Lists (3)
Stars
MAGI-2-preview: Scaling Video Generation Models Efficiently
Bark is an iOS App which allows you to push custom notifications to your iPhone
Write HTML. Render video. Built for agents.
A plug-and-play compiler that delivers free-lunch optimizations for both inference and training.
An agentic skills framework & software development methodology that works.
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
Out of time: automated lip sync in the wild
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
How to use our public wav2vec2 dimensional emotion model
Wan: Open and Advanced Large-Scale Video Generative Models
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
MoviiGen 1.1: Towards Cinematic-Quality Video Generative Models
[NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving
(CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
[ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis
Lets make video diffusion practical!
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
[NeurIPS 2024] Boosting the performance of consistency models with PCM!
GLaDOS Checkin Automatically
Scalable and memory-optimized training of diffusion models
johndpope / nemo
Forked from neeek2303/EMOPortraits"Swimmin' in the money, come and find me, Nemo"
wip - running some training with overfitting - https://wandb.ai/snoozie/vasa-overfitting
Using Claude Opus to reverse engineer code from MegaPortraits: One-shot Megapixel Neural Head Avatars