Fast SVD Video Generator

Provided by FalLearn More

Generate high-quality videos from text prompts using the SVD model. Creates short animations quickly.

Preview

Inputs

Prompt
text
The prompt to use for generating the video. Be descriptive for best results.
Negative Prompt
text
What to exclude from the video. Use it to address details you don't want.
default: blurry, low quality, distorted
Video Size
dropdown
The size of the generated video.
default: landscape_16_9Accepts: Square HD (1024x1024), Square (512x512), Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9
Motion Bucket
number
The motion bucket id determines the motion of the generated video. The higher the number, the more motion there will be.
default: 127minimum: 1maximum: 255
Conditioning Augmentation
number
The conditoning augmentation determines the amount of noise that will be added to the conditioning frame. The higher the number, the more noise there will be, and the less the video will look like the initial image. Increase it for more motion.
default: 0.02minimum: 0.01maximum: 0.1
Steps
number
Number of diffusion steps. Higher = better quality but slower.
default: 20minimum: 10maximum: 50
Deep Cache
dropdown
Enabling DeepCache will make the execution faster, but might sometimes degrade overall quality. The higher the setting, the faster the execution will be, but the more quality might be lost.
default: minimumAccepts: None, Minimum, Medium, High
FPS
number
The FPS of the generated video. The higher the number, the faster the video will play. Total video length is 25 frames.
default: 24minimum: 1maximum: 25
Seed
seed
The same seed and prompt will output the same image every time.
default: 959055

Outputs

Video
video
The generated video.