Skip to content
GitLab
Explore
Sign in
Tags
Tags give the ability to mark specific points in history as being important
This project is mirrored from
https://github.com/lucidrains/DALLE2-pytorch
. Pull mirroring updated
Sep 19, 2024
.
0.26.2
4b912a38
·
0.26.2
·
Jul 19, 2022
v0.26.1
291377bb
·
@jacobwjs reports dynamic thresholding works very well and 0.95 is a better value
·
Jul 19, 2022
v0.26.0
723bf0ab
·
complete inpainting ability using inpaint_image and inpaint_mask passed into...
·
Jul 19, 2022
v0.25.2
d88c7ba5
·
fix a bug with ddim and predict x0 objective
·
Jul 18, 2022
v0.25.1
da8e99ad
·
fix sample bug
·
Jul 18, 2022
v0.25.0
6afb886c
·
complete imagen-like noise level conditioning
·
Jul 18, 2022
v0.24.3
a2ee3fa3
·
offer way to turn off initial cross embed convolutional module, for debugging upsampler artifacts
·
Jul 15, 2022
v0.24.2
a58a370d
·
takes care of a grad strides error at...
·
Jul 14, 2022
v0.24.1
1662bbf2
·
protect against random cropping for base unet
·
Jul 14, 2022
v0.24.0
a34f6096
·
let the neural network peek at the low resolution conditioning one last time...
·
Jul 14, 2022
v0.23.10
0b40cbaa
·
just always use nearest neighbor interpolation when resizing for low...
·
Jul 13, 2022
v0.23.9
f141144a
·
allow for using classifier free guidance for some unets but not others, by...
·
Jul 13, 2022
v0.23.8
f9882077
·
hack around some inplace error, also make sure for openai clip text encoding,...
·
Jul 13, 2022
v0.23.7
b2073219
·
foolproof sampling for decoder to always use eval mode (and restore training state afterwards)
·
Jul 13, 2022
v0.23.6
cc0f7a93
·
fix non pixel shuffle upsample
·
Jul 13, 2022
v0.23.5
95a512cb
·
fix a potential bug with conditioning with blurred low resolution image, blur...
·
Jul 13, 2022
v0.23.4
972ee973
·
fix issue with ddim and normalization of lowres conditioning image
·
Jul 13, 2022
v0.23.3
79e2a3bc
·
only use the stable layernorm for final output norm in transformer
·
Jul 13, 2022
v0.23.2
349aaca5
·
add yet another transformer stability measure
·
Jul 12, 2022
v0.23.1
3ee3c56d
·
add learned padding tokens, same strategy as dalle1, for diffusion prior, and...
·
Jul 12, 2022
Prev
1
2
3
4
5
6
7
8
…
18
Next