Interface VideoProjectParams

Video-specific parameters for video workflows (t2v, i2v, s2v, ia2v, a2v, animate). Only applicable when using video models like wan_v2.2-14b-fp8_t2v or ltx2-19b-fp8_t2v. Includes frame count, fps, shift, and reference assets (image, audio, video).

Important: FPS and Frame Count Behavior Differs by Model

WAN 2.2 Models (wan_v2.2-*)

  • Always generate video at 16fps internally
  • The fps parameter (16 or 32) only controls post-render frame interpolation
  • fps=32 doubles the frames via interpolation after generation
  • Frame count is always calculated as: duration * 16 + 1
  • Example: 5 seconds at 32fps = 81 frames generated, then interpolated to 161 output frames

LTX-2 Models (ltx2-*)

  • Generate video at the actual specified FPS (1-60 fps range)
  • No post-render interpolation - fps directly affects generation
  • Frame count is calculated as: duration * fps + 1
  • Frame count must follow the pattern: 1 + n*8 (i.e., 1, 9, 17, 25, 33, ...)
  • Example: 5 seconds at 24fps = 121 frames (since 121 = 1 + 15*8)
interface VideoProjectParams {
    audioDuration?: number;
    audioStart?: number;
    controlNet?: VideoControlNetParams;
    detailerStrength?: number;
    disableNSFWFilter?: boolean;
    duration?: number;
    firstFrameStrength?: number;
    fps?: number;
    frames?: number;
    guidance?: number;
    height?: number;
    lastFrameStrength?: number;
    loras?: string[];
    loraStrengths?: number[];
    modelId: string;
    negativePrompt?: string;
    network?: SupernetType;
    numberOfMedia: number;
    outputFormat?: "mp4";
    positivePrompt: string;
    referenceAudio?: InputMedia;
    referenceImage?: InputMedia;
    referenceImageEnd?: InputMedia;
    referenceVideo?: InputMedia;
    sam2Coordinates?: { x: number; y: number }[];
    sampler?: string;
    scheduler?: string;
    seed?: number;
    shift?: number;
    steps?: number;
    stylePrompt?: string;
    teacacheThreshold?: number;
    tokenType?: TokenType;
    trimEndFrame?: boolean;
    type: "video";
    videoStart?: number;
    width?: number;
}

Hierarchy (View Summary)

Properties

audioDuration? audioStart? controlNet? detailerStrength? disableNSFWFilter? duration? firstFrameStrength? fps? frames? guidance? height? lastFrameStrength? loras? loraStrengths? modelId negativePrompt? network? numberOfMedia outputFormat? positivePrompt referenceAudio? referenceImage? referenceImageEnd? referenceVideo? sam2Coordinates? sampler? scheduler? seed? shift? steps? stylePrompt? teacacheThreshold? tokenType? trimEndFrame? type videoStart? width?

Properties

OptionalaudioDuration

audioDuration?: number

Audio duration in seconds for audio-driven workflows (s2v, ia2v, a2v). Specifies how many seconds of audio to use. If not provided, defaults to 30 seconds on the server.

OptionalaudioStart

audioStart?: number

Audio start position in seconds for audio-driven workflows (s2v, ia2v, a2v). Specifies where to begin reading from the audio file. Default: 0

OptionalcontrolNet

controlNet?: VideoControlNetParams

ControlNet parameters for LTX-2 v2v workflows. Specifies which control signal to extract from the reference video.

OptionaldetailerStrength

detailerStrength?: number

Detailer LoRA strength for LTX-2 v2v IC-Control workflows. The detailer LoRA is always loaded alongside the control LoRA (canny/pose/depth). Range: 0.0-1.0, default 0.6.

OptionaldisableNSFWFilter

disableNSFWFilter?: boolean

Disable NSFW filter for Project. Default is false, meaning NSFW filter is enabled. If image triggers NSFW filter, it will not be available for download.

Optionalduration

duration?: number

Duration of the video in seconds. Supported range 1 to 10 (WAN) or 4 to 20 (LTX-2).

The SDK automatically calculates the correct frame count based on the model:

  • WAN 2.2: duration * 16 + 1 (always 16fps generation)
  • LTX-2: duration * fps + 1, snapped to frame step constraint

OptionalfirstFrameStrength

firstFrameStrength?: number

First frame strength for LTX-2 keyframe interpolation (when referenceImageEnd is provided). Controls how strictly the first frame is matched. Range: 0.0-1.0, default 0.6. Set to 0 to disable first frame (last-frame-only mode).

Optionalfps

fps?: number

Frames per second for output video.

WAN 2.2 Models: Only 16 or 32 fps allowed. The 32fps option is post-render frame interpolation that doubles the output frames. Internal generation is always 16fps.

LTX-2 Models: Any value from 1-60 fps. This directly controls the generation frame rate - there is no post-render interpolation.

