CraftGraffiti: Exploring Human Identity with Custom Graffiti Art via Facial-Preserving Diffusion Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Banerjee, Ayan, Vilariño, Fernando, Lladós, Josep
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915930655686656
author Banerjee, Ayan
Vilariño, Fernando
Lladós, Josep
author_facet Banerjee, Ayan
Vilariño, Fernando
Lladós, Josep
contents Preserving facial identity under extreme stylistic transformation remains a major challenge in generative art. In graffiti, a high-contrast, abstract medium, subtle distortions to the eyes, nose, or mouth can erase the subject's recognizability, undermining both personal and cultural authenticity. We present CraftGraffiti, an end-to-end text-guided graffiti generation framework designed with facial feature preservation as a primary objective. Given an input image and a style and pose descriptive prompt, CraftGraffiti first applies graffiti style transfer via LoRA-fine-tuned pretrained diffusion transformer, then enforces identity fidelity through a face-consistent self-attention mechanism that augments attention layers with explicit identity embeddings. Pose customization is achieved without keypoints, using CLIP-guided prompt extension to enable dynamic re-posing while retaining facial coherence. We formally justify and empirically validate the "style-first, identity-after" paradigm, showing it reduces attribute drift compared to the reverse order. Quantitative results demonstrate competitive facial feature consistency and state-of-the-art aesthetic and human preference scores, while qualitative analyses and a live deployment at the Cruilla Festival highlight the system's real-world creative impact. CraftGraffiti advances the goal of identity-respectful AI-assisted artistry, offering a principled approach for blending stylistic freedom with recognizability in creative AI applications.
format Preprint
id arxiv_https___arxiv_org_abs_2508_20640
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CraftGraffiti: Exploring Human Identity with Custom Graffiti Art via Facial-Preserving Diffusion Models
Banerjee, Ayan
Vilariño, Fernando
Lladós, Josep
Computer Vision and Pattern Recognition
Preserving facial identity under extreme stylistic transformation remains a major challenge in generative art. In graffiti, a high-contrast, abstract medium, subtle distortions to the eyes, nose, or mouth can erase the subject's recognizability, undermining both personal and cultural authenticity. We present CraftGraffiti, an end-to-end text-guided graffiti generation framework designed with facial feature preservation as a primary objective. Given an input image and a style and pose descriptive prompt, CraftGraffiti first applies graffiti style transfer via LoRA-fine-tuned pretrained diffusion transformer, then enforces identity fidelity through a face-consistent self-attention mechanism that augments attention layers with explicit identity embeddings. Pose customization is achieved without keypoints, using CLIP-guided prompt extension to enable dynamic re-posing while retaining facial coherence. We formally justify and empirically validate the "style-first, identity-after" paradigm, showing it reduces attribute drift compared to the reverse order. Quantitative results demonstrate competitive facial feature consistency and state-of-the-art aesthetic and human preference scores, while qualitative analyses and a live deployment at the Cruilla Festival highlight the system's real-world creative impact. CraftGraffiti advances the goal of identity-respectful AI-assisted artistry, offering a principled approach for blending stylistic freedom with recognizability in creative AI applications.
title CraftGraffiti: Exploring Human Identity with Custom Graffiti Art via Facial-Preserving Diffusion Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.20640