TexControl: Sketch-Based Two-Stage Fashion Image Generation Using Diffusion Model

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Yongming, Zhang, Tianyu, Xie, Haoran
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929337596379136
author Zhang, Yongming
Zhang, Tianyu
Xie, Haoran
author_facet Zhang, Yongming
Zhang, Tianyu
Xie, Haoran
contents Deep learning-based sketch-to-clothing image generation provides the initial designs and inspiration in the fashion design processes. However, clothing generation from freehand drawing is challenging due to the sparse and ambiguous information from the drawn sketches. The current generation models may have difficulty generating detailed texture information. In this work, we propose TexControl, a sketch-based fashion generation framework that uses a two-stage pipeline to generate the fashion image corresponding to the sketch input. First, we adopt ControlNet to generate the fashion image from sketch and keep the image outline stable. Then, we use an image-to-image method to optimize the detailed textures of the generated images and obtain the final results. The evaluation results show that TexControl can generate fashion images with high-quality texture as fine-grained image generation.
format Preprint
id arxiv_https___arxiv_org_abs_2405_04675
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TexControl: Sketch-Based Two-Stage Fashion Image Generation Using Diffusion Model
Zhang, Yongming
Zhang, Tianyu
Xie, Haoran
Computer Vision and Pattern Recognition
Graphics
Deep learning-based sketch-to-clothing image generation provides the initial designs and inspiration in the fashion design processes. However, clothing generation from freehand drawing is challenging due to the sparse and ambiguous information from the drawn sketches. The current generation models may have difficulty generating detailed texture information. In this work, we propose TexControl, a sketch-based fashion generation framework that uses a two-stage pipeline to generate the fashion image corresponding to the sketch input. First, we adopt ControlNet to generate the fashion image from sketch and keep the image outline stable. Then, we use an image-to-image method to optimize the detailed textures of the generated images and obtain the final results. The evaluation results show that TexControl can generate fashion images with high-quality texture as fine-grained image generation.
title TexControl: Sketch-Based Two-Stage Fashion Image Generation Using Diffusion Model
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2405.04675