Lists (1)
Stars
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
[CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
(NeurIPS 2025) Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation
Edit-R1: Reinforce Image Editing with Diffusion Negative-Aware Finetuning and MLLM Implicit Feedback
DiffusionNFT: Online Diffusion Reinforcement with Forward Process
MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting
Unlimited-length talking video generation that supports image-to-video and video-to-video generation
A collection of paper/projects that trains flow matching model/policies via RL.
Fundamentals of Digital Media Technology(04713901) | Peking University ECE Course Materials
Efficient Triton Kernels for LLM Training
Official repository for the UAE paper, unified-GRPO, and unified-Bench
Minimal PyTorch implementation of TP, SP, and FSDP
High quality training free inpaint for every stable diffusion model. Supports ComfyUI
PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)
Odysseus: Playground of LLM Sequence Parallelism
USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
Tiny-FSDP, a minimalistic re-implementation of the PyTorch FSDP
🔊 Text-Prompted Generative Audio Model
Official inference code and LongText-Bench benchmark for our paper X-Omni (https://arxiv.org/pdf/2507.22058).
GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset