Zac Liu

I suppose you see "Final Test Acc: 28.6425" is the last run of the 15 experiments. Technically, there are 14 more "Final Test Acc". I got avg:36.71 and std:3.63.

thanks

> Please show your prompts! 请给出来你的文本描述，没准我们能改进。 I have tried some prompts from lexica. The generated images look fine to me. EN:portrait of a young handsome dark god, gold wires, intricate,...

The machine translation may be working very well for you. However, machine translations may not work well in all languages. As for the cultural differences, not all artworks have English...

hi， yeah， it‘s on the way. > 在 2020年9月17日，上午3:15，Lor 写道： > >  > Hello, > are you going to publish code? > > — > You are receiving this...

Data was released. The code is on the way.

Thanks for your question. The code needs to be reviewed before it can be published due to the company policy. We are working on it.

There are many failures in the tests. Please fix these errors and raise a pull request again. Thanks.

This PR also fix ISSUE #495

The -3.8359 is the mean of output embedding and 1.9458 is the std with mp size =4. the mean and std is changed when mp size=2