Saved in:
Bibliographic Details
Main Authors: Palaev, Andrey, Khan, Adil, Kazmi, Syed M. Ahsan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.14046
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912202401775616
author Palaev, Andrey
Khan, Adil
Kazmi, Syed M. Ahsan
author_facet Palaev, Andrey
Khan, Adil
Kazmi, Syed M. Ahsan
contents The advancement of text-to-image synthesis has introduced powerful generative models capable of creating realistic images from textual prompts. However, precise control over image attributes remains challenging, especially at the instance level. While existing methods offer some control through fine-tuning or auxiliary information, they often face limitations in flexibility and accuracy. To address these challenges, we propose a pipeline leveraging Large Language Models (LLMs), open-vocabulary detectors, cross-attention maps and intermediate activations of diffusion U-Net for instance-level image manipulation. Our method detects objects mentioned in the prompt and present in the generated image, enabling precise manipulation without extensive training or input masks. By incorporating cross-attention maps, our approach ensures coherence in manipulated images while controlling object positions. Our method enables precise manipulations at the instance level without fine-tuning or auxiliary information such as masks or bounding boxes. Code is available at https://github.com/Palandr123/DiffusionU-NetLLM
format Preprint
id arxiv_https___arxiv_org_abs_2501_14046
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-guided Instance-level Image Manipulation with Diffusion U-Net Cross-Attention Maps
Palaev, Andrey
Khan, Adil
Kazmi, Syed M. Ahsan
Computer Vision and Pattern Recognition
The advancement of text-to-image synthesis has introduced powerful generative models capable of creating realistic images from textual prompts. However, precise control over image attributes remains challenging, especially at the instance level. While existing methods offer some control through fine-tuning or auxiliary information, they often face limitations in flexibility and accuracy. To address these challenges, we propose a pipeline leveraging Large Language Models (LLMs), open-vocabulary detectors, cross-attention maps and intermediate activations of diffusion U-Net for instance-level image manipulation. Our method detects objects mentioned in the prompt and present in the generated image, enabling precise manipulation without extensive training or input masks. By incorporating cross-attention maps, our approach ensures coherence in manipulated images while controlling object positions. Our method enables precise manipulations at the instance level without fine-tuning or auxiliary information such as masks or bounding boxes. Code is available at https://github.com/Palandr123/DiffusionU-NetLLM
title LLM-guided Instance-level Image Manipulation with Diffusion U-Net Cross-Attention Maps
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.14046