You're looking at a specific version of this model. Jump to the model overview.

cjwbw /videocrafter:99957f23

Input

string

Choose the task. The resolution for text2video is 1024x576, and 512x320 for image2video.

Default: "text2video"

string
Shift + Return to add a new line

Prompt for video generation.

Default: "A tiger walks in the forest, photorealistic, 4k, high definition."

file

Input image for image2video task. The model is trained for 512x320 images.

integer

Number of denoising steps.

Default: 50

number

Classifier-free guidance scale.

Default: 12

integer

Random seed. Leave blank to randomize the seed

integer

Frame per second for the generated video.

Default: 10

Output

No output yet! Press "Submit" to start a prediction.