Junyi42

sd-dino

Official Implementation of paper "A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence"

DiffStyle

DiffStyle: Leverage Diffusion Prior to One-for-All Style Transfer. Course project of CS3310 Computer Graphics, built on Prompt-to-Prompt and Null-Text.

GeoAware-SC

Official Implementation of paper "Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence"

DiffSketch

DiffSketch: Plug-and-Play Diffusion Features for Zero-Shot Line-Drawing-to-Sketch Synthesis. Course project of CS3511, built on pnp-diffusion.

BUSS2505-MachineLearning

Homewrok & Project of this course

awesome-cs

👨‍💻 ❤️ 💻 上海交通大学计算机系本科作业参考

CS3511-Federated-Learning

CDN

Code for "Mining the Benefits of Two-stage and One-stage HOI Detection"

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

Junyi

Config files for my GitHub profile.

VPD

VPD is a framework that leverages the high-level and low-level knowledge of a pre-trained text-to-image diffusion model to downstream visual perception tasks.