search

yeungchenwa / FontDiffuser

[AAAI2024] FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning
https://yeungchenwa.github.io/fontdiffuser-homepage/
298 stars 26 forks source link

Does this model support multi words generate? #43

Open RyanHuangNLP opened 8 months ago

RyanHuangNLP commented 8 months ago

I found that it just generate one character

yeungchenwa commented 8 months ago

Yep@RyanHuangNLP. Because our model released now is trained using individual Chinese character dataset. Thus if you wanna generate line-level or paragraph-level characters, you should re-train the FontDiffuser using the relevant data.