Luma Labs

This page is auto-generated from model configurations. Last updated: 2026-03-13.

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


Luma Modify Video

Model ID: model_luma-modify-video

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_luma-modify-video/markdown

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
videofileYes----The video to modify. Maximum video size is 100mb. Maximum video duration is 30 seconds.
firstFramefileNo----An optional first frame of the video to modify. This should be a modified version of the original first frame, it will be used to guide the video modification.
promptstringNo----A prompt to guide the video modification
modestringNoadhere_1--adhere_1, adhere_2, adhere_3, flex_1, flex_2, flex_3, reimagine_1, reimagine_2, reimagine_3How closely the output should follow the source video. Adhere: very close, for subtle enhancements. Flex: allows more stylistic change while keeping recognizable elements. Reimagine: loosely follows the source, for dramatic or transformative changes.

Luma Ray 2 Flash - 540p

Luma Ray Flash 2 520p quickly generates bold videos in 30–60 seconds for impactful content creation.

Model ID: model_luma-ray-flash-2-540p

Capabilities: txt2video, img2video

LLM Markdown: https://app.scenario.com/api/models/model_luma-ray-flash-2-540p/markdown

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
promptstringYes----Describe your video
imagefileNo----Image used as the first frame of the video
endImagefileNo----Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
durationnumberNo5--5, 9Duration in seconds
aspectRatiostringNo16:9--9:21, 9:16, 3:4, 1:1, 4:3, 16:9, 21:9Aspect ratio of the generated video
loopbooleanNofalse---Matches the first and last frames for smooth, seamless looping.
conceptsstring_arrayNo---truck_left, pan_right, pedestal_down, low_angle, pedestal_up, selfie, pan_left, roll_right, zoom_in, over_the_shoulder, orbit_right, orbit_left, static, tiny_planet, high_angle, bolt_cam, dolly_zoom, overhead, zoom_out, handheld, roll_left, pov, aerial_drone, push_in, crane_down, truck_right, tilt_down, elevator_doors, tilt_up, ground_level, pull_out, aerial, crane_up, eye_levelList of camera concepts to apply to the video generation.

Luma Ray 2 Flash - 720p

Luma Ray Flash 2 720p quickly generates bold videos in 30–60 seconds for impactful content creation.

Model ID: model_luma-ray-flash-2-720p

Capabilities: txt2video, img2video

LLM Markdown: https://app.scenario.com/api/models/model_luma-ray-flash-2-720p/markdown

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
promptstringYes----Describe your video
imagefileNo----Image used as the first frame of the video.e
endImagefileNo----Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
durationnumberNo5--5, 9Duration in seconds
aspectRatiostringNo16:9--9:21, 9:16, 3:4, 1:1, 4:3, 16:9, 21:9Aspect ratio of the generated video
loopbooleanNofalse---Matches the first and last frames for smooth, seamless looping.
conceptsstring_arrayNo---truck_left, pan_right, pedestal_down, low_angle, pedestal_up, selfie, pan_left, roll_right, zoom_in, over_the_shoulder, orbit_right, orbit_left, static, tiny_planet, high_angle, bolt_cam, dolly_zoom, overhead, zoom_out, handheld, roll_left, pov, aerial_drone, push_in, crane_down, truck_right, tilt_down, elevator_doors, tilt_up, ground_level, pull_out, aerial, crane_up, eye_levelList of camera concepts to apply to the video generation.

Luma Video Reframe

Model ID: model_luma-reframe-video

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_luma-reframe-video/markdown

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
videofileYes----The video to reframe. Maximum video duration is 10 seconds.
aspectRatiostringNo16:9--9:21, 9:16, 3:4, 1:1, 4:3, 16:9, 21:9Aspect ratio of the output
promptstringNo----A prompt to guide the reframing generation