Open cuongngm opened 11 months ago
Thanks for your interest in TextDiffuser-2. Basically it is simple for adapting. You need to prepare a text image dataset in other language and add corresponding tokens to the tokenizer. You can refer to the code about adding English tokens and simply replacing them in other languages.
Describe Model I am using (UniLM, MiniLM, LayoutLM ...): textdiffuser 2
How to use this model on text in other languages, I hope the author will guide me on how to adapt it