Hi ZichengDuan!
can you please support a negative prompt? it may help to converge to the wanted character - i.e. a real human being and a CGI.
additional question: only stable-diffusion-xl-base-1.0 (among the known models) have tokenizer_2 and text_encoder_2:
how can I modify the code to work with other diffusion models?
Hi ZichengDuan! can you please support a negative prompt? it may help to converge to the wanted character - i.e. a real human being and a CGI.
additional question: only stable-diffusion-xl-base-1.0 (among the known models) have tokenizer_2 and text_encoder_2: how can I modify the code to work with other diffusion models?
Thanks!