Lightricks

This page is auto-generated from model configurations. Last updated: 2026-11-02.

This reference lists all available Lightricks video generation models and their parameters. Use these parameter names when calling the Generation API.

• LTX 2.3 Quality Render to Real
• LTX-2 Fast
• LTX-2 Pro
• LTX-2 Retake
• LTX-2.3 Fast
• LTX-2.3 Pro
• LTX-2.3 Pro Audio to Video
• LTX-2.3 Pro Extend Video
• LTX-2.3 Pro Retake
• LTX-2.5 Alpha Gen
• LTX-2.5 Clean Plate
• LTX-2.5 Colorization
• LTX-2.5 Day to Night
• LTX-2.5 Deblur
• LTX-2.5 Decompression
• LTX-2.5 Distilled Cinemagraph
• LTX-2.5 Distilled Water Simulation
• LTX-2.5 Fast
• LTX-2.5 Fast Audio to Video
• LTX-2.5 Full Cinemagraph
• LTX-2.5 Full Water Simulation
• LTX-2.5 Layout to Render
• LTX-2.5 Pro
• LTX-2.5 Pro Audio to Video
• LTX-2.5 Reference Sheet
• LTX-2.5 Refine Details
• LTX-2.5 Restore
• LTX-2.5 Slow Motion

---

LTX 2.3 Quality Render to Real

Transform 3D/CG/game renders into photorealistic video with optional first-frame anchoring.

Model ID: model_ltx-2-3-quality-render-to-real

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-3-quality-render-to-real/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
video	file	Yes	-	-	-	-	The 3D, CG, or game render you want to make look photorealistic.
image	file	No	-	-	-	-	An optional photo to set the realistic look of the opening frame. The rest of the video follows from it.
prompt	string	No	-	-	-	-	Describe the photorealistic result you want.
negativePrompt	string	No	-	-	-	-	Things to steer the result away from unwanted artifacts, styles, or defects. Comes pre-filled with common ones you can edit.
intensity	string	No	strong-v2	-	-	light, strong, strong-v2	How hard to push the render toward realism. Light keeps more of the original render’s look; Strong pushes further; Strong V2 is the newest, improved version.
resolution	string	No	720p	-	-	480p, 720p	The output quality (measured on the shorter side), keeping your source’s proportions. 720p supports clips up to ~6s; 480p up to ~15s. Higher resolution costs more.
numFrames	number	No	121	1	361	-	The total number of frames in the output. The video’s length is this divided by the frame rate (for example, 121 frames at 24 fps is about 5 seconds). More frames cost more.
framesPerSecond	number	No	24	1	60	-	How many frames play per second. Higher values look smoother.
enableDetailRefine	boolean	No	false	-	-	-	Adds a second pass for a sharper, higher-detail result. This doubles the width and height (four times the pixels), so it’s slower and costs about 4× as much.
detailRefineStrength	number	No	0.75	0	1	-	How much the refine pass reworks the image. Higher values regenerate more detail. Only applies when Detail Refine is on.
generateAudio	boolean	No	true	-	-	-	Includes a soundtrack in the returned video. On by default.
enablePromptExpansion	boolean	No	false	-	-	-	Automatically expands your prompt into a richer description before generating. The “3DREAL” trigger is always kept.
numInferenceSteps	number	No	15	8	30	-	How many refinement passes the model makes (8-30). More can improve quality but take longer.
guidanceScale	number	No	1	0	20	-	How closely the result follows your prompt. Higher values stick to it more strictly.
videoQuality	string	No	high	-	-	low, medium, high, maximum	The overall quality preset for the output video.
videoWriteMode	string	No	balanced	-	-	fast, balanced, small	How the video file is saved: Fast prioritizes speed, Small prioritizes a smaller file, Balanced sits between.
seed	number	No	-	0	-	-	A number that makes results repeatable. Reusing the same seed and settings produces the same video; leave it empty for a different result each time.

LTX-2 Fast

Ideal for rapid ideation and mobile workflows. Perfect for creators who need instant feedback, real-time previews, or high-throughput content.

Model ID: model_ltx-2-fast

Capabilities: txt2video, img2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-fast/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Text prompt describing the video to generate
image	file	No	-	-	-	-	Input image for image-to-video generation
resolution	string	No	1080p	-	-	1080p, 2k, 4k	Resolution quality of the generated video
duration	number	No	6	-	-	6, 8, 10, 12, 14, 16, 18, 20	Duration of the video in seconds
generateAudio	boolean	No	false	-	-	-	Generate audio for the video

LTX-2 Pro

Delivers high visual fidelity with fast turnaround. Great for daily content creation, marketing teams, and iterative creative workflows.

