Closed xvjiarui closed 2 years ago
@xvjiarui oh gosh, thank you for catching this bug! :man_facepalming: :pray: i've fixed it at https://github.com/lucidrains/DALLE2-pytorch/commit/5d958713c0753922b64086b2310324c1f3be64e5 hope this is the last one..
Wow, that's fast! Thank you!
Hi @lucidrains
In your implementation here, the image embedding is added to the time embedding as Sec. 2.1 in paper
However, I am wondering whether the current implementation is still classifier-free guidance. Currently, we don't drop
image_hiddens
randomly, so it is always conditioned on image embedding, I think?Please feel free to point me out if I am wrong.