[Free GPT-4]
[PDF] arxiv.org

FonTS: Text Rendering with Typography and Style Controls

W Shi, Y Song, D Zhang, J Liu, X Zou - arxiv preprint arxiv:2412.00136, 2024 - arxiv.org
Visual text images are prevalent in various applications, requiring careful font selection and
typographic choices. Recent advances in Diffusion Transformer (DiT)-based text-to-image …
Zapisz Cytuj Powiązane artykuły Wszystkie wersje 2 Wersja HTML
[Free GPT-4]
[PDF] arxiv.org

Multi-Class Textual-Inversion Secretly Yields a Semantic-Agnostic Classifier

K Wang, F Yang, B Raducanu… - arxiv preprint arxiv …, 2024 - arxiv.org
With the advent of large pre-trained vision-language models such as CLIP, prompt learning
methods aim to enhance the transferability of the CLIP model. They learn the prompt given …
Zapisz Cytuj Powiązane artykuły Wszystkie wersje 2 Wersja HTML