End-to-End Object Detection with Transformers

Official Implementations for Paper - MagicQuill: An Intelligent Interactive Image Editing System

High-resolution models for human tasks.

Scaling Properties of Diffusion Models For Perceptual Tasks

🎥 Command line video player

Let's finetune video generation models!

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion

Training-free Regional Prompting for Diffusion Transformers 🔥

A suite of image and video neural tokenizers

Grounding Image Matching in 3D with MASt3R

GenXD: Generating Any 3D and 4D Scenes

MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

ZIM: Zero-Shot Image Matting for Anything

Adobe-EntitySeg dataset

No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

霞鹜臻楷：基于「霞鹜文楷」衍生，前期手动加粗调整字形，后期由 AI 生成字形辅助补字的开源中文字体。

🧡 Follow your favorites in one inbox

MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes; NeurIPS 2024; Official code

Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组

3D Reconstruction for all

A project leveraging Stable Diffusion and attention mechanisms to remove specific objects from images. By manipulating attention maps during the diffusion process, it allows targeted object removal…

The codes of our paper "ObjectAdd: Adding Objects into Image via a Training-Free Diffusion Modification Fashion"

Focus on prompting and generating

🔥🔥🔥 Set the world of 3D faces on fire with INFERNO 🔥🔥🔥

Joint image and Depth inpainting, ldm3d

The best OSS video generation models