infery
← All models

Ltx 2.3 Quality

ltx-2.3-quality-reference-video-to-video

Video generationby Lightricks

Generate high-quality video with audio from reference video, text and images using LTX-2.3

Example

Details

Accepts
video

Pricing

Price
0.301 cr / megapixel

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seedRandom seed for reproducibility. If None, a random seed is chosen.
promptrequiredstringThe prompt to guide generation.
strengthnumberSampler denoise strength for reference-video-to-video. With preserve_original_video on, this is the video-to-video amount: lower values keep more of the original video's pixels (e.g. 0.5 = keep ~50%), 1.0 fully regenerates. Without preserve_original_video it only trims the denoise schedule.
image_urlOptional reference image for style/character anchoring. This is the FIRST-frame keyframe.
sync_modebooleanIf True, the media is returned as a data URI inline in the response. Useful for short-lived requests and tests.
video_urlrequiredstringThe URL of the reference video that supplies motion/structure.
num_framesintegerThe number of output frames to generate. This IC-LoRA endpoint caps the resolution x frames volume for stability (~150 frames at 720p-class; more at smaller sizes). A request above the budget returns a 422 — reduce num_frames or use a smaller resolution.
resolutionThe size of the generated video. In direct-control mode (skip_control_preprocess with control_video_url), 'auto' follows the source video size/aspect up to the LTX limits and explicit sizes are honored with 64px alignment. In the built-in control estimation mode, the output stays near the official c…
end_image_urlOptional last-frame keyframe image. When set, the look/appearance is anchored to this image at the end of the clip. Useful for shots where the camera travels to a different place than the start image. Requires image_url.
mid_image_urlOptional middle-frame keyframe image. When set, the look/appearance is anchored to this image around the middle of the clip (in addition to image_url at the start), so the appearance follows a moving camera instead of drifting. Requires image_url.
video_qualitystringenum: low, medium, high, maximumThe quality preset of the generated video.
generate_audiobooleanWhether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.
guidance_scalenumberClassifier-free guidance scale. The default is tuned for fast, high-quality generation.
video_strengthnumberVideo conditioning strength. Lower values give the model more freedom to change the reference video motion/structure.
negative_promptstringThe negative prompt to steer generation away from.
video_write_modestringenum: fast, balanced, smallThe write mode of the generated video.
control_video_url
frames_per_secondnumberFrames per second of the generated video.
num_inference_stepsintegerNumber of inference steps. Defaults to 15 and can be increased up to 30.
enable_safety_checkerbooleanWhether to enable the safety checker.
enable_prompt_expansionbooleanWhether to enable prompt expansion.
preserve_original_videobooleanTrue video-to-video: the base video_url is used as the generation's starting point, while control_video_url still drives the structure. The amount of the original preserved is controlled by `strength` (denoise): lower `strength` keeps more of the original video's pixels. Requires skip_control_prepro…
skip_control_preprocessbooleanSkip the built-in control estimation (depth / edge / pose) and use control_video_url directly as the control signal. Requires control_video_url; ignored if it is not set. With resolution='auto', the output follows the source video size/aspect up to the LTX limits. Explicit resolutions are honored an…

Output

FieldTypeDescription
seedintegerThe seed actually used for generation.
videoThe generated video.
promptstringThe prompt used for generation (after any expansion).