Sketch-based image synthesis with pre-trained text-to-image models

This paper presents the development of Inpainting with ControlNet - ComfyUI, a novel workflow designed to seamlessly integrate the capabilities of stable diffusion models with ControlNets in the ComfyUI platform. This approach enables users to generate edited images by providing a combination of an...

Full description

Saved in:
Bibliographic Details
Main Author: Ng, Samuel I-Shen
Other Authors: Xingang Pan
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/181525
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-181525
record_format dspace
spelling sg-ntu-dr.10356-1815252024-12-09T07:11:50Z Sketch-based image synthesis with pre-trained text-to-image models Ng, Samuel I-Shen Xingang Pan College of Computing and Data Science xingang.pan@ntu.edu.sg Computer and Information Science Image generation This paper presents the development of Inpainting with ControlNet - ComfyUI, a novel workflow designed to seamlessly integrate the capabilities of stable diffusion models with ControlNets in the ComfyUI platform. This approach enables users to generate edited images by providing a combination of an image, a mask, and a sketch, resulting in coherent and context-aware outputs that closely match the surrounding area. By leveraging the strengths of both stable diffusion models and ControlNets, our method provides a more efficient, effective, and user-friendly approach to image inpainting. The integration of ControlNets with inpainting models allows users to harness the power of text-to-image models while also providing additional guidance through image input, bridging the gap between user intent and the editing process. This solution has far-reaching implications, particularly in the context of image editing and manipulation. Our method has shown promising results, but there are still areas that require further investigation and improvement. Potential avenues for future research include exploring the feasibility of integrating models lacking ControlNets, investigating the benefits and limitations of using different models, and developing strategies for accurately specifying desired colours via a coloured sketch. The potential applications of this approach are vast, and further research and development could lead to even more innovative and powerful tools for image editing and manipulation. Bachelor's degree 2024-12-09T07:11:49Z 2024-12-09T07:11:49Z 2024 Final Year Project (FYP) Ng, S. I. (2024). Sketch-based image synthesis with pre-trained text-to-image models. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/181525 https://hdl.handle.net/10356/181525 en SCSE23-1125 application/pdf application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Computer and Information Science
Image generation
spellingShingle Computer and Information Science
Image generation
Ng, Samuel I-Shen
Sketch-based image synthesis with pre-trained text-to-image models
description This paper presents the development of Inpainting with ControlNet - ComfyUI, a novel workflow designed to seamlessly integrate the capabilities of stable diffusion models with ControlNets in the ComfyUI platform. This approach enables users to generate edited images by providing a combination of an image, a mask, and a sketch, resulting in coherent and context-aware outputs that closely match the surrounding area. By leveraging the strengths of both stable diffusion models and ControlNets, our method provides a more efficient, effective, and user-friendly approach to image inpainting. The integration of ControlNets with inpainting models allows users to harness the power of text-to-image models while also providing additional guidance through image input, bridging the gap between user intent and the editing process. This solution has far-reaching implications, particularly in the context of image editing and manipulation. Our method has shown promising results, but there are still areas that require further investigation and improvement. Potential avenues for future research include exploring the feasibility of integrating models lacking ControlNets, investigating the benefits and limitations of using different models, and developing strategies for accurately specifying desired colours via a coloured sketch. The potential applications of this approach are vast, and further research and development could lead to even more innovative and powerful tools for image editing and manipulation.
author2 Xingang Pan
author_facet Xingang Pan
Ng, Samuel I-Shen
format Final Year Project
author Ng, Samuel I-Shen
author_sort Ng, Samuel I-Shen
title Sketch-based image synthesis with pre-trained text-to-image models
title_short Sketch-based image synthesis with pre-trained text-to-image models
title_full Sketch-based image synthesis with pre-trained text-to-image models
title_fullStr Sketch-based image synthesis with pre-trained text-to-image models
title_full_unstemmed Sketch-based image synthesis with pre-trained text-to-image models
title_sort sketch-based image synthesis with pre-trained text-to-image models
publisher Nanyang Technological University
publishDate 2024
url https://hdl.handle.net/10356/181525
_version_ 1819113007178842112