Metraipolis › archive › dc_01ccae2f96a6
A Large-scale Evaluation of Text-guided Models for Facial Editing — arXiv:2608.28802
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28802
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:47:16.194Z
- SHA-256 of the archived text
29ce3124f19c1dc0adf777a732b83e6dd487f6ffc4d2b35600facc9f5048ba78- Stable URL of this page
https://metraipolis.com/documento/dc_01ccae2f96a6
How to cite
A Large-scale Evaluation of Text-guided Models for Facial Editing — arXiv:2608.28802 — arXiv (en), https://arxiv.org/abs/2608.28802 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_01ccae2f96a6 (Metraipolis archive dc_01ccae2f96a6, sha256 29ce3124f19c1dc0adf777a732b83e6dd487f6ffc4d2b35600facc9f5048ba78)
BibTeX
@misc{dc01ccae2f96a6,
title = {A Large-scale Evaluation of Text-guided Models for Facial Editing — arXiv:2608.28802},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28802},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_01ccae2f96a6; sha256 29ce3124f19c1dc0adf777a732b83e6dd487f6ffc4d2b35600facc9f5048ba78},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28802. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Facial appearance editing powers popular applications like FaceApp and Photoshop. Generative Adversarial Networks (GANs) and 3D Morphable Models (3DMMs) have been widely used for facial editing. GANs can perform varied facial edits (e.g., changing hair color, hairstyle), but often produce unstable edits. 3DMMs produce stable edits, but can only alter pose and facial expression. Recently, text-guided diffusion models like Nano Banana have become popular for image editing. Text-guided models are a compelling alternative to GANs and 3DMMs since they can produce both stable and varied image edits. While text-guided models have been widely tested for whole-scene edits (e.g., ``make the woman play a guitar''), they have not been comprehensively tested for facial editing. We conducted the first large-scale evaluation ($\sim1$M images evaluated) of six popular text-guided models on a sequential facial editing task. We present Face-Edit-Attributes, the largest collection of $169$ facial editing attributes focused on hair, accessories, and pose edits. We compared model performance using two popular celebrity face datasets: CelebA and CelebSET. Our results show that most models performed hair and accessory edits well, but struggled with editing pose. All models over-edit (e.g., changing hair color when asked only to change the hairstyle). We also evaluated demographic biases in each model. Our results show surprising biases in overediting: almost all models created more overedits for dark-skinned male faces and old faces. The code and data for our results (including our repository of $\sim 1$M images) can be accessed \href{ this https URL }{\textcolor{blue}{here}}.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.28802 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T07:28:26.684Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).