Tootfinder

heise | Vom Text zum Bild: So funktioniert Stable Diffusion
Das frei verfügbare Stable Diffusion generiert aus Texten realitätsnahe und detailreiche Bilder. Wir erklären, wie die KI arbeitet.
https://www.

AMD and Stability AI launch the industry's first Stable Diffusion 3.0 Medium AI model optimized for AMD's XDNA 2 NPUs, designed to run locally on Ryzen laptops (Anton Shilov/Tom's Hardware)

AMD unveils industry-first Stable Diffusion 3.0 Medium AI model generator tailored for XDNA 2 NPUs — designed to run locally on Ryzen AI laptops
An offline image generator for XDNA 2 NPUs.

rd-spiral: An open-source Python library for learning 2D reaction-diffusion dynamics through pseudo-spectral method
Sandy H. S. Herho, Iwan P. Anwar, Rusmawan Suwarman
https://arxiv.org/abs/2506.20633

rd-spiral: An open-source Python library for learning 2D reaction-diffusion dynamics through pseudo-spectral method
We introduce rd-spiral, an open-source Python library for simulating 2D reaction-diffusion systems using pseudo-spectral methods. The framework combines FFT-based spatial discretization with adaptive Dormand-Prince time integration, achieving exponential convergence while maintaining pedagogical clarity. We analyze three dynamical regimes: stable spirals, spatiotemporal chaos, and pattern decay, revealing extreme non-Gaussian statistics (kurtosis $>96$) in stable states. Information-theoretic m…

heise | macOS: Stable Diffusion in die eigene App integrieren
Ohne Training, aber mit dem vollen Potenzial von Apples Hardware: So binden Sie den Text-zu-Bild-Generator in Ihre eigene App ein.
https://www.

Q&A with Stability AI CEO Prem Akkaraju on taking over from Emad Mostaque, his movie background, data and copyright, working with creative industries, and more (Melissa Heikkilä/Financial Times)
https://www.ft.com/content/fc4cb659-bf01-4f68-a828-40ff98c24e51

AI ‘a great opportunity for artists’ says head of Stable Diffusion owner
The boss of StablityAI insists film industry fears about the impact of the popular image-generating model are misplaced

Efficient and Robust Semantic Image Communication via Stable Cascade
Bilal Khalid, Pedro Freire, Sergei K. Turitsyn, Jaroslaw E. Prilepsky
https://arxiv.org/abs/2507.17416

Efficient and Robust Semantic Image Communication via Stable Cascade
Diffusion Model (DM) based Semantic Image Communication (SIC) systems face significant challenges, such as slow inference speed and generation randomness, that limit their reliability and practicality. To overcome these issues, we propose a novel SIC framework inspired by Stable Cascade, where extremely compact latent image embeddings are used as conditioning to the diffusion process. Our approach drastically reduces the data transmission overhead, compressing the transmitted embedding to just …

SustainDiffusion: Optimising the Social and Environmental Sustainability of Stable Diffusion Models
Giordano d'Aloisio, Tosin Fadahunsi, Jay Choy, Rebecca Moussa, Federica Sarro
https://arxiv.org/abs/2507.15663

SustainDiffusion: Optimising the Social and Environmental Sustainability of Stable Diffusion Models
Background: Text-to-image generation models are widely used across numerous domains. Among these models, Stable Diffusion (SD) - an open-source text-to-image generation model - has become the most popular, producing over 12 billion images annually. However, the widespread use of these models raises concerns regarding their social and environmental sustainability. Aims: To reduce the harm that SD models may have on society and the environment, we introduce SustainDiffusion, a search-based appr…

Explicit Monotone Stable Super-Time-Stepping Methods for Finite Time Singularities
Zheng Tan, Tariq D. Aslam, Andrea L. Bertozzi
https://arxiv.org/abs/2507.17062 https://…

Explicit Monotone Stable Super-Time-Stepping Methods for Finite Time Singularities
We explore a novel way to numerically resolve the scaling behavior of finite-time singularities in solutions of nonlinear parabolic PDEs. The Runge--Kutta--Legendre (RKL) and Runge--Kutta--Gegenbauer (RKG) super-time-stepping methods were originally developed for nonlinear complex physics problems with diffusion. These are multi-stage single step second-order, forward-in-time methods with no implicit solves. The advantage is that the timestep size for stability scales with stage number $s$ as $…

Probabilistic approximation of fully nonlinear second-order PIDEs with convergence rates for the universal robust limit theorem
Lianzi Jiang, Mingshang Hu, Gechun Liang
https://arxiv.org/abs/2506.18374

Probabilistic approximation of fully nonlinear second-order PIDEs with convergence rates for the universal robust limit theorem
This paper develops a probabilistic approximation scheme for a class of nonstandard, fully nonlinear second-order partial integro-differential equations (PIDEs) arising from nonlinear Lévy processes under Peng's G-expectation framework. The PIDE involves a supremum over a set of \(α\)-stable Lévy measures, potentially with degenerate diffusion and a non-separable uncertainty set, which renders existing numerical results inapplicable. We construct a recursive, piecewise-constant approximation…

Concept Unlearning by Modeling Key Steps of Diffusion Process
Chaoshuo Zhang, Chenhao Lin, Zhengyu Zhao, Le Yang, Qian Wang, Chao Shen
https://arxiv.org/abs/2507.06526

Concept Unlearning by Modeling Key Steps of Diffusion Process
Text-to-image diffusion models (T2I DMs), represented by Stable Diffusion, which generate highly realistic images based on textual input, have been widely used. However, their misuse poses serious security risks. While existing concept unlearning methods aim to mitigate these risks, they struggle to balance unlearning effectiveness with generative retainability.To overcome this limitation, we innovatively propose the Key Step Concept Unlearning (KSCU) method, which ingeniously capitalizes on th…

DLSF: Dual-Layer Synergistic Fusion for High-Fidelity Image Syn-thesis
Zhen-Qi Chen, Yuan-Fu Yang
https://arxiv.org/abs/2507.13388 https://

DLSF: Dual-Layer Synergistic Fusion for High-Fidelity Image Syn-thesis
With the rapid advancement of diffusion-based generative models, Stable Diffusion (SD) has emerged as a state-of-the-art framework for high-fidelity im-age synthesis. However, existing SD models suffer from suboptimal feature aggregation, leading to in-complete semantic alignment and loss of fine-grained details, especially in highly textured and complex scenes. To address these limitations, we propose a novel dual-latent integration framework that en-hances feature interactions between the bas…

Taming Stable Diffusion for Computed Tomography Blind Super-Resolution
Chunlei Li, Yilei Shi, Haoxi Hu, Jingliang Hu, Xiao Xiang Zhu, Lichao Mou
https://arxiv.org/abs/2506.11496

Taming Stable Diffusion for Computed Tomography Blind Super-Resolution
High-resolution computed tomography (CT) imaging is essential for medical diagnosis but requires increased radiation exposure, creating a critical trade-off between image quality and patient safety. While deep learning methods have shown promise in CT super-resolution, they face challenges with complex degradations and limited medical training data. Meanwhile, large-scale pre-trained diffusion models, particularly Stable Diffusion, have demonstrated remarkable capabilities in synthesizing fine …

SD-Acc: Accelerating Stable Diffusion through Phase-aware Sampling and Hardware Co-Optimizations
Zhican Wang, Guanghui He, Hongxiang Fan
https://arxiv.org/abs/2507.01309

SD-Acc: Accelerating Stable Diffusion through Phase-aware Sampling and Hardware Co-Optimizations
The emergence of diffusion models has significantly advanced generative AI, improving the quality, realism, and creativity of image and video generation. Among them, Stable Diffusion (StableDiff) stands out as a key model for text-to-image generation and a foundation for next-generation multi-modal algorithms. However, its high computational and memory demands hinder inference speed and energy efficiency. To address these challenges, we identify three core issues: (1) intensive and often redund…

When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting
Xiaodong Wu, Tianyi Tang, Xiangman Li, Jianbing Ni, Yong Yu
https://arxiv.org/abs/2507.03646

When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting
Watermarking has emerged as a promising solution to counter harmful or deceptive AI-generated content by embedding hidden identifiers that trace content origins. However, the robustness of current watermarking techniques is still largely unexplored, raising critical questions about their effectiveness against adversarial attacks. To address this gap, we examine the robustness of model-specific watermarking, where watermark embedding is integrated with text-to-image generation in models like lat…

EXPO: Stable Reinforcement Learning with Expressive Policies
Perry Dong, Qiyang Li, Dorsa Sadigh, Chelsea Finn
https://arxiv.org/abs/2507.07986 https://arxiv.org/pdf/2507.07986 https://arxiv.org/html/2507.07986
arXiv:2507.07986v1 Announce Type: new
Abstract: We study the problem of training and fine-tuning expressive policies with online reinforcement learning (RL) given an offline dataset. Training expressive policy classes with online RL present a unique challenge of stable value maximization. Unlike simpler Gaussian policies commonly used in online RL, expressive policies like diffusion and flow-matching policies are parameterized by a long denoising chain, which hinders stable gradient propagation from actions to policy parameters when optimizing against some value function. Our key insight is that we can address stable value maximization by avoiding direct optimization over value with the expressive policy and instead construct an on-the-fly RL policy to maximize Q-value. We propose Expressive Policy Optimization (EXPO), a sample-efficient online RL algorithm that utilizes an on-the-fly policy to maximize value with two parameterized policies -- a larger expressive base policy trained with a stable imitation learning objective and a light-weight Gaussian edit policy that edits the actions sampled from the base policy toward a higher value distribution. The on-the-fly policy optimizes the actions from the base policy with the learned edit policy and chooses the value maximizing action from the base and edited actions for both sampling and temporal-difference (TD) backup. Our approach yields up to 2-3x improvement in sample efficiency on average over prior methods both in the setting of fine-tuning a pretrained policy given offline data and in leveraging offline data to train online.
toXiv_bot_toot

Process-aware and high-fidelity microstructure generation using stable diffusion
Hoang Cuong Phan, Minh Tien Tran, Chihun Lee, Hoheok Kim, Sehyok Oh, Dong-Kyu Kim, Ho Won Lee
https://arxiv.org/abs/2507.00459

Process-aware and high-fidelity microstructure generation using stable diffusion
Synthesizing realistic microstructure images conditioned on processing parameters is crucial for understanding process-structure relationships in materials design. However, this task remains challenging due to limited training micrographs and the continuous nature of processing variables. To overcome these challenges, we present a novel process-aware generative modeling approach based on Stable Diffusion 3.5 Large (SD3.5-Large), a state-of-the-art text-to-image diffusion model adapted for micro…

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor
Vatsal Agarwal, Matthew Gwilliam, Gefen Kohavi, Eshan Verma, Daniel Ulbricht, Abhinav Shrivastava
https://arxiv.org/abs/2507.07106

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor
Recent advances in multimodal large language models (MLLMs) have enabled image-based question-answering capabilities. However, a key limitation is the use of CLIP as the visual encoder; while it can capture coarse global information, it often can miss fine-grained details that are relevant to the input query. To address these shortcomings, this work studies whether pre-trained text-to-image diffusion models can serve as instruction-aware visual encoders. Through an analysis of their internal re…

A gradient-enhanced approach for stable finite element approximations of reaction-convection-diffusion problems
Soheil Firooz, B. Daya Reddy, Paul Steinmann
https://arxiv.org/abs/2506.01873