Model ID: model_ltx-2-pro

Capabilities: txt2video, img2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-pro/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Text prompt describing the video to generate
image	file	No	-	-	-	-	Input image for image-to-video generation
resolution	string	No	1080p	-	-	1080p, 2k, 4k	Resolution quality of the generated video
duration	number	No	6	-	-	6, 8, 10	Duration of the video in seconds
generateAudio	boolean	No	false	-	-	-	Generate audio for the video

LTX-2 Retake

Model ID: model_ltx-2-retake

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-retake/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
video	file	Yes	-	-	-	-	Input video to edit
prompt	string	Yes	-	-	-	-	Text prompt describing the edit
mode	string	No	replace_video	-	-	replace_audio, replace_video, replace_audio_and_video	Mode of operation
startTime	number	No	0	0	-	-	Start time of the edit in seconds
duration	number	No	6	2	16	-	Duration of the edited section in seconds

LTX-2.3 Fast

Speed-optimized LTX-2.3 video generation. Generates videos with synchronized audio faster than real-time — ideal for rapid prototyping, mobile workflows, and high-volume production.

Model ID: model_ltx-2-3-fast

Capabilities: txt2video, img2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-3-fast/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Text prompt describing the video to generate
startImage	file	No	-	-	-	-	First frame image for image-to-video generation
endImage	file	No	-	-	-	-	End frame for interpolation (requires first frame). Video interpolates between first and last frame.
resolution	string	No	1080p	-	-	1080p, 2k, 4k	Video resolution. Durations longer than 10 seconds only at 1080p with 24 or 25 FPS.
duration	number	No	6	-	-	6, 8, 10, 12, 14, 16, 18, 20	Duration of the video in seconds
aspectRatio	string	No	16:9	-	-	16:9, 9:16	Aspect ratio of the generated video
fps	number	No	25	-	-	24, 25, 48, 50	Frame rate in frames per second
cameraMotion	string	No	none	-	-	none, dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down, static, focus_shift	Camera motion effect to apply to the generated video
generateAudio	boolean	No	true	-	-	-	Generate synchronized audio for the video

LTX-2.3 Pro

High-fidelity LTX-2.3 video generation. Produces higher visual quality than LTX 2.3 Fast. Supports text-to-video, image-to-video with optional end frame interpolation.

Model ID: model_ltx-2-3-pro

Capabilities: txt2video, img2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-3-pro/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Text prompt describing the video to generate
startImage	file	No	-	-	-	-	First frame image for image-to-video.
endImage	file	No	-	-	-	-	Optional end frame for interpolation. Video interpolates between first and last frame.
resolution	string	No	1080p	-	-	1080p, 2k, 4k	Video resolution (audio_to_video, retake, extend are 1080p only)
duration	number	No	6	-	-	6, 8, 10	Duration of the video in seconds
aspectRatio	string	No	16:9	-	-	16:9, 9:16	Aspect ratio of the generated video
fps	number	No	25	-	-	24, 25, 48, 50	Frame rate in frames per second
cameraMotion	string	No	none	-	-	none, dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down, static, focus_shift	Camera motion effect to apply to the generated video
generateAudio	boolean	No	true	-	-	-	Generate synchronized audio for the video

LTX-2.3 Pro Audio to Video

Generate video driven by an audio file. Speech cadence controls pacing, musical energy influences motion. $0.10/sec via fal.ai.

Model ID: model_ltx-2-3-pro-audio-to-video

Capabilities: audio2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-3-pro-audio-to-video/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
audio	file	Yes	-	-	-	-	Audio file (2-20 seconds). Drives the video generation.
image	file	No	-	-	-	-	Optional image to use as the first frame. If not provided, prompt is required.
prompt	string	No	-	-	-	-	Text description of how the video should be generated. Required if image is not provided.
guidanceScale	number	No	5	1	50	-	Higher values make output follow the prompt more closely. Default 5 for text-only, 9 with image.

LTX-2.3 Pro Extend Video

Add duration to the beginning or end of a video using LTX 2.3 Pro. Extend existing clips with high-fidelity continuation.

