TonyLianLong/LLM-groundedVideoDiffusion

[ICLR 2024] LLM-grounded Video Diffusion Models (LVD): official implementation for the LVD paper

27
/ 100
Experimental

This project helps video creators and content producers generate short video clips from detailed text descriptions. You input a text prompt, and the system uses an AI planner to create a scene layout with objects and their movements. This layout then guides a video generator to produce a video that accurately reflects your prompt's specifics, making it easier to visualize and create dynamic scenes.

167 stars. No commits in the last 6 months.

Use this if you need to create specific video content from complex text prompts, ensuring objects and their actions appear exactly as described across multiple frames.

Not ideal if you're looking for a simple text-to-video tool that doesn't require precise control over scene composition and object placement.

video-production content-creation digital-art animation generative-ai
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

167

Forks

8

Language

Python

License

Last pushed

May 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/TonyLianLong/LLM-groundedVideoDiffusion"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.