paper-with-me

Papers

A Prompt Log Analysis of Text-to-Image Generation Systems

2023-03-08 · Yutong Xie, Zhaoying Pan, Jinge Ma, Luo Jie, Qiaozhu Mei

Recent developments in large language models (LLM) and generative AI have unleashed the astonishing capabilities of text-to-image generation systems to synthesize high-quality images that are faithful to a given reference text, known as a "prompt". These systems have immediately received lots of attention from researchers, creators, and common users. Despite the plenty of efforts to improve the generative models, there is limited work on understanding the information needs of the users of these systems at scale. We conduct the first comprehensive analysis of large-scale prompt logs collected from multiple text-to-image generation systems. Our work is analogous to analyzing the query logs of Web search engines, a line of work that has made critical contributions to the glory of the Web search industry and research. Compared with Web search queries, text-to-image prompts are significantly longer, often organized into special structures that consist of the subject, form, and intent of the generation tasks and present unique categories of information needs. Users make more edits within creation sessions, which present remarkable exploratory patterns. There is also a considerable gap between the user-input prompts and the captions of the images included in the open training data of the generative models. Our findings provide concrete implications on how to improve text-to-image generation systems for creation purposes.

📄 PDF Abstract BibTeX arXiv:2303.04587

Code (1)

zhaoyingpan/prompt_log_analysis 공식 구현

Tasks

Image GenerationText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity

2023-08-11 · Melissa Hall, Candace Ross, Adina Williams, Nicolas Carion 외

The unprecedented photorealistic results achieved by recent text-to-image generative systems and their increasing use as plug-and-play content creation solutions make it crucial to understand their potential biases. In t…

BenchmarkingDiversityImage Generation

Capability-aware Prompt Reformulation Learning for Text-to-Image Generation

2024-03-27 · Jingtao Zhan, Qingyao Ai, Yiqun Liu, Jia Chen 외

Text-to-image generation systems have emerged as revolutionary tools in the realm of artistic creation, offering unprecedented ease in transforming textual prompts into visual art. However, the efficacy of these systems …

Image GenerationText to Image GenerationText-to-Image Generation

No Longer Trending on Artstation: Prompt Analysis of Generative AI Art

2024-01-24 · Jon McCormack, Maria Teresa Llano, Stephen James Krol, Nina Rajcic

Image generation using generative AI is rapidly becoming a major new source of visual media, with billions of AI generated images created using diffusion models such as Stable Diffusion and Midjourney over the last few y…

Image Generation

FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation

2024-10-24 · Christopher T. H Teo, Milad Abdollahzadeh, Xinda Ma, Ngai-Man Cheung

Recently, prompt learning has emerged as the state-of-the-art (SOTA) for fair text-to-image (T2I) generation. Specifically, this approach leverages readily available reference images to learn inclusive prompts for each t…

AttributeDenoisingFairnessImage Generation+3

Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models

2025-01-12 · Michael Toker, Ido Galil, Hadas Orgad, Rinon Gal 외

Text-to-image (T2I) diffusion models rely on encoded prompts to guide the image generation process. Typically, these prompts are extended to a fixed length by adding padding tokens before text encoding. Despite being a d…

Image Generation