ProFusion
ProFusion copied to clipboard
drboog
Code for Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach
Hello, I would like to know that whether I can train this model on stable-diffusion-v1-5, which is applicable to ControlNet. I have tried to change the base model, but encounter...
First, thanks for a very interesting paper. Looking through your code I see that you pass use `_build_causal_attention_mask` and pass this attention mask to text encoder during training, which indeed...
Looking forward to your reply.
Amazing effect!! could you provide a model and parameters to reproduce the davidwu effect in the paper, plz 
I want to create two people simultaneously, is multiple subjects possible?
Great jobs！If I want to get higher resolution photos，like 1024*1024. Do I need to retrain the pretrained model?
Hi, Thanks for the great work! Could you say which prompt was used during training? Did you used the default prompt: "A photo of", or did you varied the text...
Hi! @drboog Thank you for releasing the code. I read your paper with deep impression!! While following the flow of the paper, I don't know which evaluation metric to use....
White running test.ipynb file, we are running into this error. 'CLIPTextTransformer' object has no attribute '_build_causal_attention_mask' Followed same process, as installation.
