xiaqingsun
xiaqingsun
When I train with a picture from the paper my training results are as follows with the prompt "a painting of city, art by ch_fg4; ch_fg-neg" :   but...
When I train with a picture from the paper my training results are as follows with the prompt "a painting of city, art by ch_fg4; ch_fg-neg" :   but...
Has anyone encountered this problem “AttributeError: 'CrossAttention' object has no attribute 'reshape_heads_to_batch_dim' ”
Is this problem “No module named 'torch._dynamo' ” because of the wrong version of some packages?
how to solve the problem of connection refused when downlowd imgs from https://knn5.laion.ai/knn-service
The results I reproduced with the data in the paper are good my input images:  my result:   But I change other pictures, the result is worse(the sunglasses...