Model ID: model_ltx-2-3-pro-extend-video

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-3-pro-extend-video/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
video	file	Yes	-	-	-	-	Input video to extend
prompt	string	Yes	-	-	-	-	Text prompt describing how the video should continue
duration	number	No	6	-	-	6, 8, 10	Duration of the video in seconds
extendMode	string	No	end	-	-	start, end	Where to add the new duration

LTX-2.3 Pro Retake

Re-generate a section of an existing video. Replace audio, video, or both with LTX 2.3 Pro. 1080p only.

Model ID: model_ltx-2-3-pro-retake

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-3-pro-retake/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
video	file	Yes	-	-	-	-	Input video to edit
prompt	string	Yes	-	-	-	-	Text prompt describing the edit
retakeMode	string	No	replace_audio_and_video	-	-	replace_audio, replace_video, replace_audio_and_video	What to replace in the section
startTime	number	No	0	0	-	-	Start time in seconds of section to edit
duration	number	No	2	2	-	-	Duration in seconds of section to edit (≥2s)

LTX-2.5 Alpha Gen

Generate a grayscale alpha matte, a mask that separates the subject from the background, from a video, for use in compositing and masking.

Model ID: model_ltx-2-5-alpha-gen

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-alpha-gen/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
referenceVideos	file_array	Yes	-	-	-	-	The source video to generate an alpha matte from, up to about 6.33 seconds (at 24 fps) and 100 MB. The output matches your video’s length, though it can be up to 0.3 seconds shorter, and keeps its size, scaled down to fit 1920×1088.
seed	number	No	-	0	2147483647	-	Random seed for reproducibility. Leave blank for random.

LTX-2.5 Clean Plate

Removes people from a video to produce a clean plate.

Model ID: model_ltx-2-5-clean-plate

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-clean-plate/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Describe the empty scene, without the people.
referenceVideos	file_array	Yes	-	-	-	-	The source video to transform. The output has the same length, rounded down to 8k+1 frames, up to 121 frames: an input of up to 5.33 s at 24 fps. The output keeps your video’s size, scaled down to fit 1920×1920. Up to 100 MB.
seed	number	No	-	0	2147483647	-	Random seed for reproducibility. Leave blank for random.

LTX-2.5 Colorization

Colorizes a black-and-white video.

Model ID: model_ltx-2-5-colorization

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-colorization/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Follow this template, filling in the <…> parts: “Reference shows <grayscale scene description>. Edited shows the same scene with natural colors restored. COLORIZE <vivid natural-color description>. Subject identity, framing, and background geometry are identical to the reference; only color information differs between reference and edited.”
referenceVideos	file_array	Yes	-	-	-	-	The source video to transform. The output has the same length, rounded down to 8k+1 frames, up to 121 frames: an input of up to 5.33 s at 24 fps. The output keeps your video’s size, scaled down to fit 1920×1920. Up to 100 MB.
seed	number	No	-	0	2147483647	-	Random seed for reproducibility. Leave blank for random.

LTX-2.5 Day to Night

Relights a daytime video as a night scene.

Model ID: model_ltx-2-5-day-to-night

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-day-to-night/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Describe the night look you want.
negativePrompt	string	No	daytime, bright sunlight, blue sky, overexposed	-	-	-	What to avoid in the video.
referenceVideos	file_array	Yes	-	-	-	-	The source video to transform. The output has the same length, rounded down to 8k+1 frames, up to 97 frames: an input of up to 4.33 s at 24 fps. The output keeps your video’s size, scaled down to fit 768×768. Up to 100 MB.
seed	number	No	-	0	2147483647	-	Random seed for reproducibility. Leave blank for random.

LTX-2.5 Deblur

Brings an out-of-focus video back into sharp focus.

Model ID: model_ltx-2-5-deblur

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-deblur/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Follow this template, filling in the <…> parts: “Reference shows <scene>, heavily out of focus with soft defocused blur and no fine detail. Edited shows the same scene in sharp focus with crisp detail and clean edges. DEBLUR <scene>. Subject identity, framing, and background geometry are identical to the reference; only focus and sharpness differ between reference and edited.”
referenceVideos	file_array	Yes	-	-	-	-	The source video to transform. The output has the same length, rounded down to 8k+1 frames, up to 121 frames: an input of up to 5.33 s at 24 fps. The output keeps your video’s size, scaled down to fit 1920×1920. Up to 100 MB.
seed	number	No	-	0	2147483647	-	Random seed for reproducibility. Leave blank for random.

