arXiv Machine Learning September 21, 2026 By Frieder Ganz, Maximilian M\"uller

The Weight Is Over - Interactive Diffusion on Consumer GPUs

Read the original on arXiv Machine Learning →

The paper introduces techniques for efficient on-device diffusion-based image generation on consumer GPUs. It presents an embedding translator that reduces weight and latency by mapping a small text encoder into a larger encoder space, a reproducible sweep recipe for balancing speed, quality, and memory, and an interactive editor that achieves sub‑second time‑to‑first‑image on recent GPUs. These contributions aim to broaden the reach of diffusion pipelines to a wide range of client devices.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers

Jul 21

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack for efficient text-to-image generation and instruction-based image editing.

llms diffusion nlp reinforcement-learning fine-tuning efficiency multimodal benchmarks safety

arXiv Machine Learning

Jun 15

Efficient On-Device Diffusion LLM Inference with Mobile NPU

arXiv:2606. 13740v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) accelerate generation by denoising multiple tokens in parallel, making them attractive for latency-sensitive mobile inference.

By Tuowei Wang, Yanfan Sun, Ju Ren

llms diffusion efficiency

arXiv Computation and Language

1d ago

Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs

Flash-dLLM is a training‑free inference acceleration framework that improves the speed and memory efficiency of Diffusion Large Language Models (dLLMs). It tackles GPU memory I/O bottlenecks by introducing an I/O‑aware fused KV‑cache kernel and then employs a draft‑and‑verify decoding strategy that uses the dLLM itself as both drafter and verifier. Experiments on mathematical reasoning and code‑generation tasks show Flash‑dLLM outperforms existing acceleration methods, achieving up to 11.0× speedups over the Elastic‑Cache baseline.

By Quan Nguyen-Tri, Mukul Ranjan, Zhiqiang Shen

llms diffusion efficiency benchmarks

arXiv AI

Jul 22

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

arXiv:2607. 19064v1 Announce Type: cross Abstract: Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy.

By Xinjie Zhang, Peng Zhang, Shicheng Zheng, Jinghao Guo, Zhaoyang Jia, Yifei Shen, Xun Guo, Yuxuan Luo, Jiahao Li, Wenxuan Xie, Fanyi Pu, Xiaoyi Zhang, Kaichen Zhang, Zongyu Guo, Tianci Bi, Dongnan Gui, Zhening Liu, Zimo Wen, Zihan Zheng, Senqiao Yang, Xiao Li, Jinglu Wang, Bin Li, Yan Lu

llms diffusion nlp reinforcement-learning fine-tuning efficiency multimodal benchmarks safety

arXiv Machine Learning

Aug 3

Paris: A Decentralized Trained Open-Weight Diffusion Model

arXiv:2510. 03434v3 Announce Type: replace-cross Abstract: We present Paris, the first publicly released diffusion model pre-trained entirely through decentralized computation.

By Zhiying Jiang, Raihan Seraj, Marcos Villagra, Bidhan Roy

llms diffusion

arXiv AI

Jun 2

Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference

arXiv:2603. 29002v3 Announce Type: replace-cross Abstract: Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation (RAG), and compressed contextual memory, to support complex reasoning.

By Zifan He, Rui Ma, Yizhou Sun, Jason Cong

llms rag

One email a morning, machine-written

Related stories

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Efficient On-Device Diffusion LLM Inference with Mobile NPU

Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Paris: A Decentralized Trained Open-Weight Diffusion Model

Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference