Video Models - Parameters Reference

Kling

🎯 Kling 2.1 Master

Model ID: model_kling-v2-1-master

ParameterTypeDefaultDescription
promptstring``Describe your video
startImagefile``Image used as the first frame of the video.
aspectRatiostring16:9Aspect ratio of the video. Ignored if first frame is provided.
durationnumber5Duration in seconds

🎯 Kling 2.1

Model ID: model_kling-v2-1

ParameterTypeDefaultDescription
promptstring``Describe your video
startImagefile``Image used as the first frame of the video.
modestringstandardStandard has a resolution of 720p, pro is 1080p. Both are 24fps.
durationnumber5Duration in seconds

🎯 Kling 2.0

Model ID:model_kling-v2-0

ParameterTypeDefaultDescription
promptstring``Describe your video
startImagefile``Image used as the first frame of the video.
aspectRatiostring16:9Aspect ratio of the video. Ignored if first frame is provided.
cfgScalenumber0.5Higher values follow the prompt more closely, lower values are more creative
durationnumber5Duration in seconds

🎯 Kling 1.6 Pro

Model ID: model_kling-v1-6-pro

ParameterTypeDefaultDescription
promptstring``Describe your video
startImagefile``Image used as the first frame of the video.
endImagefile``Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
referenceImagesfile_array``Use up to 4 reference images (scene elements) for video generation. Start/end images are ignored when using references.
aspectRatiostring16:9Aspect ratio of the video. Ignored if first frame is provided.
cfgScalenumber0.5Higher values follow the prompt more closely, lower values are more creative
durationnumber5Duration in seconds

🎯 Kling 1.6

Model ID: model_kling-v1-6-standard

ParameterTypeDefaultDescription
promptstring``Describe your video
startImagefile``Image used as the first frame of the video.
referenceImagesfile_array``Use up to 4 reference images (scene elements) for video generation. Start/end images are ignored when using references.
aspectRatiostring16:9Aspect ratio of the video. Ignored if first frame is provided.
cfgScalenumber0.5Higher values follow the prompt more closely, lower values are more creative
durationnumber5Duration in seconds

Bytedance

🎯 Seedance 1 Pro

Model ID: model_bytedance-seedance-1-pro

ParameterTypeDefaultDescription
promptstring``Describe your video
imagefile``Image used as the first frame of the video.
durationnumber5Duration in seconds
resolutionstring1080pOutput video resolution
aspectRatiostring16:9Aspect ratio of the video. Ignored if first frame is provided.
cameraFixedbooleanFalseWhether to fix camera position
seednumber``Use a seed for reproducible results. Leave blank to use a random seed.

🎯 Seedance 1 Lite

Model ID: model_bytedance-seedance-1-lite

ParameterTypeDefaultDescription
promptstring``Describe your video
imagefile``Image used as the first frame of the video.
durationnumber5Duration in seconds
resolutionstring720pOutput video resolution
aspectRatiostring16:9Aspect ratio of the video. Ignored if first frame is provided.
cameraFixedbooleanFalseWhether to fix camera position
seednumber``Use a seed for reproducible results. Leave blank to use a random seed.

Google VEO

🎯 VEO3

Model ID: model_veo3

ParameterTypeDefaultDescription
promptstring``Describe your video
imagefile``Image used as the first frame of the video. Ideal images are 16:9 or 9:16 and 1280x720 or 720x1280, depending on the aspect ratio you choose.
generateAudiobooleanTrueGenerate audio for the video
aspectRatiostring16:9Video aspect ratio
durationnumber8Video duration
seednumber``Use a seed for reproducible results. Leave blank to use a random seed.

🎯 VEO2

Model ID: model_veo2

ParameterTypeDefaultDescription
promptstring``Describe your video
imagefile``Image used as the first frame of the video. Ideal images are 16:9 or 9:16 and 1280x720 or 720x1280, depending on the aspect ratio you choose.
aspectRatiostring16:9Video aspect ratio
durationnumber5Video duration
seednumber``Use a seed for reproducible results. Leave blank to use a random seed.

