FLUX

In the model registry

Timeline

1. Oct 8, 2026 · Research paper · 1 source
   Deflating the Hessian: Rank-4 W4A4 Quantization for Multimodal Diffusion Transformers
   In diffusion transformers, low-rank branches can mitigate 4-bit weight--activation (W4A4) post-training quantization (PTQ) loss by decomposing each weight into a low-bit residual and a high-precision low-rank component.
2. Oct 8, 2026 · Research paper · 1 source
   When Scene Text Hijacks the Scene: Uncovering, Exploiting, and Mitigating Rendered-Text Semantic Leakage in Image Generation Models
   In this work, we study rendered-text semantic leakage, a largely overlooked phenomenon in open-domain text rendering.
3. Oct 7, 2026 · Research paper · 2 sources
   Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning
   Pixel-space diffusion models avoid the lossy VAE of latent models, which suggests an advantage on downstream tasks where fine-grained detail matters.
4. Oct 6, 2026 · Research paper · 1 source
   Backend-Agnostic Sparse Attention for Fast High-Resolution Visual Generation
   To tackle these challenges, we propose BASA, a backend-agnostic sparse attention, which brings the best of both worlds: visual quality and practical acceleration.
5. Oct 6, 2026 · Research paper · 1 source
   Two Halves are More than One: Phase-wise Velocity Distillation for Fast and High-Quality Image Generation
   Recent diffusion-based image generation backbones have grown substantially in scale, making the network inference cost increase rapidly.
6. Oct 6, 2026 · Research paper · 1 source
   RefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial Routing
   We present RefRoute, a framework that addresses both reference representation cost and attention overhead through two complementary mechanisms.
7. Oct 2, 2026 · Open-source release · 1 source
   sgl-project/sglang v0.5.21
   | Model | Type | Cookbook |
8. Sep 29, 2026 · Research paper · 1 source
   How Diffusion Controller unifies and simplifies AI image generation
   We introduce Diffusion Controller, a lightweight "steering damper" network that precisely steers image generation to achieve significantly better prompt alignment.
9. Jun 13, 2026 · Open-source release · 1 source
   sgl-project/sglang v0.5.13
   DeepSeek V4 — context parallelism & sparse-attention kernels: Building on the v0.5.12 Day-0 path, v0.5.13 extends DeepSeek-V4 to context-parallel serving and adds its sparse-attention kernels:
10. May 5, 2026 · Open-source release · 1 source
    sgl-project/sglang v0.5.11
    Speculative Decoding V2 by default: Spec V2 (with overlap scheduling to hide CPU overhead) is now the default, materially reducing per-step CPU cost for EAGLE/MTP/DFLASH paths: #21062
11. Jan 23, 2026 · Open-source release · 1 source
    sgl-project/sglang v0.5.8
    Qwen3-VL-Embedding & Qwen3-VL-Reranker model support: #16635, #16403

Often appears with