Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Video synthesis and editing, talking heads, avatars, animation and 3D asset generation.
Signals: video-generation, text-to-video, video-editing, animation, talking-head, avatar, deepfake, lip-sync
331 results
[AAAI 2025] EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
Awesome iOS guides from the community, shared on Flawless iOS Medium blog 👉
List of recent advances for human avatars, including generation, reconstruction, and editing, etc.
[CVPR 2025] Official implementation of "Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation"
TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes
[NeurIPS 2023] Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation
[CVPR 2024 Highlight] Code for "HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting"
GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation
[NeurIPS 2025 Spotlight] A Native Multimodal LLM for 3D Generation and Understanding
(ICCV 2023) official repository for "Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation"
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction (ICCV 2025)
T3Bench: Benchmarking Current Progress in Text-to-3D Generation
Roblox Foundation Model for 3D Intelligence
ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation (NeurIPS 2023 Spotlight)
Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model
From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
[ICLR 2024 Oral] Generative Gaussian Splatting for Efficient 3D Content Creation
Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.
Long-Inference, High Quality Synthetic Speaker (AI avatar/ AI presenter)
Talking Head (3D): A JavaScript class for real-time lip-sync using full-body 3D avatars.
Implementation of Lumiere, SOTA text-to-video generation from Google Deepmind, in Pytorch
🎥 Create youtube videos from a text prompt in seconds
24,535 repositories in the index in total.
