Retail photography imposes specific requirements on images. For instance, images may need uniform background colors, consistent model poses, centered products, and consistent lighting. Minor deviations from these standards impact a site’s aesthetic appeal, making the images unsuitable for use. We show that Stable Diffusion methods, as currently applied, do not respect these requirements. The usual practice of training the denoiser with a very noisy image and starting inference with a sample of pure noise leads to inconsistent generated images during inference. This inconsistency occurs because it is easy to tell the difference between samples of the training and inference distributions. As a result, a network trained with centered retail product images with uniform backgrounds generates images with erratic backgrounds. The problem is easily fixed by initializing inference with samples from an approximation of noisy images. However, in using such an approximation, the joint distribution of text and noisy image at inference time still slightly differs from that at training time. This discrepancy is corrected by training the network with samples from the approximate noisy image distribution. Extensive experiments on real application data show significant qualitative and quantitative improvements in performance from adopting these procedures. Finally, our procedure can interact well with other control-based methods to further enhance the controllability of diffusion-based methods.

This paper shows how to impose rendering policies on a virtual try-on (VTON) pipeline. Our rendering policies are lightweight procedural descriptions of how the pipeline should render outfits or render particular types of garments. Our policies are procedural expressions describing offsets to the control points for each set of garment types. The policies are easily authored and are generalizable to any outfit composed of garments of similar types. We describe a VTON pipeline that accepts our policies to modify garment drapes and produce high-quality try-on images with garment attributes preserved.Layered outfits are a particular challenge to VTON systems because learning to coordinate warps between multiple garments so that nothing sticks out is difficult. Our rendering policies offer a lightweight and effective procedure to achieve this coordination, while also allowing precise manipulation of drape. Drape describes the way in which a garment is worn (for example, a shirt could be tucked or untucked).Quantitative and qualitative evaluations demonstrate that our method allows effective manipulation of drape and produces significant measurable improvements in rendering quality for complicated layering interactions.

Abstract Text-to-image (TTI) models provide huge innovation ability for many industries, while the content security triggered by them has also attracted wide attention. Considerable research has focused on content security threats of large language models (LLMs), yet comprehensive studies on the content security of TTI models are notably scarce. This paper introduces a systematic tool, named EvilPromptFuzzer, designed to fuzz evil prompts in TTI models. For 15 kinds of fine-grained risks, EvilPromptFuzzer employs the strong knowledge-mining ability of LLMs to construct seed banks, in which the seeds cover various types of characters, interrelations, actions, objects, expressions, body parts, locations, surroundings, etc. Subsequently, these seeds are fed into the LLMs to build scene-diverse prompts, which can weaken the semantic sensitivity related to the fine-grained risks. Hence, the prompts can bypass the content audit mechanism of the TTI model, and ultimately help to generate images with inappropriate content. For the risks of violence, horrible, disgusting, animal cruelty, religious bias, political symbol, and extremism, the efficiency of EvilPromptFuzzer for generating inappropriate images based on DALL.E 3 are greater than 30%, namely, more than 30 generated images are malicious among 100 prompts. Specifically, the efficiency of horrible, disgusting, political symbols, and extremism up to 58%, 64%, 71%, and 50%, respectively. Additionally, we analyzed the vulnerability of existing popular content audit platforms, including Amazon, Google, Azure, and Baidu. Even the most effective Google SafeSearch cloud platform identifies only 33.85% of malicious images across three distinct categories.

Virtual dressing room applications help online shoppers visualize outfits. Such a system, to be commercially viable, must satisfy a set of performance criteria. The system must produce high quality images that faithfully preserve garment properties, allow users to mix and match garments of various types and support human models varying in skin tone, hair color, body shape, and so on. This paper describes POVNet, a framework that meets all these requirements (except body shapes variations). Our system uses warping methods together with residual data to preserve garment texture at fine scales and high resolution. Our warping procedure adapts to a wide range of garments and allows swapping in and out of individual garments. A learned rendering procedure using an adversarial loss ensures that fine shading, etc. is accurately reflected. A distance transform representation ensures that hems, cuffs, stripes, and so on are correctly placed. We demonstrate improvements in garment rendering over state of the art resulting from these procedures. We demonstrate that the framework is scalable, responds in real-time, and works robustly with a variety of garment categories. Finally, we demonstrate that using this system as a virtual dressing room interface for fashion e-commerce websites has significantly boosted user-engagement rates.

Virtual try-on methods aim to generate images of fashion models wearing arbitrary combinations of garments. This is a challenging task because the generated image must appear realistic and accurately display the interaction between garments. Prior works produce images that are filled with artifacts and fail to capture important visual details necessary for commercial applications. We propose Outfit Visualization Net (OVNet) to capture these important details (e.g. buttons, shading, textures, realistic hemlines, and interactions between garments) and produce high quality multiple-garment virtual try-on images. OVNet consists of 1) a semantic layout generator and 2) an image generation pipeline using multiple coordinated warps. We train the warper to output multiple warps using a cascade loss, which refines each successive warp to focus on poorly generated regions of a previous warp and yields consistent improvements in detail. In addition, we introduce a method for matching outfits with the most suitable model and produce significant improvements for both our and other previous try-on methods. Through quantitative and qualitative analysis, we demonstrate our method generates substantially higher-quality studio images compared to prior works for multi-garment outfits. An interactive interface powered by this method has been deployed on fashion e-commerce websites and received overwhelmingly positive feedback.

As the Internet and the big data system evolve rapidly, the deployment of distributed applications becomes widespread, promoting the development of Distributed File System (DFS). The existing defense technologies for DFS, such as detection or patching, mainly aim to protect the system from known attacks and vulnerabilities. However, it is difficult for those systems to solve the growing security issues from the unknown threats due to their passiveness and hysteresis. In this paper, we propose MDFS, a mimic defense theory based architecture for DFS with the capability to improve the data security. Mimic Defense (MD), a proactive defense embedded in MDFS, emphasizes dynamism, heterogeneity and redundancy. The key benefits of MD are transferring the attack surface as well as increasing the cost of modification.

Ceph is a reliable, scalable, unified distributed storage system, and recently has become one of OpenStack's standard open source storage solutions. For the reason of the low performance, Ceph Filesystem (Cephfs) cannot employ erasure codes directly, especially for binary Reed-Solomon (BRS) codes, whose size of the parity block is larger than that of the data block. To address these problems, we implemented efficient BRS codes, and filled the gap between BRS codes and Cephfs by a simple conversion. In addition to that, an efficient framework consisting of filesystem, cache tier and storage tier was adopted in Ceph to ensure that the file data is finally stored with the erasure coding technology. The experimental results show that such a design spends a small amount of additional cost but obtains much better effects.