A gradient-enhanced approach for stable finite element approximations of reaction-convection-diffusion problems
We develop a micromorphic-based approach for finite element stabilization of reaction-convection-diffusion equations, by gradient enhancement of the field of interest via introducing an auxiliary variable. The well-posedness of the coupled-field approach is established, together with an error estimate. Through a set of 1D and 2D numerical examples the high accuracy and enhanced stability of the approach in approximating solutions associated with complex problems is demonstrated, for situations …

Diffusion and heat dissipation in marginally stable linear time-delayed Langevin systems
Xin Wang
https://arxiv.org/abs/2506.23939 https://

Diffusion and heat dissipation in marginally stable linear time-delayed Langevin systems
We investigate the dynamics and heat dissipation in marginally stable linear time-delayed Langevin systems. We analytically characterize two distinct critical classes: (i) diffusive criticality, where the variance grows linearly with suppressed/enhanced diffusion due to time-delayed forces, and (ii) oscillatory criticality, exhibiting oscillations with diffusing amplitude. Crucially, we derive asymptotic heat dissipation rates, revealing fundamentally different thermodynamic signatures: a const…

Music Boomerang: Reusing Diffusion Models for Data Augmentation and Audio Manipulation
Alexander Fichtinger, Jan Schl\"uter, Gerhard Widmer
https://arxiv.org/abs/2507.04864

Music Boomerang: Reusing Diffusion Models for Data Augmentation and Audio Manipulation
Generative models of music audio are typically used to generate output based solely on a text prompt or melody. Boomerang sampling, recently proposed for the image domain, allows generating output close to an existing example, using any pretrained diffusion model. In this work, we explore its application in the audio domain as a tool for data augmentation or content manipulation. Specifically, implementing Boomerang sampling for Stable Audio Open, we augment training data for a state-of-the-art…

I heard they were working on a middle ground between flat earthers and scientists. What's that supposed to be? Cubic earth??
#humor #flatearth #science

Enhancing Food-Domain Question Answering with a Multimodal Knowledge Graph: Hybrid QA Generation and Diversity Analysis
Srihari K B, Pushpak Bhattacharyya
https://arxiv.org/abs/2507.06571

Enhancing Food-Domain Question Answering with a Multimodal Knowledge Graph: Hybrid QA Generation and Diversity Analysis
We propose a unified food-domain QA framework that combines a large-scale multimodal knowledge graph (MMKG) with generative AI. Our MMKG links 13,000 recipes, 3,000 ingredients, 140,000 relations, and 14,000 images. We generate 40,000 QA pairs using 40 templates and LLaVA/DeepSeek augmentation. Joint fine-tuning of Meta LLaMA 3.1-8B and Stable Diffusion 3.5-Large improves BERTScore by 16.2\%, reduces FID by 37.8\%, and boosts CLIP alignment by 31.1\%. Diagnostic analyses-CLIP-based mismatch det…

ME: Trigger Element Combination Backdoor Attack on Copyright Infringement
Feiyu Yang, Siyuan Liang, Aishan Liu, Dacheng Tao
https://arxiv.org/abs/2506.10776

ME: Trigger Element Combination Backdoor Attack on Copyright Infringement
The capability of generative diffusion models (DMs) like Stable Diffusion (SD) in replicating training data could be taken advantage of by attackers to launch the Copyright Infringement Attack, with duplicated poisoned image-text pairs. SilentBadDiffusion (SBD) is a method proposed recently, which shew outstanding performance in attacking SD in text-to-image tasks. However, the feasible data resources in this area are still limited, some of them are even constrained or prohibited due to the iss…

FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale
Boris Bonev, Thorsten Kurth, Ankur Mahesh, Mauro Bisson, Jean Kossaifi, Karthik Kashinath, Anima Anandkumar, William D. Collins, Michael S. Pritchard, Alexander Keller
https://arxiv.org/abs/2507.12144…

FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale
FourCastNet 3 advances global weather modeling by implementing a scalable, geometric machine learning (ML) approach to probabilistic ensemble forecasting. The approach is designed to respect spherical geometry and to accurately model the spatially correlated probabilistic nature of the problem, resulting in stable spectra and realistic dynamics across multiple scales. FourCastNet 3 delivers forecasting accuracy that surpasses leading conventional ensemble models and rivals the best diffusion-ba…

This https://arxiv.org/abs/2405.20032 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csNI_…

Promptus: Can Prompts Streaming Replace Video Streaming with Stable Diffusion
With the exponential growth of video traffic, traditional video streaming systems are approaching their limits in compression efficiency and communication capacity. To further reduce bitrate while maintaining quality, we propose Promptus, a disruptive semantic communication system that streaming prompts instead of video content, which represents real-world video frames with a series of "prompts" for delivery and employs Stable Diffusion to generate videos at the receiver. To ensure that the gen…

A fourth-order exponential time differencing scheme with real and distinct poles rational approximation for solving non-linear reaction-diffusion systems
Wisdom Kwame Attipoe, Andreas Kleefeld, Emmanuel Asante-Asamani
https://arxiv.org/abs/2507.01245

A fourth-order exponential time differencing scheme with real and distinct poles rational approximation for solving non-linear reaction-diffusion systems
A fourth-order, L-stable, exponential time differencing Runge-Kutta type scheme is developed to solve nonlinear systems of reaction diffusion equations with nonsmooth data. The new scheme, ETDRK4RDP, is constructed by approximating the matrix exponentials in the ETDRK4 scheme with a fourth order, L-acceptable, non-Padé rational function having real and distinct poles (RDP). Using RDP rational functions to construct the scheme ensures efficient damping of spurious oscillations arising from non-…

Noise Consistency Regularization for Improved Subject-Driven Image Synthesis
Yao Ni, Song Wen, Piotr Koniusz, Anoop Cherian
https://arxiv.org/abs/2506.06483

Noise Consistency Regularization for Improved Subject-Driven Image Synthesis
Fine-tuning Stable Diffusion enables subject-driven image synthesis by adapting the model to generate images containing specific subjects. However, existing fine-tuning methods suffer from two key issues: underfitting, where the model fails to reliably capture subject identity, and overfitting, where it memorizes the subject image and reduces background diversity. To address these challenges, we propose two auxiliary consistency losses for diffusion fine-tuning. First, a prior consistency regul…

GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models
Zilong Wang, Xiang Zheng, Xiaosen Wang, Bo Wang, Xingjun Ma, Yu-Gang Jiang
https://arxiv.org/abs/2506.10047

GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models
Text-to-image (T2I) models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety risks. While most platforms employ content moderation systems, underlying vulnerabilities can still be exploited by determined adversaries. Recent research on red-teaming and adversarial attacks against T2I models has notable limitations: some studies succes…

This https://arxiv.org/abs/2402.10346 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Wavelet compressed, modified Hilbert transform in the space-time discretization of the heat equation
On a finite time interval $(0,T)$, we consider the multiresolution Galerkin discretization of a modified Hilbert transform $\mathcal H_T$ which arises in the space-time Galerkin discretization of the linear diffusion equation. To this end, we design spline-wavelet systems in $(0,T)$ consisting of piecewise polynomials of degree $\geq 1$ with sufficiently many vanishing moments which constitute Riesz bases in the Sobolev spaces $H^{s}_{0,}(0,T)$ and $H^{s}_{,0}(0,T)$. These bases provide stable …

This https://arxiv.org/abs/2505.04411 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_nli…

Turbulence spreading and anomalous diffusion on combs
This paper presents a simple model for such processes as chaos spreading or turbulence spillover into stable regions. In this simple model the essential transport occurs via inelastic resonant interactions of waves on a lattice. The process is shown to result universally in a subdiffusive spreading of the wave field. The dispersion of this spreading process is found to depend exclusively on the type of the interaction process (three- or four-wave), but not on a particular instability behind. Th…