OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

NVIDIA Linux open GPU with P2P support

Lumina-T2X is a unified framework for Text to Any Modality Generation

An uroboros program with 100+ programming languages

AdamW for bfloat16 weights with stochastic rounding

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Swift app demonstrating Core ML Stable Diffusion

Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>

Implementation of MagViT2 Tokenizer in Pytorch

A general fine-tuning kit geared toward diffusion models.

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer