CIntellifusion/VideoDPO

Official Implementation of VideoDPO

25
/ 100
Experimental

This project helps video creators, marketers, or digital artists refine existing text-to-video diffusion models to produce videos that better match their specific preferences. You input text prompts and an existing video generation model, and it outputs a fine-tuned model that generates videos with improved visual quality and semantic alignment to your prompts. This is for anyone who uses AI to generate video content and struggles with the output not quite matching their vision.

161 stars. No commits in the last 6 months.

Use this if you need to fine-tune a pre-trained text-to-video model to generate videos that are more visually appealing and semantically accurate to your text descriptions.

Not ideal if you are starting a video generation project from scratch or don't have access to existing text-to-video diffusion models.

video-creation generative-AI content-production digital-art video-editing
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

161

Forks

3

Language

Python

License

Last pushed

Jun 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/CIntellifusion/VideoDPO"

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