falVideo to videoComing soon

fal-ai/ltx-2.3-22b/extend-video

Name: fal-ai/ltx-2.3-22b/extend-video
Brand: fal

fal-ai/ltx-2.3-22b/extend-video 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 generate the video from.
`video_url` required	URL or file	—	The URL of the video to extend.
`end_image_url`	URL or file	—	The URL of the image to use as the end of the extended video.
`num_frames`	number (whole) 9 to 481	121	The number of frames to generate.
`video_size`	JSON	auto	The size of the generated video.
`generate_audio`	true or false	true	Whether to generate audio for the video.
`use_multiscale`	true or false	true	Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.
`match_input_fps`	true or false	true	When true, match the output FPS to the input video's FPS instead of using the default target FPS.
`fps`	number 1 to 60	24	The frames per second of the generated video.
`num_inference_steps`	number (whole) 8 to 50	40	The number of inference steps to use.
`video_cfg_scale`	number 1 to 20	3	The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.
`video_stg_scale`	number 0 to 20	0	The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.
`video_rescaling_scale`	number 0 to 1	0.7	The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.
`video_modality_scale`	number 0 to 10	3	The modality scale for the video. Controls the ratio between video and audio modalities.
`audio_cfg_scale`	number 1 to 20	7	The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.
`audio_stg_scale`	number 0 to 20	0	The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.
`audio_rescaling_scale`	number 0 to 1	0.7	The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.
`audio_modality_scale`	number 0 to 10	3	The modality scale for the audio. Controls the ratio between video and audio modalities.
`gradient_estimation_gamma`	number 0 to 10	2	The gamma of gradient estimation during denoising. Set to 0 to disable.
`use_restart_sampling`	true or false	false	Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video.
`scheduler`	one of ltx2, linear_quadratic, beta	ltx2	The scheduler to use.
`acceleration`	one of none, regular, high, full	regular	The acceleration level to use.
`camera_lora`	one of dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down, static, none	none	The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.
`camera_lora_scale`	number 0 to 1	1	The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.
`negative_prompt`	text	news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static	The negative prompt to generate the video from.
`seed`	number (whole)	—	The seed for the random number generator.
`enable_prompt_expansion`	true or false	true	Whether to enable prompt expansion.
`video_output_type`	one of X264 (.mp4), VP9 (.webm), PRORES4444 (.mov), GIF (.gif)	X264 (.mp4)	The output type of the generated video.
`video_quality`	one of low, medium, high, maximum	high	The quality of the generated video.
`video_write_mode`	one of fast, balanced, small	balanced	The write mode of the generated video.
`distill_lora_first_pass_scale`	number 0 to 1	0.2	The scale of the distill LoRA to use for the first pass. Set to 0 to disable.
`distill_lora_second_pass_scale`	number 0 to 1	0.5	The scale of the distill LoRA to use for the second and subsequent passes.
`extend_direction`	one of forward, backward	forward	Direction to extend the video. 'forward' extends from the end of the video, 'backward' extends from the beginning.
`num_context_frames`	number (whole) 0 to 121	25	The number of frames to use as context for the extension.
`video_strength`	number 0 to 1	1	Video conditioning strength. Lower values represent more freedom given to the model to change the video content.
`audio_strength`	number 0 to 1	1	Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.
`end_image_strength`	number 0 to 1	1	The strength of the end image to use for the video generation.

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-2.3-22b/extend-video",
    "input": {
      "prompt": "Continue the scene naturally, maintaining the same style and motion.",
      "video_url": "https://v3b.fal.media/files/b/0a8824b1/sdm0KfmenrlywesfzY1Y1_if6euPp1.mp4"
    }
  }'