falVideo to videoComing soon

fal-ai/ltxv-13b-098-distilled/extend

Name: fal-ai/ltxv-13b-098-distilled/extend
Brand: fal

fal-ai/ltxv-13b-098-distilled/extend 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.

Priced by usage

Pricing

$0.026 per second. Measured from the input file. The final charge comes from usage.

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	—	Text prompt to guide generation
`negative_prompt`	text	worst quality, inconsistent motion, blurry, jittery, distorted	Negative prompt for generation
`loras`	JSON	[]	LoRA weights to use for generation
`resolution`	one of 480p, 720p	720p	Resolution of the generated video.
`aspect_ratio`	one of 9:16, 1:1, 16:9, auto	auto	The aspect ratio of the video.
`seed`	number (whole)	—	Random seed for generation
`num_frames`	number (whole) 9 to 1441	121	The number of frames in the video.
`first_pass_num_inference_steps`	number (whole) 2 to 12	8	Number of inference steps during the first pass.
`second_pass_num_inference_steps`	number (whole) 2 to 12	8	Number of inference steps during the second pass.
`second_pass_skip_initial_steps`	number (whole) 1 to 11	5	The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes.
`frame_rate`	number (whole) 1 to 60	24	The frame rate of the video.
`expand_prompt`	true or false	false	Whether to expand the prompt using a language model.
`reverse_video`	true or false	false	Whether to reverse the video.
`enable_detail_pass`	true or false	false	Whether to use a detail pass. If True, the model will perform a second pass to refine the video and enhance details. This incurs a 2.0x cost multiplier on the base price.
`temporal_adain_factor`	number 0 to 1	0.5	The factor for adaptive instance normalization (AdaIN) applied to generated video chunks after the first. This can help deal with a gradual increase in saturation/contrast in the generated video by normalizing the color distribution across the video. A high value will ensure the color distribution is more consistent across the video, while a low value will allow for more variation in color distribution.
`tone_map_compression_ratio`	number 0 to 1	0	The compression ratio for tone mapping. This is used to compress the dynamic range of the video to improve visual quality. A value of 0.0 means no compression, while a value of 1.0 means maximum compression.
`constant_rate_factor`	number (whole) 0 to 51	29	The constant rate factor (CRF) to compress input media with. Compressed input media more closely matches the model's training data, which can improve motion quality.
`video` required	JSON	—	Video to be extended.

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/ltxv-13b-098-distilled/extend",
    "input": {
      "prompt": "Woman walking on a street in Tokyo",
      "video": {}
    }
  }'