Text2Video-Zero

lastmod 2023-04-03created 2023-04-031 edits

Text-to-Image Diffusion Models are Zero-Shot Video Generators

Features

• A model that performs Text-To-Video generation without prior training (Zero Shot)
• Low cost, achieved by applying existing Text-To-Image techniques to the video domain (currently runs on 12GB VRAM, with plans to reduce this further)

See also

• Text-To-Image
• Text-To-Video
• Deep learning

Favorite site

• Github - Picsart-AI-Research/Text2Video-Zero