Luma Ray 2

🎯 Luma Ray 2 540p

Model ID: model_luma-ray-2-540p

ParameterTypeDefaultDescription
promptstring``Describe your video
imagefile``Image used as the first frame of the video.
endImagefile``Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
durationnumber5Duration in seconds
aspectRatiostring16:9Aspect ratio of the generated video
loopbooleanFalseMatches the first and last frames for smooth, seamless looping.
conceptsstring_array``List of camera concepts to apply to the video generation.

🎯 Luma Ray 2 Flash 540p

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

ParameterTypeDefaultDescription
promptstring``Describe your video
imagefile``Image used as the first frame of the video
endImagefile``Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
durationnumber5Duration in seconds
aspectRatiostring16:9Aspect ratio of the generated video
loopbooleanFalseMatches the first and last frames for smooth, seamless looping.
conceptsstring_array``List of camera concepts to apply to the video generation.

🎯 Luma Ray 2 720p

Model ID: model_luma-ray-2-720p

ParameterTypeDefaultDescription
promptstring``Describe your video
imagefile``Image used as the first frame of the video.
endImagefile``Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
durationnumber5Duration in seconds
aspectRatiostring16:9Aspect ratio of the generated video
loopbooleanFalseMatches the first and last frames for smooth, seamless looping.
conceptsstring_array``List of camera concepts to apply to the video generation.

🎯 Luma Ray 2 Flash 720p

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

ParameterTypeDefaultDescription
promptstring``Describe your video
imagefile``Image used as the first frame of the video.e
endImagefile``Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
durationnumber5Duration in seconds
aspectRatiostring16:9Aspect ratio of the generated video
loopbooleanFalseMatches the first and last frames for smooth, seamless looping.
conceptsstring_array``List of camera concepts to apply to the video generation

Pixverse

🎯 Pixverse v4.5

Model ID: model_pixverse-v4-5

ParameterTypeDefaultDescription
promptstring``Describe your video
imagefile``Image used as the first frame of the video.
lastFrameImagefile``Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
qualitystring540pVideo resolution
aspectRatiostring16:9Aspect ratio of the video
durationnumber5Duration in seconds. (1080p does not support 8 second duration)
motionModestringnormalMotion mode for the video. Smooth videos generate more frames, so they cost more. (smooth is only available when using a 5 second duration, 1080p does not support smooth motion)
stylestringNoneStyle of the video
effectstringNoneSpecial effect to apply to the video
seednumber``Use a seed for reproducible results. Leave blank to use a random seed.

🎯 Pixverse v4

Model ID: model_pixverse-v4

ParameterTypeDefaultDescription
promptstring``Describe your video
imagefile``Image used as the first frame of the video.
lastFrameImagefile``Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
qualitystring540pVideo resolution
aspectRatiostring16:9Aspect ratio of the video
durationnumber5Duration in seconds. (1080p does not support 8 second duration)
motionModestringnormalMotion mode for the video. Smooth videos generate more frames, so they cost more. (smooth is only available when using a 5 second duration, 1080p does not support smooth motion)
stylestringNoneStyle of the video
effectstringNoneSpecial effect to apply to the video
seednumber``Use a seed for reproducible results. Leave blank to use a random seed.

Wan

🎯 Wan 2.1 1.3b

Model ID: model_wan-2-1-1-3b

ParameterTypeDefaultDescription
promptstring``Describe your video
aspectRatiostring16:9Video aspect ratio
frameNumnumber81Video duration in frames (based on standard 16fps playback)
sampleStepsnumber30Number of sampling steps (higher = better quality but slower)
sampleGuideScalenumber6Higher values follow the prompt more closely, lower values are more creative
sampleShiftnumber8Sampling shift factor for flow matching (recommended range: 8-12)
seednumber``Use a seed for reproducible results. Leave blank to use a random seed.

