360CVGroup/Qihoo-T2X

Efficient DiT architecture for text2any tasks, ICLR2025

31
/ 100
Emerging

This project offers an advanced method for generating diverse content, like images, from text descriptions. You input a text prompt detailing what you want to create, and it efficiently produces the corresponding visual or other media. It's designed for researchers and practitioners working on cutting-edge generative AI models.

447 stars. No commits in the last 6 months.

Use this if you are developing or experimenting with next-generation text-to-content generation models and prioritize efficiency in your generative AI architecture.

Not ideal if you are an end-user looking for a ready-to-use application for simple image generation without needing to delve into model architecture or research.

generative-AI-research diffusion-models text-to-image-generation AI-model-efficiency deep-learning-research
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

447

Forks

22

Language

License

Category

gan-based-t2i

Last pushed

May 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/360CVGroup/Qihoo-T2X"

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