TIPO: Text to Image with Text Presampling for Prompt Optimization
TIPO (Text to Image with text pre-sampling for Prompt Optimization) is an innovative framework designed to enhance text-to-image (T2I) generation by language model (LM) for automatic prompt engineering. By refining and extending user-provided prompts, TIPO bridges the gap between simple inputs and the detailed prompts required for high-quality image generation. Unlike previous approaches that rely on Large Language Models (LLMs) or reinforcement learning (RL), TIPO adjusts user input prompts with the distribution of a trained prompt dataset, eliminating the need for complex runtime cost via lightweight model. This pre-sampling approach enables efficient and scalable prompt optimization, grounded in the model's training distribution. Experimental results demonstrate TIPO's effectiveness in improving aesthetic scores, reducing image corruption, and better aligning generated images with dataset distributions. These findings highlight the critical role of prompt engineering in T2I systems and open avenues for broader applications of automatic prompt refinement.
Code (1)
Tasks
Image GenerationLanguage ModelingLanguage ModellingPrompt EngineeringReinforcement Learning (RL)Similar Papers 제목 키워드 기반
CreatiPoster: Towards Editable and Controllable Multi-Layer Graphic Design Generation
Graphic design plays a crucial role in both commercial and personal contexts, yet creating high-quality, editable, and aesthetically pleasing graphic compositions remains a time-consuming and skill-intensive task, especi…
Multipoint-BAX: A New Approach for Efficiently Tuning Particle Accelerator Emittance via Virtual Objectives
Although beam emittance is critical for the performance of high-brightness accelerators, optimization is often time limited as emittance calculations, commonly done via quadrupole scans, are typically slow. Such calculat…
Bayesian OptimizationContent Based Image Indexing and Retrieval
In this paper, we present the efficient content based image retrieval systems which employ the color, texture and shape information of images to facilitate the retrieval process. For efficient feature extraction, we extr…
Content-Based Image RetrievalEdge DetectionImage CompressionImage Retrieval+1Multipole Attention for Efficient Long Context Reasoning
Large Reasoning Models (LRMs) have shown promising accuracy improvements on complex problem-solving tasks. While these models have attained high accuracy by leveraging additional computation at test time, they need to ge…
Fast Multipole Attention: A Divide-and-Conquer Attention Mechanism for Long Sequences
Transformer-based models have achieved state-of-the-art performance in many areas. However, the quadratic complexity of self-attention with respect to the input length hinders the applicability of Transformer-based model…
Language ModelingLanguage Modelling