paper-with-me

Papers

Prompt Refinement with Image Pivot for Text-to-Image Generation

2024-06-28 · Jingtao Zhan, Qingyao Ai, Yiqun Liu, Yingwei Pan, Ting Yao, Jiaxin Mao, Shaoping Ma, Tao Mei

For text-to-image generation, automatically refining user-provided natural language prompts into the keyword-enriched prompts favored by systems is essential for the user experience. Such a prompt refinement process is analogous to translating the prompt from "user languages" into "system languages". However, the scarcity of such parallel corpora makes it difficult to train a prompt refinement model. Inspired by zero-shot machine translation techniques, we introduce Prompt Refinement with Image Pivot (PRIP). PRIP innovatively uses the latent representation of a user-preferred image as an intermediary "pivot" between the user and system languages. It decomposes the refinement process into two data-rich tasks: inferring representations of user-preferred images from user languages and subsequently translating image representations into system languages. Thus, it can leverage abundant data for training. Extensive experiments show that PRIP substantially outperforms a wide range of baselines and effectively transfers to unseen systems in a zero-shot manner.

📄 PDF Abstract BibTeX arXiv:2407.00247

Code (1)

jingtaozhan/promptreformulate 공식 구현 pytorch

Tasks

Image GenerationMachine TranslationText to Image GenerationText-to-Image GenerationZero-Shot Machine Translation

Similar Papers 제목 키워드 기반

Test-time Prompt Refinement for Text-to-Image Models

2025-07-22 · Mohammad Abdul Hafeez Khan, Yash Jain, Siddhartha Bhattacharyya, Vibhav Vineet arxiv

Text-to-image (T2I) generation models have made significant strides but still struggle with prompt sensitivity: even minor changes in prompt wording can yield inconsistent or inaccurate outputs. To address this challenge…

Image Generation

Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement

2025-02-24 · Suchae Jeong, Inseong Choi, Youngsik Yun, Jihie Kim

Text-to-Image models, including Stable Diffusion, have significantly improved in generating images that are highly semantically aligned with the given prompts. However, existing models may fail to produce appropriate ima…

Image GenerationText to Image GenerationText-to-Image Generation

Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation

2023-10-12 · Zhengyuan Yang, JianFeng Wang, Linjie Li, Kevin Lin 외

We introduce ``Idea to Image,'' a system that enables multimodal iterative self-refinement with GPT-4V(ision) for automatic image design and generation. Humans can quickly identify the characteristics of different text-t…

PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset

2024-03-17 · CVPR 2025 1 · Jiazhen Liu, Yuhan Fu, Ruobing Xie, Runquan Xie 외

Multimodal Large Language Models (MLLMs) hallucinate, resulting in an emerging topic of visual hallucination evaluation (VHE). This paper contributes a ChatGPT-Prompted visual hallucination evaluation Dataset (PhD) for o…

AttributeCommon Sense ReasoningHallucinationHallucination Evaluation+2

Iterative Prompt Refinement for Safer Text-to-Image Generation

2025-09-17 · Jinwoo Jeon, JunHyeok Oh, Hayeong Lee, Byung-Jun Lee arxiv

Text-to-Image (T2I) models have made remarkable progress in generating images from text prompts, but their output quality and safety still depend heavily on how prompts are phrased. Existing safety methods typically refi…

Text-to-Image Generation