paper-with-me

Papers

TextLap: Customizing Language Models for Text-to-Layout Planning

2024-10-09 · Jian Chen, Ruiyi Zhang, Yufan Zhou, Jennifer Healey, Jiuxiang Gu, Zhiqiang Xu, Changyou Chen

Automatic generation of graphical layouts is crucial for many real-world applications, including designing posters, flyers, advertisements, and graphical user interfaces. Given the incredible ability of Large language models (LLMs) in both natural language understanding and generation, we believe that we could customize an LLM to help people create compelling graphical layouts starting with only text instructions from the user. We call our method TextLap (text-based layout planning). It uses a curated instruction-based layout planning dataset (InsLap) to customize LLMs as a graphic designer. We demonstrate the effectiveness of TextLap and show that it outperforms strong baselines, including GPT-4 based methods, for image generation and graphical design benchmarks.

📄 PDF Abstract BibTeX arXiv:2410.12844

Code (1)

puar-playground/TextLap 공식 구현 pytorch

Tasks

Image GenerationNatural Language Understanding

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Attention 설명 없음
Adam 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

LayoutGPT: Compositional Visual Planning and Generation with Large Language Models

2023-05-24 · NeurIPS 2023 11 · Weixi Feng, Wanrong Zhu, Tsu-Jui Fu, Varun Jampani 외

Attaining a high degree of user controllability in visual generation often requires intricate, fine-grained inputs like layouts. However, such inputs impose a substantial burden on users when compared to simple text inpu…

Image GenerationIndoor Scene SynthesisText to Image GenerationText-to-Image Generation

PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models

2025-03-13 · Runze He, Bo Cheng, Yuhang Ma, Qingxiang Jia 외

In this paper, we propose a unified layout planning and image generation model, PlanGen, which can pre-plan spatial layout conditions before generating images. Unlike previous diffusion-based models that treat layout pla…

Image GenerationImage ManipulationLayout-to-Image Generation

UniSparse: An Intermediate Language for General Sparse Format Customization

2024-03-09 · Jie Liu, Zhongyuan Zhao, Zijian Ding, Benjamin Brock 외

The ongoing trend of hardware specialization has led to a growing use of custom data formats when processing sparse workloads, which are typically memory-bound. These formats facilitate optimized software/hardware implem…

AttributeCode GenerationCPUGPU

MusicLayout: Explicit Structural Planning for Controllable Text-to-Music Generation

2026-08-10 · Shuyu Li, Kejun Zhang, Jiahe Lei, Shulei Ji 외 arxiv

Text-to-music generation has advanced rapidly, but current systems still rely primarily on global text prompts, leaving the structural organization of generated music implicit and difficult to inspect, control, or revise…

Text-to-Music GenerationAudio Generation

LayoutAgent: A Vision-Language Agent Guided Compositional Diffusion for Spatial Layout Planning

2025-09-24 · Zezhong Fan, Xiaohan Li, Luyi Ma, Kai Zhao 외 arxiv

Designing realistic multi-object scenes requires not only generating images, but also planning spatial layouts that respect semantic relations and physical plausibility. On one hand, while recent advances in diffusion mo…

Spatial ReasoningImage Generation