Namhyuk Ahn
Namhyuk Ahn
@feiyangha Just DIV2K. The reason for describing three datasets is that they have been widely used, but we choose to use DIV2K.
Hi. I'm sorry, I had been very busy recently. I'll look how to handle it today or tomorrow and let you know after finding the way. Thanks!
Could you guys elaborate more details on how you ran the code, or the hierarchy of the dataset directory? I checked that the above script generates the output with a...
Hi. You can control the `--sty_gamma` args when you run the inference_t2i code. (see https://github.com/webtoon/dreamstyler/blob/main/dreamstyler/inference_t2i.py#L52) By the way, I didn't put the style guidance in style transfer as this doesn't...
Hi, sorry for the late reply. As you mentioned, the open-source code does not include style mixing. You can implement style mixing by providing different prompt tokens for each layer...
Hello, you can find the style images and eval prompts in https://drive.google.com/file/d/1DtSK2goKeNWv7EQ7Adh9t6Jm0j7PCzqP/view?usp=share_link