LTX-2.5 Decompression

Removes compression artifacts from a video.

Model ID: model_ltx-2-5-decompression

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-decompression/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Follow this template, filling in the <…> parts: “Reference shows <scene>, heavily compressed with visible macroblocking, chroma bleed, and ringing artifacts. Edited shows the same scene restored to high quality with sharp detail, clean edges, and no compression artifacts. ENHANCE QUALITY <scene>. Subject identity, framing, and background geometry are identical to the reference; only compression artifacts and image quality differ between reference and edited.”
referenceVideos	file_array	Yes	-	-	-	-	The source video to transform. The output has the same length, rounded down to 8k+1 frames, up to 121 frames: an input of up to 5.33 s at 24 fps. The output keeps your video’s size, scaled down to fit 1920×1920. Up to 100 MB.
seed	number	No	-	0	2147483647	-	Random seed for reproducibility. Leave blank for random.

LTX-2.5 Distilled Cinemagraph

Animates an image into a smoothly looping cinemagraph.

Model ID: model_ltx-2-5-distilled-cinemagraph

Capabilities: img2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-distilled-cinemagraph/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Include the trigger CINEMAGRAPH_MOTION and “tripod locked-off static camera … seamless natural loop”.
image	file	Yes	-	-	-	-	The image to animate. The video takes the image’s size, scaled down to fit 1920×1920.
numFrames	number	No	25	9	121	-	Number of frames at 24 fps, in steps of 8 from 9.
seed	number	No	-	0	2147483647	-	Random seed for reproducibility. Leave blank for random.

LTX-2.5 Distilled Water Simulation

Adds simulated water to a dry scene video. Works best on scenes without people or animals.

Model ID: model_ltx-2-5-distilled-water-simulation

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-distilled-water-simulation/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Follow this template, filling in the <…> parts: “Reference shows <dry scene>. Edited shows the same scene with water added. ADD WATER <water description>. Subject identity, clothing, framing, and background geometry are identical to the reference; only water-related elements differ between reference and edited.”
referenceVideos	file_array	Yes	-	-	-	-	The source video to transform. The output has the same length, rounded down to 8k+1 frames, from 97 to 185 frames: an input of 4.04 to 8 s at 24 fps. The output keeps your video’s size, scaled down to fit 1920×1920. Up to 100 MB.
seed	number	No	-	0	2147483647	-	Random seed for reproducibility. Leave blank for random.

LTX-2.5 Fast

Speed-optimized LTX-2.5 video generation with synchronized audio. Up to 4K and 20 seconds; natively multi-shot, so one prompt can produce several connected shots.

Model ID: model_ltx-2-5-fast

Capabilities: txt2video, img2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-fast/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Text prompt describing the video to generate. LTX-2.5 is natively multi-shot: a prompt describing several connected shots produces them in one video.
image	file	No	-	-	-	-	Opening frame for image-to-video. Leave empty for text-to-video.
lastFrameImage	file	No	-	-	-	-	Closing frame for interpolation. Requires a first frame.
resolution	string	No	1080p	-	-	720p, 1080p, 1440p, 4k	Video resolution. Durations longer than 10 seconds are only available at 720p or 1080p with 24 or 25 FPS.
duration	number	No	6	-	-	6, 8, 10, 12, 14, 16, 18, 20	Duration of the video in seconds. 12–20s require 720p or 1080p at 24 or 25 FPS.
aspectRatio	string	No	auto	-	-	auto, 16:9, 9:16	Output orientation. Match Input follows the first frame and falls back to 16:9 for text-to-video.
fps	number	No	24	-	-	24, 25, 48, 50	Frame rate in frames per second. 48 and 50 FPS cap duration at 10 seconds.
cameraMotion	string	No	static	-	-	dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down, static, focus_shift	Optional camera motion preset applied to the generated video
generateAudio	boolean	No	true	-	-	-	Generate synchronized audio for the video

LTX-2.5 Fast Audio to Video

Generate a video driven by a soundtrack. Speech cadence and musical energy set the pacing. Fast variant, up to 4K and 20 seconds of audio.

