README.md

Paper reading and round-table discussion of Minisora Community

 

English | 简体中文

Paper Reading Notes

Data Notes(zh-CN)

Latte Paper Intensive Translation(zh-CN)

Latte Paper Interpretation(zh-CN)

Parallel Acceleration Method for Diffusion Models: DistriFusion Paper Discussion(zh-CN)

SD3 Paper Interpretation(zh-CN, ZhiHu)

Previous round-table discussions

Night Talk with Sora: Video Diffusion Overview

Speaker: Xing Zhen, PhD candidate in the Vision and Learning Lab, Fudan University

Highlights: Fundamentals of Diffusion Modeling for Image Generation / Development of Diffusion Modeling for Text to Video / An Introduction to the Technology and Reproduction Challenges Behind Sora

Time of Online Live: 02/28 20:00-21:00

Bilibili: Sora 之 Video Diffusion 综述(zh-CN)

PPT: FeiShu Link

ZhiHu Notes: A Survey on Generative Diffusion Model(zh-CN)

---

Paper Interpretation of Stable Diffusion 3 paper: MM-DiT

Speaker: MMagic Core Contributors

Highlights: MMagic core contributors will lead us in interpreting the Stable Diffusion 3 paper, discussing the architecture details and design principles of Stable Diffusion 3.

Time of Online Live: 03/12 20:00

PPT: FeiShu Link