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] Follow-Your-Click: This repo is the official implementation of "Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts"
Video generation from text&image, 1st-gen
A system of bots that collects clips automatically via custom made filters, lets you easily browse these clips, and puts them together into a compilation video ready to be uploaded straight to any social media platform. Full VPS support is provided, along with an accounts system so multiple users can use the bot at once. This bot is split up into three separate programs. The server. The client. The video generator. These programs perform different functions that when combined creates a very powerful system for auto generating compilation videos.
Official repo for VideoComposer: Compositional Video Synthesis with Motion Controllability
Fine-Grained Open Domain Image Animation with Motion Guidance
[AAAI 2026] EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation
SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations (CVPR 2026 Findings)
[ECCV 2024 Oral] MotionDirector: Motion Customization of Text-to-Video Diffusion Models.
Wunjo CE: Face Swap, Lip Sync, Control Remove Objects & Text & Background, Restyling, Audio Separator, Clone Voice, Video Generation. Open Source, Local & Free.
Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.
Code for SCIS-2025 Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a reference image and audio.
A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.
Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators
[AAAI 2024] Follow-Your-Pose: This repo is the official implementation of "Follow-Your-Pose : Pose-Guided Text-to-Video Generation using Pose-Free Videos"
Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch
Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment
Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"
Official implementations for paper: DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising
24,535 repositories in the index in total.
