[ECCV 2026] The official implementation of paper "PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion"

[ECCV 2026] Official implementation of Hi-DiT: Hybrid Latent-Pixel Diffusion Transformer for Image Generation

Official JAX code of MiniT2I.

A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.

Ideogram 4: Open image model at the forefront of design

Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation

SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles

[NeurIPS 2025] Official implementation for our paper "Scaling Diffusion Transformers Efficiently via μP".

Train the smallest LM you can that fits in 16MB. Best model wins!

Fast, accurate & comprehensive text measurement & layout

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

AI agents running research on single-GPU nanochat training automatically

[ICML'26] Code and website for Self-Flow: Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis

NextFlow🚀: Unified Sequential Modeling Activates Multimodal Understanding and Generation

Qwen-Image-Layered: Layered Decomposition for Inherent Editablity

A research-friendly PyTorch Lightning toolkit for training, fine-tuning, and evaluating AutoencoderKL for Stable Diffusion and FLUX.

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …

[ICLR 2026] Official repo of paper "Reconstruction Alignment Improves Unified Multimodal Models". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Lear…

Ming - facilitating advanced multimodal understanding and generation capabilities built upon the Ling LLM.

[NeurIPS 2025] Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation

[Fully open] [Encoder-free MLLM] Vision as LoRA

Awesome Layout Generation

The official repository for LaCTok:Latent Consistency Tokenizer for High-resolution Image Reconstruction and Generation by 256 Tokens

Enjoy the magic of Diffusion models!

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

Open-source SOTA multi-image editing model