lhd777
Follow
Stars
Unofficial PyTorch implementation of Denoising Diffusion Probabilistic Models
Memory-Guided Diffusion for Expressive Talking Video Generation
Out of time: automated lip sync in the wild
Official Implementations for Paper - MagicQuill: An Intelligent Interactive Image Editing System
[ECCV 2024] PowerPaint, a versatile image inpainting model that supports text-guided object inpainting, object removal, image outpainting and shape-guided object inpainting with only a single model…
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Select a portrait, click to move the head around (please use your own space / GPU!)
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
🎓 Update Talking-Face Research Papers Daily, Now Integrated with LLM Analysis.
MMSA is a unified framework for Multimodal Sentiment Analysis.
GPT4V-level open-source multi-modal model based on Llama3-8B
The official implementation of the ECCV 2024 paper: Continuity Preserving Online CenterLine Graph Learning
ICML'2024 | MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI
[ECCV 2024] Sparse Beats Dense: Rethinking Supervision in Radar-Camera Depth Completion
[ECCV 2024] Official implementation of the paper "X-Pose: Detecting Any Keypoints"
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
The official PyTorch implementation of L2CS-Net for gaze estimation and tracking
[EMNLP 2024] RWKV-CLIP: A Robust Vision-Language Representation Learner
the dataset and code for "Flow-guided One-shot Talking Face Generation with a High-resolution Audio-visual Dataset"
Official implementation of ID-unaware Deepfake Detection Model
Unofficial Implementation of ReplaceAnything: https://aigcdesigngroup.github.io/replace-anything/
[ECCV 2024] HiDiffusion: Increases the resolution and speed of your diffusion model by only adding a single line of code!
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.