AI based multi-label girl image classification system, implemented by using TensorFlow.

Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀

LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.

Official implementation of Dynamic Sparse Local Patch Transformer

SPIGA: Shape Preserving Facial Landmarks with Graph Attention Networks.

A curated collection of fun and creative examples generated with Nano Banana & Nano Banana Pro🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the commu…

Official PyTorch implementation for the paper Generalizable Face Landmarking Guided by Conditional Face Warping (CVPR 2024).

[NeurIPS 2023] PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance

Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning

[CVPR 2023] STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection

The repo of Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection(WACV2025)

Create 3DGS heads from latent vectors

This is the official implementation of "The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing"

Official PyTorch implementation of Retrieve in Style: Unsupervised Facial Feature Transfer and Retrieval.

Total Selfie: Generating Full-Body Selfies, CVPR 2024 (Highlight)

Get started quickly with Next.js, Postgres, StepPay, and shadcn/ui.

[CVPR2025] FFaceNeRF: Few-shot Face Editing in Neural Radiance Fields

OFER: Occluded Face Expression Reconstruction. A 3D face reconstruction method producing diverse plausible expressive faces from a single-view occluded image.

FaceScape (PAMI2023 & CVPR2020)

Everything about the SmolLM and SmolVLM family of models

Real-time image filter engine based on GPU

[CVPR 2025 Highlight] Official implementation of "MangaNinja: Line Art Colorization with Precise Reference Following"

Janus-Series: Unified Multimodal Understanding and Generation Models

Summary of publicly available ressources such as code, datasets, and scientific papers for the FLAME 3D head model

.

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models