🚀 Convert Xiaomi Mimo AI into an OpenAI-compatible API for deep thinking applications, easily installable on multiple platforms.

🎥 Generate high-quality video editing data with Ditto, a scalable pipeline that trains advanced instruction-based editing models.

[AAAI 2026] EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation

[ACM MM 2025] Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis

About [ICMR 2025] CFSynthesis: Controllable and Free-view 3D Human Video Synthesis

MoDA: Multi-modal Diffusion Architecture for Talking Head Generation

[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation

[AAAI 2025] EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

Official Code for "CanonicalFusion: Generating Drivable 3D Human Avatars from Multiple Images (ECCV 2024)"

Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"

[ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

PyTorch implementation of the human neural rendering in unseen positions presented at WACV 2022 "Creating and Reenacting Controllable 3D Humans with Differentiable Rendering"