Optionalframes

frames?: number

Number of frames to generate.

Deprecated

Use duration instead. When using duration, the SDK automatically calculates the correct frame count based on the model type.

Optionalguidance

guidance?: number

Guidance scale. For most Stable Diffusion models, optimal value is 7.5. For video models: Regular models range 0.7-8.0, LoRA version (lightx2v) range 0.7-1.6, step 0.01. This maps to guidanceScale in the keyFrame for both image and video models.

Optionalheight

height?: number

Output video height. Only used if sizePreset is "custom"

OptionallastFrameStrength

lastFrameStrength?: number

Last frame strength for LTX-2 keyframe interpolation (when referenceImageEnd is provided). Controls how strictly the last frame is matched. Range: 0.0-1.0, default 0.6.

Optionalloras

loras?: string[]

Array of LoRA IDs to apply. Available LoRAs are model-specific. The worker will download the LoRA if not already present on the persistent volume. LoRA IDs are resolved to filenames via the worker config API. Example: ['multiple_angles']

OptionalloraStrengths

loraStrengths?: number[]

Array of LoRA strengths corresponding to each LoRA in the loras array. Values should be between 0.0 and 2.0. Defaults to 1.0 if not specified. Example: [0.9]

modelId

modelId: string

ID of the model to use, available models are available in the availableModels property of the ProjectsApi instance.

OptionalnegativePrompt

negativePrompt?: string

Prompt for what to be avoided. If not provided, server default is used.

Optionalnetwork

network?: SupernetType

Override current network type. Default value can be read from sogni.account.currentAccount.network

numberOfMedia

numberOfMedia: number

Number of media files to generate. Depending on project type, this can be number of images or number of videos.

OptionaloutputFormat

outputFormat?: "mp4"

Output video format. For now only 'mp4' is supported, defaults to 'mp4'.

positivePrompt

positivePrompt: string

Prompt for what to be created

OptionalreferenceAudio

referenceAudio?: InputMedia

Reference audio for audio-driven video workflows (s2v, ia2v, a2v).

OptionalreferenceImage

referenceImage?: InputMedia

Reference image for video workflows. Maps to: startImage (i2v), characterImage (animate), referenceImage (s2v, ia2v)

OptionalreferenceImageEnd

referenceImageEnd?: InputMedia

Optional end image for i2v interpolation workflows. When provided with referenceImage, the video will interpolate between the two images.

OptionalreferenceVideo

referenceVideo?: InputMedia

Reference video for animate and v2v (ControlNet) workflows. Maps to: drivingVideo (animate-move), sourceVideo (animate-replace), referenceVideo (v2v)

Optionalsam2Coordinates

sam2Coordinates?: { x: number; y: number }[]

SAM2 click coordinates for subject detection in animate-replace workflows. Array of {x, y} coordinate objects indicating where the subject is located in the reference image.

Coordinates can be normalized (0.0-1.0) or absolute pixel values. Normalized coordinates are automatically converted to pixel values by the server. If not provided, the server defaults to the center of the frame.

Example: [{ x: 0.5, y: 0.5 }] for center of frame

Optionalsampler

sampler?: string

Sampler, available options depend on the model. Use sogni.projects.getModelOptions(modelId) to get the list of available samplers.

Optionalscheduler

scheduler?: string

Scheduler, available options depend on the model. Use sogni.projects.getModelOptions(modelId) to get the list of available schedulers.

Optionalseed

seed?: number

Seed for one of images in project. Other will get random seed. Must be Uint32

Optionalshift

shift?: number

Shift parameter for video diffusion models. Controls motion intensity. Range: 1.0-8.0, step 0.1. Default: 8.0 for regular models, 5.0 for speed lora (lightx2v) except s2v and animate which use 8.0

Optionalsteps

steps?: number

Number of steps. For most Stable Diffusion models, optimal value is 20.

OptionalstylePrompt

stylePrompt?: string

Image style prompt. If not provided, server default is used.

OptionalteacacheThreshold

teacacheThreshold?: number

TeaCache optimization threshold for T2V and I2V models. Range: 0.0-1.0. 0.0 = disabled. Recommended: 0.15 for T2V (~1.5x speedup), 0.2 for I2V (conservative quality-focused)

OptionaltokenType

tokenType?: TokenType

Select which tokens to use for the project. If not specified, the Sogni token will be used.

OptionaltrimEndFrame

trimEndFrame?: boolean

Trim the last frame from the generated video. Used for seamless stitching of transition videos where the last frame duplicates the end reference image. Default: false

type

type: "video"

OptionalvideoStart

videoStart?: number

Video start position in seconds for animate workflows (animate-move, animate-replace). Specifies where to begin reading from the reference video file. Default: 0

Optionalwidth

width?: number

Output video width. Only used if sizePreset is "custom"

Settings

Member Visibility

On This Page

Important: FPS and Frame Count Behavior Differs by Model
Properties