MegaPortrait: Revisiting Diffusion Control for High-fidelity Portrait Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Han, Anagnostidis, Sotiris, Simsar, Enis, Hofmann, Thomas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909379412885504
author Yang, Han
Anagnostidis, Sotiris
Simsar, Enis
Hofmann, Thomas
author_facet Yang, Han
Anagnostidis, Sotiris
Simsar, Enis
Hofmann, Thomas
contents We propose MegaPortrait. It's an innovative system for creating personalized portrait images in computer vision. It has three modules: Identity Net, Shading Net, and Harmonization Net. Identity Net generates learned identity using a customized model fine-tuned with source images. Shading Net re-renders portraits using extracted representations. Harmonization Net fuses pasted faces and the reference image's body for coherent results. Our approach with off-the-shelf Controlnets is better than state-of-the-art AI portrait products in identity preservation and image fidelity. MegaPortrait has a simple but effective design and we compare it with other methods and products to show its superiority.
format Preprint
id arxiv_https___arxiv_org_abs_2411_04357
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MegaPortrait: Revisiting Diffusion Control for High-fidelity Portrait Generation
Yang, Han
Anagnostidis, Sotiris
Simsar, Enis
Hofmann, Thomas
Computer Vision and Pattern Recognition
We propose MegaPortrait. It's an innovative system for creating personalized portrait images in computer vision. It has three modules: Identity Net, Shading Net, and Harmonization Net. Identity Net generates learned identity using a customized model fine-tuned with source images. Shading Net re-renders portraits using extracted representations. Harmonization Net fuses pasted faces and the reference image's body for coherent results. Our approach with off-the-shelf Controlnets is better than state-of-the-art AI portrait products in identity preservation and image fidelity. MegaPortrait has a simple but effective design and we compare it with other methods and products to show its superiority.
title MegaPortrait: Revisiting Diffusion Control for High-fidelity Portrait Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.04357