SandBaseSandBase
Start building
Use in agentLightricks models

Lightricks modelsvideo generation api

lightricks/ltx-2.3-quality/extend-video

Ltx 2.3 Quality Extend Video by Lightricks - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions.

Input
The prompt describing how the video should continue.
Optional keyframe image for the far end of the extension: the final frame for forward extension, or the new first frame for backward extension.
The URL of the video to extend.
The size of the generated video. 'auto' follows the source video size/aspect up to the LTX limits; the source is scaled to the final size in the stitched output. Sizes are 32px-aligned (e.g. 1920x1080 is delivered as 1888x1056). Higher resolutions reduce the maximum stable extension length; lower resolutions can run longer. Allowed values: auto, square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9.
Whether to generate new audio for the extension segment (crossfaded with the source audio at the seam). When disabled, the source video's own audio track is preserved and the extension stays silent.
120
Classifier-free guidance scale. The default is tuned for fast, high-quality generation. Range: 1 to 20.
830
Number of inference steps. Defaults to 15 and can be increased up to 30. Range: 8 to 30.
Random seed for reproducibility. If None, a random seed is chosen.
9121
The number of source frames used as context/overlap for the extension. Snapped down to the LTX temporal grid (8k+1) and clamped to the frames available in the source video. Range: 9 to 121.
The write mode of the generated video. Allowed values: fast, balanced, small.
The quality preset of the generated video. Allowed values: low, medium, high, maximum.
When enabled, the output FPS matches the source video's FPS (rounded to an integer and clamped to the supported range) instead of frames_per_second.
01
Conditioning strength of the source context frames. 1.0 keeps the overlap locked to the source for a seamless transition; lower values give the model more freedom. Range: 0 to 1.
9481
The number of frames to generate for the extension segment, including num_context_frames of overlap with the source video. The new content adds approximately (num_frames - num_context_frames) / frames_per_second seconds. The stable generation budget caps the resolution x frames volume: at 24 fps roughly 20s at 480p-class, 11s at 720p-class and 5s at 1080p-class; a request above the budget returns a 422 (lower num_frames or use a smaller resolution). Range: 9 to 481.
160
Frames per second of the generated video. Range: 1 to 60.
Direction to extend the video. 'forward' continues from the end of the video, 'backward' generates a new beginning. Allowed values: forward, backward.
01
Conditioning strength of the optional end keyframe. 1.0 = exact match, lower = more freedom for the model. Range: 0 to 1.
Idle

Example output — click Run to generate your own

API README

PRICED DRAFT — MANUAL REVIEW REQUIRED exact_model_mode: lightricks/ltx-2.3-quality/extend-video original_unit: Your request will cost $0.0024075 per megapixel of generated video data (width × height × num_frames), rounded up. Only the generated extension segment is billed — num_frames includes the context overlap, but your source video's own frames are never billed, even though the returned file contains the full stitched video. For example, if you extend a video at 1280 × 720 with num_frames = 121, the generated segment is ≈112 MP, and your request will cost $0.270. method: generated-extension megapixel price with image-size preset pixels result_base_price: 0.26964 result_price_formula: Math.ceil((((params.resolution ?? "landscape_16_9") == "square_hd" ? 1048576 : (params.resolution ?? "landscape_16_9") == "square" ? 262144 : ((params.resolution ?? "landscape_16_9") == "portrait_4_3" || (params.resolution ?? "landscape_16_9") == "landscape_4_3") ? 786432 : 921600) * (params.num_frames ?? 121)) / 1000000) * 0.0024075 review_status: pending; model remains disabled checked_at: 2026-08-16

Related Models

lightricks/ltx-2.3-quality/hdrLtx 2.3 Quality Hdr is Lightricks's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.lightricks/ltx-2.3-quality/image-to-videoLtx 2.3 Quality by Lightricks - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.lightricks/ltx-2.3-quality/text-to-videoLtx 2.3 Quality is Lightricks's text-to-video AI model. Turn written scripts and prompts into professional-quality video clips with realistic motion, lighting, and scene composition.lightricks/ltx-2-19b/distilled/extend-videoLtx 2 19b Distilled Extend Video by Lightricks - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions.lightricks/ltx-2-19b/distilled/extend-video/loraLtx 2 19b Distilled Extend Video is Lightricks's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.lightricks/ltx-2-19b/distilled/image-to-videoLtx 2 19b Distilled by Lightricks - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.lightricks/ltx-2-19b/distilled/image-to-video/loraLtx 2 19b Distilled Lora is Lightricks's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.lightricks/ltx-2-19b/distilled/text-to-videoLtx 2 19b Distilled is Lightricks's text-to-video AI model. Turn written scripts and prompts into professional-quality video clips with realistic motion, lighting, and scene composition.