ali-vilab/i2vgen-xl

RESEARCH/NON-COMMERCIAL USE ONLY: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models

Input
Configure the inputs for the AI model.

Random seed. Leave blank to randomize the seed

Input image.

Describe the input image.

2
100

Number of frames in the output

1
20

Scale for classifier-free guidance

1
500

Number of denoising steps

Output
The generated output will appear here.

No output yet

Click "Generate" to create an output.

i2vgen-xl - ikalos.ai