Text Conditioning Dropout about stable-diffusion HOT 6 CLOSED

Same question. Did you find it?

from stable-diffusion.

@XavierXiao I didn't find it. Probably it is not the latest code for the released stable diffusion. Anyway, we can do it on our own. If you want to do text drop out, one way may be, we can filter it in get_input method in ddpm.py. Text conditions are a list of captions, for example a batch size of 3, ['capiton one', 'caption two', 'caption three']. I think it is easier to do it in numpy.

captions = ['caption one', 'caption two', 'caption three']
null_labels = [""] * len(captions)
prob = torch.rand((len(captions),))
filtered_captions = np.where(prob > 0.1, captions, null_labels).tolist()

I'm a newbie in diffusion. Sorry, I am not very friendly with the whole codebase. I might miss something.

from stable-diffusion.

If you're still looking it's here:

from stable-diffusion.

@justinpinkney Thank you so much. I'm clear now. Let me close this issue.

from stable-diffusion.

Interesting. This block does not exist in the official CompVis release...

from stable-diffusion.

@XavierXiao I think official CompVis release is mainly for inference. Pesser is really kind to share development repo here. Justin (@justinpinkney ) also share training details of image variation fork (https://github.com/justinpinkney/stable-diffusion), he shares all the training details. I am really grateful to both of them. I cannot understand things if I don't try. I can play around with this repo and makes me more understood about how stable diffusion works.

from stable-diffusion.