🎯 Wan 2.1 720p

Model ID: model_wan-2-1-i2v-720p

ParameterTypeDefaultDescription
promptstring``Describe your video
imagefile``Image used as the first frame of the video.
numFramesnumber81Number of video frames. 81 frames give the best results
maxAreastring1280x720Maximum area of generated image. The input image will shrink to fit these dimensions
framesPerSecondnumber16Frames per second
fastModestringBalancedSpeed up generation with different levels of acceleration. Faster modes may degrade quality somewhat. The speedup is dependent on the content, so different videos may see different speedups.
sampleStepsnumber30Number of generation steps. Fewer steps means faster generation, at the expensive of output quality. 30 steps is sufficient for most prompts
sampleGuideScalenumber5Higher values follow the prompt more closely, lower values are more creative
sampleShiftnumber5Sample shift factor
seednumber``Use a seed for reproducible results. Leave blank to use a random seed.

🎯 Wan 2.1 480p

Model ID: model_wan-2-1-i2v-480p

ParameterTypeDefaultDescription
promptstring``Describe your video
imagefile``Image used as the first frame of the video.
numFramesnumber81Number of video frames. 81 frames give the best results
maxAreastring832x480Maximum area of generated image. The input image will shrink to fit these dimensions
framesPerSecondnumber16Frames per second. Note that the pricing of this model is based on the video duration at 16 fps
fastModestringBalancedSpeed up generation with different levels of acceleration. Faster modes may degrade quality somewhat. The speedup is dependent on the content, so different videos may see different speedups.
sampleStepsnumber30Number of generation steps. Fewer steps means faster generation, at the expensive of output quality. 30 steps is sufficient for most prompts
sampleGuideScalenumber5Higher values follow the prompt more closely, lower values are more creative
sampleShiftnumber3Sample shift factor
seednumber``Use a seed for reproducible results. Leave blank to use a random seed.

Minimax

🎯 Minimax Video

Model ID: model_minimax-video-01

ParameterTypeDefaultDescription
promptstring``Describe your video
firstFrameImagefile``Image used as the first frame of the video.
subjectReferencefile``An optional character reference image to use as the subject in the generated video
promptOptimizerbooleanTrueUse prompt optimizer

🎯 Minimax Director

Model ID: model_minimax-video-01-director

ParameterTypeDefaultDescription
promptstring``Describe your video. Try Prompt Spark or check our Help Center for detailed prompt tips for this model.
firstFrameImagefile``Image used as the first frame of the video.
promptOptimizerbooleanTrueUse prompt optimizer

🎯 Minimax Live

Model ID: model_minimax-video-01-live

ParameterTypeDefaultDescription
imagefile``Image used as the first frame of the video.
promptstring``Describe your video
promptOptimizerbooleanTrueUse prompt optimizer

Hunyuan Video

🎯 Hunyuan Video

Model ID: model_hunyuan-video

ParameterTypeDefaultDescription
promptstring``Describe your video
widthnumber864Width of the video in pixels (must be divisible by 16)
heightnumber480Height of the video in pixels (must be divisible by 16)
videoLengthnumber129Number of frames to generate (must be 4k+1, ex: 49 or 129)
inferStepsnumber50Number of denoising steps
embeddedGuidanceScalenumber6Higher values follow the prompt more closely, lower values are more creative
fpsnumber24Frames per second of the output video
seednumber``Use a seed for reproducible results. Leave blank to use a random seed.

Framepack

🎯 Framepack

Model ID: model_framepack

ParameterTypeDefaultDescription
imagefile``Image used as the first frame of the video
promptstring``Describe your video
videoLengthnumber5Duration in seconds
stepsnumber25Number of steps. Recommended value: 25
cfgScalenumber10Distilled CFG scale. Recommended value: 10
teaCachebooleanTrueMakes generation faster with minimal quality impact
seednumber``Use a seed for reproducible results. Leave blank to use a random seed.

Video Foreground Extractor

🎯 Video Matting

Model ID: model_ariel-robust-video-matting

ParameterTypeDefaultDescription
inputVideofile``Source video for foreground extraction.
outputTypestringgreen-screenSelect background style for the extracted video.