GET

/v1/schemas/fal/video/fal-ai/ltx-2.3-22b/reference-video-to-video/lora

Accept:

kind inputactivity videohash c0bb9709…extracted Jul 6, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `bbeb121e5b785fdf8e146f59907e913096246dd6ea16e0ec73083dc73f16467c` { "fetchedAt": 1783331098, "extractorVersion": "1", "verifiedAt": null }

Request body

42 properties · 3 required · 2 $defs

property	type	description	constraints
video_url*	string	The URL of the video to reference.
prompt*	string	The prompt to generate the video from.
loras*	LoRAInput[]	The LoRAs to use for the generation.
video_strength	number	Video conditioning strength. Lower values represent more freedom given to the model to change the video content.	0 ≤ n ≤ 1 · default: 1
image_url	string	An optional URL of an image to use as the first frame of the video.	nullable
generate_audio	boolean	Whether to generate audio for the video.	default: true
enable_prompt_expansion	boolean	Whether to enable prompt expansion.	default: true
seed	integer	The seed for the random number generator.	nullable
audio_strength	number	Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.	0 ≤ n ≤ 1 · default: 1
use_multiscale	boolean	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.	default: true
audio_modality_scale	number	The modality scale for the audio. Controls the ratio between video and audio modalities.	0 ≤ n ≤ 10 · default: 3
video_cfg_scale	number	The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.	1 ≤ n ≤ 20 · default: 3
enable_safety_checker	boolean	Whether to enable the safety checker.	default: true
acceleration	enum	The acceleration level to use.	none \| regular \| high \| full · default: "regular"
video_modality_scale	number	The modality scale for the video. Controls the ratio between video and audio modalities.	0 ≤ n ≤ 10 · default: 3
video_rescaling_scale	number	The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.	0 ≤ n ≤ 1 · default: 0.7
preprocessor	enum	The preprocessor to use for the generation.	depth \| canny \| pose \| none · default: "none"
use_restart_sampling	boolean	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.	default: false
num_frames	integer	The number of frames to generate.	9 ≤ n ≤ 481 · default: 121
num_inference_steps	integer	The number of inference steps to use.	8 ≤ n ≤ 50 · default: 40
distill_lora_second_pass_scale	number	The scale of the distill LoRA to use for the second and subsequent passes.	0 ≤ n ≤ 1 · default: 0.5
fps	number	The frames per second of the generated video.	1 ≤ n ≤ 60 · default: 24
scheduler	enum	The scheduler to use.	ltx2 \| linear_quadratic \| beta · default: "ltx2"
video_stg_scale	number	The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.	0 ≤ n ≤ 20 · default: 0
negative_prompt	string	The negative prompt to generate the video from.	default: "news broadcast, 3d animation, c…
match_video_length	boolean	When enabled, the number of frames will be calculated based on the video duration and FPS. When disabled, use the specified num_frames.	default: true
audio_cfg_scale	number	The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.	1 ≤ n ≤ 20 · default: 7
audio_rescaling_scale	number	The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.	0 ≤ n ≤ 1 · default: 0.7
video_output_type	enum	The output type of the generated video.	X264 (.mp4) \| VP9 (.webm) \| PRORES4444 (.mov) \| GIF (.gif) · default: "X264 (.mp4)"
video_write_mode	enum	The write mode of the generated video.	fast \| balanced \| small · default: "balanced"
distill_lora_first_pass_scale	number	The scale of the distill LoRA to use for the first pass. Set to 0 to disable.	0 ≤ n ≤ 1 · default: 0.2
video_size	ImageSize \| enum	The size of the generated video.	default: "auto"
camera_lora	enum	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.	dolly_in \| dolly_out \| dolly_left \| dolly_right \| jib_up \| jib_down · +2 more · default: "none"
camera_lora_scale	number	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.	0 ≤ n ≤ 1 · default: 1
audio_stg_scale	number	The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.	0 ≤ n ≤ 20 · default: 0
video_quality	enum	The quality of the generated video.	low \| medium \| high \| maximum · default: "high"
audio_url	string	An optional URL of an audio to use as the audio for the video. If not provided, any audio present in the input video will be used.	nullable
end_image_url	string	The URL of the image to use as the end of the video.	nullable
sync_mode	boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the request history.	default: false
gradient_estimation_gamma	number	The gamma of gradient estimation during denoising. Set to 0 to disable.	0 ≤ n ≤ 10 · default: 2
ic_lora_type	enum	The IC LoRA type to use for the generation.	match_preprocessor \| union \| detailer \| none · default: "union"
match_input_fps	boolean	When true, match the output FPS to the input video's FPS instead of using the default target FPS.	default: true

Types

2 $defs

ImageSizeobject

height	integer	The height of the generated image.	0 < n ≤ 14142 · default: 512
width	integer	The width of the generated image.	0 < n ≤ 14142 · default: 512

LoRAInputobject

LoRA weight configuration.

scale	number	Scale factor for LoRA application (0.0 to 4.0).	0 ≤ n ≤ 4 · default: 1
path*	string	URL, HuggingFace repo ID (owner/repo) to lora weights.
weight_name	string	Name of the LoRA weight. Only used if `path` is a HuggingFace repository, and is only required when the repository contains multiple LoRA weights.	nullable

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/ltx-2.3-22b/reference-video-to-video/lora","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}