MagIC Research ORG

[CVPR 2024] Official repository for "MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model"

MagicAnimate turns a still photo of a person into a video by animating them to follow a body motion sequence, using a Stable Diffusion model extended to produce temporally consistent frames.

MagicEdit: High-Fidelity Temporally Coherent Video Editing

Official repository for the paper PLLaVA

MagicAvatar: Multimodal Avatar Generation and Animation

PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator (NeurIPS 2024)

BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs

[ICCV2023] Dataset Quantization

No description.

AvatarStudio: High-fidelity and Animatable 3D Avatar Creation from Text

[ICCV 2023] GETAvatar: Generative Textured Meshes for Animatable Human Avatars

Experiencing lightning fast (~1s) and accurate drag-based image editing

[NeurIPS 2023] XAGen: 3D Expressive Human Avatars Generation

[NeurIPS 2024] Image Understanding Makes for A Good Tokenizer for Image Generation

No description.