maximum	high	The quality preset of the generated video.
`video_write_mode`	one of fast, balanced, small	balanced	The write mode of the generated video.

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/ltx-2.3-quality/outpaint",
    "input": {
      "prompt": "A cinematic wide shot of the same scene, extending the environment naturally beyond the original frame.",
      "video_url": "<video_url>"
    }
  }'