Stars
HeartMuLa Official Repo: The Most Powerful Open-Source Music Generation Model of 2026
Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO
[ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling
[SIGGRAPH Asia 2024] BSDF importance sampling using a diffusion model
Official Repo: Is There a Better Source Distribution than Gaussian? Exploring Source Distributions for Image Flow Matching
We present FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6$\times$ acceleration in inference speed.
Official Repository of paper: "MotionEdit: Benchmarking and Learning Motion-Centric Image Editing"
[NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
3D structure generation in Minecraft, powered by fal.ai
The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)
"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"
Wrapper of 50+ image matching models with a unified interface
MoCha: End-to-End Video Character Replacement without Structural Guidance
[ICLR 2026] Trace Anything: Representing Any Video in 4D via Trajectory Fields
TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's …
The official implementation of Attentive Convolution.
adefossez / demucs
Forked from facebookresearch/demucsCode for the paper Hybrid Spectrogram and Waveform Source Separation
A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.
[Preprint 2025] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset
[ICLR 2026] rCM: SOTA JVP-Based Diffusion Distillation & Few-Step Video Generation & Scaling Up sCM/MeanFlow