diffusion

An easy to understand TTS / SVS / SVC framework

HY-SOAR:Self-Correction for Optimal Alignment and Refinement in Diffusion Models

Omega-AI：基于java打造的深度学习框架，帮助你快速搭建神经网络，实现模型推理与训练，引擎支持自动求导，多线程与GPU运算，GPU支持CUDA，CUDNN。

[ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention

A unified framework for easy fine-tuning in Flow-Matching models

Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]

[ECCV 2026] A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.

[CVPR 2025] RollingDepth: Video Depth without Video Models

[TIP2026] Official codes of CCSRv2 and CCSRv1: Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution

Yet another PyTorch implementation of Stable Diffusion (probably easy to read)

📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉

Official implementation for "Blended Diffusion for Text-driven Editing of Natural Images" [CVPR 2022]

An AI framework for generating and modding osu! beatmaps for all gamemodes from spectrogram inputs.

[AAAI2024] FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning

A high-performance framework for training LLMs, VLMs, diffusion, and embodied models on NVIDIA GPUs and Kunlun XPUs.

[WACV'25 Oral] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think