Model ID: model_ltx-2-5-fast-audio-to-video

Capabilities: audio2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-fast-audio-to-video/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
audio	file	Yes	-	-	-	-	Soundtrack that drives the video. Its length becomes the video’s. Up to 20s at 720p/1080p, 10s at 1440p/4K.
prompt	string	No	-	-	-	-	What the video should show, or how the first frame should be animated. Required when no image is provided.
image	file	No	-	-	-	-	Optional opening frame. Required when no prompt is provided.
lastFrameImage	file	No	-	-	-	-	Closing frame for interpolation. Requires a first frame.
resolution	string	No	1080p	-	-	720p, 1080p, 1440p, 4k	Video resolution. Audio longer than 10 seconds is only available at 720p or 1080p.
aspectRatio	string	No	auto	-	-	auto, 16:9, 9:16	Output orientation. Match Input follows the first frame and falls back to 16:9 with no image.
fps	number	No	24	-	-	24, 25, 48, 50	Frame rate in frames per second
cameraMotion	string	No	static	-	-	dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down, static, focus_shift	Optional camera motion preset applied to the generated video

LTX-2.5 Full Cinemagraph

Animates an image into a smoothly looping cinemagraph.

Model ID: model_ltx-2-5-full-cinemagraph

Capabilities: img2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-full-cinemagraph/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Include the trigger CINEMAGRAPH_MOTION and “tripod locked-off static camera … seamless natural loop”.
negativePrompt	string	No	-	-	-	-	What to avoid in the video.
image	file	Yes	-	-	-	-	The image to animate. The video takes the image’s size, scaled down to fit 1920×1920.
numFrames	number	No	25	9	121	-	Number of frames at 24 fps, in steps of 8 from 9.
seed	number	No	-	0	2147483647	-	Random seed for reproducibility. Leave blank for random.

LTX-2.5 Full Water Simulation

Adds simulated water to a dry scene video. Works best on scenes without people or animals.

Model ID: model_ltx-2-5-full-water-simulation

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-full-water-simulation/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Follow this template, filling in the <…> parts: “Reference shows <dry scene>. Edited shows the same scene with water added. ADD WATER <water description>. Subject identity, clothing, framing, and background geometry are identical to the reference; only water-related elements differ between reference and edited.”
negativePrompt	string	No	-	-	-	-	What to avoid in the video.
referenceVideos	file_array	Yes	-	-	-	-	The source video to transform. The output has the same length, rounded down to 8k+1 frames, from 97 to 185 frames: an input of 4.04 to 8 s at 24 fps. The output keeps your video’s size, scaled down to fit 1920×1920. Up to 100 MB.
seed	number	No	-	0	2147483647	-	Random seed for reproducibility. Leave blank for random.

LTX-2.5 Layout to Render

Turns a 3D layout or playblast video into a finished, photoreal shot.

Model ID: model_ltx-2-5-layout-to-render

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-layout-to-render/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	One or two sentences describing the finished shot. Avoid the words “clay”, “3D” or “Unreal”.
referenceVideos	file_array	Yes	-	-	-	-	The source video to transform. The output has the same length, rounded down to 8k+1 frames, up to 241 frames: an input of up to 10.33 s at 24 fps. The output keeps your video’s size, scaled down to fit 1920×1088. Up to 100 MB.
firstFrameImage	file_array	No	-	-	-	-	Optional still of the intended final look, applied to the first frame. Strongly recommended for a close match.
seed	number	No	-	0	2147483647	-	Random seed for reproducibility. Leave blank for random.

LTX-2.5 Pro

High-fidelity LTX-2.5 video generation with synchronized audio. Higher visual quality than Fast, up to 4K. Natively multi-shot, with optional end-frame interpolation.

Model ID: model_ltx-2-5-pro

Capabilities: txt2video, img2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-pro/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Text prompt describing the video to generate. LTX-2.5 is natively multi-shot: a prompt describing several connected shots produces them in one video.
image	file	No	-	-	-	-	Opening frame for image-to-video. Leave empty for text-to-video.
lastFrameImage	file	No	-	-	-	-	Closing frame for interpolation. Requires a first frame.
resolution	string	No	1080p	-	-	720p, 1080p, 1440p, 4k	Video resolution. Pro supports 720p, 1080p, 1440p and 4K; duration is capped at 10 seconds at every resolution.
duration	number	No	6	-	-	6, 8, 10	Duration of the video in seconds. Pro caps at 10 seconds at every resolution.
aspectRatio	string	No	auto	-	-	auto, 16:9, 9:16	Output orientation. Match Input follows the first frame and falls back to 16:9 for text-to-video.
fps	number	No	24	-	-	24, 25, 48, 50	Frame rate in frames per second. 24, 25, 48 and 50 are available at every resolution.
cameraMotion	string	No	static	-	-	dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down, static, focus_shift	Optional camera motion preset applied to the generated video
generateAudio	boolean	No	true	-	-	-	Generate synchronized audio for the video

LTX-2.5 Pro Audio to Video

Generate a video driven by a soundtrack. Higher visual quality than Fast, up to 4K and 10 seconds of audio.

Model ID: model_ltx-2-5-pro-audio-to-video

Capabilities: audio2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-pro-audio-to-video/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
audio	file	Yes	-	-	-	-	Soundtrack that drives the video. Its length becomes the video’s. Pro accepts up to 10 seconds at every resolution.
prompt	string	No	-	-	-	-	What the video should show, or how the first frame should be animated. Required when no image is provided.
image	file	No	-	-	-	-	Optional opening frame. Required when no prompt is provided.
lastFrameImage	file	No	-	-	-	-	Closing frame for interpolation. Requires a first frame.
resolution	string	No	1080p	-	-	720p, 1080p, 1440p, 4k	Video resolution. Pro supports 720p, 1080p, 1440p and 4K; audio is capped at 10 seconds at every resolution.
aspectRatio	string	No	auto	-	-	auto, 16:9, 9:16	Output orientation. Match Input follows the first frame and falls back to 16:9 with no image.
fps	number	No	24	-	-	24, 25, 48, 50	Frame rate in frames per second. 24, 25, 48 and 50 are available at every resolution.
cameraMotion	string	No	static	-	-	dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down, static, focus_shift	Optional camera motion preset applied to the generated video

LTX-2.5 Reference Sheet

Animates a reference sheet into a video.

Model ID: model_ltx-2-5-ingredients

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-ingredients/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Two sections: “### Reference Sheet Description” describing each panel of the sheet, then “### Target Description” describing the shot to generate.
referenceVideos	file_array	Yes	-	-	-	-	The reference sheet still, looped into a static video of at least 121 frames. The output takes its size, scaled down to fit 768×768. Up to 100 MB and 21 s.
seed	number	No	-	0	2147483647	-	Random seed for reproducibility. Leave blank for random.

LTX-2.5 Refine Details

Adds fine detail and texture to a video already at its output size.

Model ID: model_ltx-2-5-refine-details

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-refine-details/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	No	sharp photographic detail, crisp natural texture	-	-	-	Generic rendering terms describing the detail to add, such as “sharp photographic detail, crisp natural texture”.
referenceVideos	file_array	Yes	-	-	-	-	The source video to transform. The output has the same length, rounded down to 8k+1 frames, up to 241 frames: an input of up to 10.33 s at 24 fps. The output keeps your video’s size, scaled down to fit 1024×1024. Up to 100 MB.
seed	number	No	-	0	2147483647	-	Random seed for reproducibility. Leave blank for random.

LTX-2.5 Restore

Restores damaged archival film (grain, scratches, dust, flicker) in natural color.

Model ID: model_ltx-2-5-restore

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-restore/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Describe the scene: period, place, light and materials, ending with “natural colour”, as in the LoRA’s example prompts.
referenceVideos	file_array	Yes	-	-	-	-	Damaged archival footage to restore. The output has the same length, rounded down to 8k+1 frames, from 49 to 97 frames: an input of 2.04 to 4.33 s at 24 fps. The output keeps your video’s size, scaled down to fit 960×960. Up to 100 MB.
seed	number	No	-	0	2147483647	-	Random seed for reproducibility. Leave blank for random.

LTX-2.5 Slow Motion

Animates an image in controllable slow motion.

Model ID: model_ltx-2-5-slow-motion-control

Capabilities: img2video

LLM Markdown: https://app.scenario.com/api/models/model_ltx-2-5-slow-motion-control/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	Describe the scene. Do not use speed words such as “slow motion” or “high fps”; keep the same prompt at every speed.
image	file	Yes	-	-	-	-	The image to animate. The video takes the image’s size, scaled down to fit 1920×1920.
motionSpeed	number	No	0.2	0.025	1	-	Playback speed of the motion: 1.0 is normal, 0.2 is 5x slower. Raise it if motion looks smeared.
numFrames	number	No	121	9	121	-	Number of frames at 24 fps, in steps of 8 from 9.
seed	number	No	-	0	2147483647	-	Random seed for reproducibility. Leave blank for random.