Official implementaiton of RefAM: Attention Magnets for Zero-Shot Referral Segmentaiton

[NIPS2025] RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers

Interactive visualizations of the geometric intuition behind diffusion models.

[SIGGRAPH 2025] 3D Stylization via Large Reconstruction Model

Text-guided 3D texture generation using training-free multi-diffusion in UV space.

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

[ICCV 2025] Identity Preserving 3D Head Stylization with Multiview Score Distillation

🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!

Workshop for computer scinece students to learn the basics of github API

[NIPS2024] Official Code Repository for "Dual Encoder GAN Inversion for High-Fidelity 3D Head Reconstruction from Single Images"

Connect to Slurm Compute Nodes Directly from VSCode. Do your debugging and development easily.

Contrast is All You Need For High-Fidelity Text-to-Image Diffusion Models [CVPR 2024]

Official implementation of project NoiseCLR, published at CVPR 2024

PyTorch implementation of One-step Diffusion with Distribution Matching Distillation

Official code for "Amodal Completion via Progressive Mixed Context Diffusion" [CVPR 2024 Highlight]

METU CENG796 Deep Generative Models 2024-Spring Course Projects

[NeurIPS 2024] Official Implementation of CLIPAway

[CVPR 2025 Highlight] Reference-Based 3D-Aware Image Editing with Triplanes

[ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation

DivSem proposes an end-to-end framework that can encode visible and partially visible objects with a novel mechanism to achieve consistency in the style encoding.

Foundational Models for State-of-the-Art Speech and Text Translation

A collection of pre-trained StyleGAN 2 models to download

PyTorch tutorial notebooks for beginners.

A novel inpainting framework that can remove objects from images based on the instructions given as text prompts.

Implementation for the works "VecGAN: Image-to-Image Translation with Interpretable Latent Directions" (ECCV 2022) and "Face Attribute Editing with Disentangled Latent Vectors"

In this project, we aim to use Generative Adversarial Network (GAN) model in order to predict the stock prices from a time series data.