SGLang is a high-performance serving framework for large language models and multimodal models.
Repository Index
111,820 visible repositories in the index
1–12 of 12 · Most stars
OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.
- super-resolution
- inpainting
- matting
- image-generation
TranslatedGenerate all kinds of short videos in batches with one click using AI, automatically remix short videos in batches, and automatically publish videos to Douyin, Kuaishou, Xiaohongshu, and Video Accounts (WeChat Channels). Making money has never been this easy! Supports local voice models chatTTS, fasterwhisper, GPTSoVITS, and cloud voice services: Azure, Alibaba Cloud, Tencent Cloud. Supports Stable diffusion and comfyUI for direct AI image generation. Generate short videos with one click using AI LLM,print money together! support:chatTTS,faster-whisper,GPTSoVITS,Azure,tencent Cloud,Ali Cloud.
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
- ai-infra
- diffusion-models
- inference-acceleration
- rcm
A denoising autoencoder + adversarial losses and attention mechanisms for face swapping.
- face-swap
- generative-adversarial-network
- gan
- gans
Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch
- artificial-intelligence
- attention-mechanisms
- deep-learning
- text-to-video
[CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional decoder.
- diffusion-models
- video-super-resolution
- video-restoration
[TMLR 2025] Latte: Latent Diffusion Transformer for Video Generation.
PALLAIDIUM — a generative AI movie studio, seamlessly integrated into the Blender Video Editor (VSE), enabling end-to-end production from script to screen and back.
- text2video
- blender
- text2audio
- text2image
We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.
- diffusion-models
- high-resolution
- sparse-attention
- video-generation
Dandere2x - Fast Waifu2x Video Upscaling.
- waifu2x
- faster
- video
- fast
[SIGGRAPH Asia 2026] 4DAnyone: Create Anyone in 4D from a Casual Monocular Video
- 4d-gaussian-splatting
- generative-ai
- generative-model
- video-generation