Measuring Style Similarity in Diffusion Models
Generative models are now widely used by graphic designers and artists. Prior works have shown that these models remember and often replicate content from their training data during generation. Hence as their proliferation increases, it has become important to perform a database search to determine whether the properties of the image are attributable to specific training data, every time before a generated image is used for professional purposes. Existing tools for this purpose focus on retrieving images of similar semantic content. Meanwhile, many artists are concerned with style replication in text-to-image models. We present a framework for understanding and extracting style descriptors from images. Our framework comprises a new dataset curated using the insight that style is a subjective property of an image that captures complex yet meaningful interactions of factors including but not limited to colors, textures, shapes, etc. We also propose a method to extract style descriptors that can be used to attribute style of a generated image to the images used in the training dataset of a text-to-image model. We showcase promising results in various style retrieval tasks. We also quantitatively and qualitatively analyze style attribution and matching in the Stable Diffusion model. Code and artifacts are available at https://github.com/learn2phoenix/CSD.
Code (1)
Tasks
AttributeStyle DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DiffSim: Taming Diffusion Models for Evaluating Visual Similarity
Diffusion models have fundamentally transformed the field of generative models, making the assessment of similarity between customized model outputs and reference inputs critically important. However, traditional percept…
Contrastive LearningDenoisingSelf-Supervised LearningSemantic Similarity+1Perceptual Similarity for Measuring Decision-Making Style and Policy Diversity in Games
Defining and measuring decision-making styles, also known as playstyles, is crucial in gaming, where these styles reflect a broad spectrum of individuality and diversity. However, finding a universally applicable measure…
Atari GamesBoard GamesCar RacingDecision Making+4StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion
The rapid development of large-scale text-to-speech (TTS) models has led to significant advancements in modeling diverse speaker prosody and voices. However, these models often face issues such as slow inference speeds, …
Speech Synthesistext-to-speechText to SpeechText-To-Speech SynthesisLearning Style Similarity for Searching Infographics
Infographics are complex graphic designs integrating text, images, charts and sketches. Despite the increasing popularity of infographics and the rapid growth of online design portfolios, little research investigates how…
Image RetrievalRetrievalSTELLAR: Scene Text Editor for Low-Resource Languages and Real-World Data
Scene Text Editing (STE) is the task of modifying text content in an image while preserving its visual style, such as font, color, and background. While recent diffusion-based approaches have shown improvements in visual…