Struct VideoToVideoInput

pub struct VideoToVideoInput {
    pub export_fps: Option<i64>,
    pub guidance_scale: Option<f64>,
    pub loras: Option<Vec<Option<LoraWeight>>>,
    pub negative_prompt: Option<String>,
    pub num_inference_steps: Option<i64>,
    pub prompt: String,
    pub seed: Option<i64>,
    pub strength: Option<f64>,
    pub use_rife: Option<bool>,
    pub video_size: Option<VideoSizeProperty>,
    pub video_url: String,
}

Fields

export_fps: Option<i64>

The target FPS of the video

guidance_scale: Option<f64>

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related video to show you.

loras: Option<Vec<Option<LoraWeight>>>

The LoRAs to use for the image generation. We currently support one lora./// The LoRAs to use for the image generation. We currently support one lora.

negative_prompt: Option<String>

The negative prompt to generate video from/// The negative prompt to generate video from/// “Distorted, discontinuous, Ugly, blurry, low resolution, motionless, static, disfigured, disconnected limbs, Ugly faces, incomplete arms”

num_inference_steps: Option<i64>

The number of inference steps to perform.

prompt: String

The prompt to generate the video from./// The prompt to generate the video from./// “An astronaut stands triumphantly at the peak of a towering mountain. Panorama of rugged peaks and valleys. Very futuristic vibe and animated aesthetic. Highlights of purple and golden colors in the scene. The sky is looks like an animated/cartoonish dream of galaxies, nebulae, stars, planets, moons, but the remainder of the scene is mostly realistic. “

seed: Option<i64>

The same seed and the same prompt given to the same version of the model will output the same video every time.

strength: Option<f64>

The strength to use for Video to Video. 1.0 completely remakes the video while 0.0 preserves the original.

use_rife: Option<bool>

Use RIFE for video interpolation

video_size: Option<VideoSizeProperty>

The size of the generated video.

video_url: String

The video to generate the video from./// The video to generate the video from./// “https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/hiker.mp4”

Trait Implementations

impl Debug for VideoToVideoInput

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for VideoToVideoInput

fn default() -> VideoToVideoInput

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for VideoToVideoInput

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for VideoToVideoInput

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.