Bilinear models of parts and appearances in generative adversarial networks

[PDF] arxiv.org

MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistance

D Meng, C Tzelepis, I Patras… - arXiv preprint arXiv …, 2024 - arxiv.org
Generating human portraits is a hot topic in the image generation area, eg mask-to-face
generation and text-to-face generation. However, these unimodal generation methods lack …
相关文章 所有 3 个版本
[PDF] arxiv.org

Are CLIP features all you need for Universal Synthetic Image Origin Attribution?

D Cioni, C Tzelepis, L Seidenari, I Patras - arXiv preprint arXiv:2408.09153, 2024 - arxiv.org
The steady improvement of Diffusion Models for visual synthesis has given rise to many new
and interesting use cases of synthetic images but also has raised concerns about their …
相关文章 所有 4 个版本