DragonDiffusion

DragonDiffusion copied to clipboard

caojiehui

Code release inquiry

2

Thanks to the authors for their excellent work, what approximate time will the code be published?

HEUfcy

JoshonSmith

Asuka001100

Questions regarding the details of DragonDiffusion

2

Thanks for the great work! I am wondering how you obtain the mask of a specific object?

Kyfafyd

Question about Cross-branch Self-attention

3

Hi, thanks for the interesting work! According to the Sec 3.4, W_{Q, K, V} are learnable projection matrices, so does DragonDiffusion need to fine-tune projection matrices for all two branches?...

jiawei-liu1103

请教如何得到图像的prompt

1

作者您好，非常感谢论文提供的出色的思路和结果。论文基于text-to-image的stable diffusion，那么我们怎么得到这张图片的text prompt，从而能够完成操作呢？或者说对于任一图片，整体思路都是在基于null-text的uncondition来弄的呢？谢谢！

monkeyCv

Expected time of release of code and models

2

Hey team, Thank you so much for the exciting work that you have done. My question is that what is the expected date of the launch of code and models....

abi98213

就冲这名字 得给个赞呀！ 不过第一眼以为你要画龙了，点进去跟龙没关系，原来是拖动。。

PL23K

No fine-tuning or extra module needed, why losses and learning rate?

1

Hi, interesting work. As mentioned in the paper: > All content editing and preservation signals in our proposed method come from the image itself. It allows for a direct translation...

DarrenIm