paper-with-me

홈 › Papers

Scribble-Guided Diffusion for Training-free Text-to-Image Generation

2024-09-12 · Seonho Lee, Jiho Choi, Seohyun Lim, Jiwook Kim, Hyunjung Shim

Recent advancements in text-to-image diffusion models have demonstrated remarkable success, yet they often struggle to fully capture the user's intent. Existing approaches using textual inputs combined with bounding boxes or region masks fall short in providing precise spatial guidance, often leading to misaligned or unintended object orientation. To address these limitations, we propose Scribble-Guided Diffusion (ScribbleDiff), a training-free approach that utilizes simple user-provided scribbles as visual prompts to guide image generation. However, incorporating scribbles into diffusion models presents challenges due to their sparse and thin nature, making it difficult to ensure accurate orientation alignment. To overcome these challenges, we introduce moment alignment and scribble propagation, which allow for more effective and flexible alignment between generated images and scribble inputs. Experimental results on the PASCAL-Scribble dataset demonstrate significant improvements in spatial control and consistency, showcasing the effectiveness of scribble-based guidance in diffusion models. Our code is available at https://github.com/kaist-cvml-lab/scribble-diffusion.

📄 PDF Abstract BibTeX arXiv:2409.08026

Code (1)

kaist-cvml-lab/scribble-diffusion 공식 구현 pytorch

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

ScribbleEdit: Synthetic Data for Image Editing with Scribbles and Text

2026-05-01 · Anya Ji, George Ma, Téa Wright, Yiming Zhang 외 arxiv

Recent progress in generative models has significantly advanced image editing capabilities, yet precise and intuitive user control remains difficult. Specifically, users often struggle to communicate both exact spatial l…

Image Editing

Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model

2024-07-24 · Lirui Zhao, Tianshuo Yang, Wenqi Shao, Yuxin Zhang 외

This paper addresses an important problem of object addition for images with only text guidance. It is challenging because the new object must be integrated seamlessly into the image with consistent visual context, such …

Image InpaintingObject

ScribbleGen: Generative Data Augmentation Improves Scribble-supervised Semantic Segmentation

2023-11-28 · Jacob Schnell, Jieke Wang, Lu Qi, Vincent Tao Hu 외

Recent advances in generative models, such as diffusion models, have made generating high-quality synthetic images widely accessible. Prior works have shown that training on synthetic images improves many perception task…

Data Augmentationimage-classificationImage Classificationobject-detection+3

High-Fidelity Guided Image Synthesis with Latent Diffusion Models

2022-11-30 · CVPR 2023 1 · Jaskirat Singh, Stephen Gould, Liang Zheng

Controllable image synthesis with user scribbles has gained huge public interest with the recent advent of text-conditioned latent diffusion models. The user scribbles control the color composition while the text prompt …

Image GenerationVocal Bursts Intensity Prediction

BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

2023-07-20 · ICCV 2023 1 · Jinheng Xie, Yuexiang Li, Yawen Huang, Haozhe Liu 외

Recent text-to-image diffusion models have demonstrated an astonishing capacity to generate high-quality images. However, researchers mainly studied the way of synthesizing images with only text prompts. While some works…

Conditional Text-to-Image SynthesisDenoisingImage GenerationText-to-Image Generation