Nexus: Structured Synergy for Efficient Text-to-Image Generation using Rectified Flow Model
On the map: Diffusion models → Image generation, text-to-image and editing
Abstract (arXiv)
Diffusion and flow matching models have made significant progress in text-to-image generation, yet high computation, quadratic complexity, and large memory footprint hinder high-resolution synthesis and edge deployment. We propose Nexus, which integrates sparse architecture, linear complexity, and low-bit quantization. It combines MoE feed-forward layers, gated DeltaNet attention, and per-expert low-bit training to reduce computation and memory. Their joint optimization allows Nexus to achieve generation quality comparable to mainstream models such as SDXL and SD3 while delivering markedly higher inference efficiency. Experiments on COCO and LAION validate its effectiveness.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 23 of its 30 references that are in the map. First posted on arXiv 17 Aug 2026.
Builds on
23 of 30 references.
Closest ancestors · 4
Same direction, newest first
- 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space17 Jun
- 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding14 May
- 2023MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices28 Nov
- 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds1 Jun
Other references · 19
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2022Scalable Diffusion Models with Transformerscited by 6,054
- 2022Flow Matching for Generative Modelingcited by 5,702
- 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
- 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
- 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
- 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
- 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
- 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 846
7 more
- 2023RWKV: Reinventing RNNs for the Transformer Eracited by 827
- 2024Gated Delta Networks: Improving Mamba2 with Delta Rulecited by 532
- 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 502
- 2024DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesiscited by 72
- 2024Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Modelscited by 41
- 2026Qwen-Image-2.0 Technical Reportcited by 36
- 2026Asymmetric Flow Modelscited by 8
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024EdgeFusion: On-Device Text-to-Image Generation
- 2026Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
- 2025Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
- 2025FlowTok: Flowing Seamlessly Across Text and Image Tokens
- 2025Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis
- 2026NanoFLUX: Distillation-Driven Compression of Large Text-to-Image Generation Models for Mobile Devices
- 2026FullFlow: Upgrading Text-to-Image Flow Matching Models for Bidirectional Vision--Language Generation
- 2025DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation