Repository Index

SGLang is a high-performance serving framework for large language models and multimodal models.

• cuda
• inference
• llama
• llm

Formerly KrillinAI, VideoTranslation and Dubbing Tool for 120+ Languages. Open-source AI workspace for creators, powered by Codex. Video downloader, video translation, create videos, images, audios, and edits with Agents in one place. For your Social Media like YouTube, TikTok, Instagram, etc.

• video-transcription
• video-translation
• dubbing
• localization

SANA & Sol: Efficient Generative Models and Full-Stack Training & Inference Engines for Image, Video, and World Modeling

• diffusion
• dit
• pytorch
• sana

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

• auto-regressive-model
• diffusion-models
• image-generation
• transformers

SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing

• sdnext
• ai-art
• caption
• diffusers

Taming Transformers for High-Resolution Image Synthesis

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

• artificial-intelligence
• deep-learning
• attention-mechanism
• text-to-image

Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun

• artificial-intelligence
• deep-learning
• transformers
• siren

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

• chinese-nlp
• pretrained-models
• pytorch
• distributed-training

Efficient vision foundation models for high-resolution generation and perception.

• high-resolution
• imagenet
• efficientvit
• segment-anything

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

[ECCV 2026] Official implementation of "HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models"

• diffusion-transformers
• eccv2026
• image-generation
• training-free

Official implementation of "AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers"

• diffusion-models
• efficient-inference
• high-resolution
• image-generation