The paper introduces AnchorCache, a parameter‑free token‑layout and attention‑mask design that decouples reference tokens from the target in in‑context diffusion transformers. By inserting static text anchors, the method conditions reference representations on the instruction during cache construction, enabling exact key‑value reuse across denoising steps. To restore quality lost by this structural change, the authors employ teacher‑forced velocity distillation followed by a brief on‑policy stage, achieving full‑attention quality while delivering up to 6.40× speedup in diffusion transformer inference across image, speech, and video benchmarks.
By Yangshuai Liu, Zheming Li, Jiaao Li, Kang He, Ziliang Lai, Zhitai Liu, Chengru Song
arXiv:2610.35566v1 Announce Type: new
Abstract: Image editors built on diffusion transformers (DiTs), such as Flux Kontext, make it possible to turn a single photograph into a convincing manipulated...
By Salma Abdel Magid, Sanghyuk Chun, Eric Slyman, Kushal Kafle, Olga Russakovsky
ToDoPro introduces an early token‑reduction strategy for reference‑based image generation that uses a few denoising steps on 2× downsampled reference images to probe token importance with the existing Diffusion Transformer. Tokens are then hierarchically pruned: low‑importance tokens are discarded, mid‑importance tokens are replaced by their downsampled versions, and high‑importance tokens are retained. Experiments on three base models and two benchmarks show significant inference speedups, reduced peak GPU memory, and improved generation quality by filtering out noisy reference tokens.
By Caiyi Sun, Yujing Sun, Siu-Ming Yiu
arXiv:2610.07720v1 Announce Type: cross
Abstract: Multi-reference image generation requires preserving the appearance of multiple subjects while composing them into a coherent scene. However, existin...
By Wanning He, Yuyao Zhang, Yu-Wing Tai
arXiv:2602. 05305v3 Announce Type: replace-cross Abstract: Generating long-form content, such as minute-long videos and extended texts, is increasingly important for modern generative models.
By Zhuokun Chen, Jianfei Cai, Bohan Zhuang
Reference-based diffusion models enable highly controllable image generation by leveraging elements from input images to guide prompt-driven synthesis. However, these models are computationally expensive in runtime, and their cost scales severely with the number of input references.
arXiv:2610.08772v1 Announce Type: new
Abstract: Diffusion Transformers (DiTs) have achieved strong performance in image and video generation, but the quadratic complexity of full attention makes high...
By Liao Ma, Jiayi Song, Yunfeng Wu, Songhua Liu, Peilin Zhao
Autoregressive image generation has emerged as a paradigm for multimodal AI systems due to its compatibility with transformer-based LLM serving infrastructures. However, generating thousands of visual...
Subject-driven image personalization---generating new images that preserve the identity of one or several reference subjects in novel scenes---is a foundational capability for modern visual content creation. It is currently dominated by generalized methods that fine-tune a pretrained multimodal diffusion transformer (MMDiT) on hundreds of thousands to millions of paired \emph{(reference, composed-target)} examples, where each composed target is a synthesized image of the subject in a novel scene.
arXiv:2606. 14125v1 Announce Type: cross Abstract: Inversion-based image editing offers flexible and training-free control but still struggles with inversion accuracy and the trade-off between editing fidelity and background preservation.
By Zheyuan Zhan, Hongchen Li, Can Wang, Yinfei Ma, Mingzhen Huang, Ruoshi Bai, Jiawei Chen, Siwei Lyu, Defang Chen
The paper investigates how attention sparsity behaves in autoregressive image generation, finding a distinct diagonal sparsity pattern due to spatial locality of visual tokens. It introduces a diagonal‑aware sparse attention mechanism that skips KV entries along the diagonal within a recent window, achieving up to 3.1× higher throughput and 1.19× lower latency with less than 2% quality loss compared to dense inference.
By Daeun Kim, Junwha Hong, Changhun Oh, Yoonsung Kim, Yoonhyeong Lee, Jongse Park
arXiv:2606. 13898v1 Announce Type: cross Abstract: Creative image editing tools, such as Photoshop's Remove or Generative Fill buttons, are central to everyday customer use and account for a major share of traffic in Photoshop and Lightroom.
By Haoran You, Yotam Nitzan, Lingzhi Zhang, Yifan Gong, Mang-Tik Chiu, Connelly Barnes, Yan Kang, Yuqian Zhou, Eli Shechtman, Sohrab Amirghodsi