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
.
0.0.37
be72f857
·
first pass at complete DALL-E2 + Latent Diffusion integration, latent...
·
Apr 22, 2022
0.0.36
461347c1
·
fix vqgan-vae for latent diffusion
·
Apr 22, 2022
0.0.35
46cef31c
·
optional projection out for prior network causal transformer
·
Apr 22, 2022
0.0.34
59b1a77d
·
be a bit more conservative and stick with layernorm (without bias) for now,...
·
Apr 22, 2022
0.0.33
7f338319
·
makes more sense for blur augmentation to happen before the upsampling
·
Apr 22, 2022
0.0.32
2c6c9182
·
refactor blurring training augmentation to be taken care of by the decoder,...
·
Apr 22, 2022
0.0.31
faebf4c8
·
from my vision transformer experience, dimension of attention head of 32 is...
·
Apr 20, 2022
0.0.28
27a33e1b
·
complete contextmanager method for keeping only one unet in GPU during training or inference
·
Apr 20, 2022
0.0.27
6f941a21
·
give time tokens a surface area of 2 tokens as default, make it so researcher...
·
Apr 20, 2022
0.0.26
ddde8ca1
·
fix cosine bbeta schedule, thanks to @Zhengxinyang
·
Apr 19, 2022
0.0.25
a35c309b
·
add sparse attention layers in between convnext blocks in unet (grid like...
·
Apr 19, 2022
0.0.24
82328f16
·
same for text encodings for decoder ddpm training
·
Apr 18, 2022
0.0.23
6fee4fce
·
also allow for image embedding to be passed into the diffusion model, in the...
·
Apr 18, 2022
0.0.22
960a7985
·
use some magic just this once to remove the need for researchers to think
·
Apr 18, 2022
0.0.21
5a731cc9
·
make kernel size and sigma for gaussian blur for cascading DDPM overridable at...
·
Apr 18, 2022
0.0.20
0332eaa6
·
complete first pass at full cascading DDPM setup in Decoder, flexible enough...
·
Apr 18, 2022
0.0.18
1cce4225
·
0.0.18
·
Apr 17, 2022
0.0.17
c400d875
·
prepare for cascading diffusion in unet, save the full progressive upsampling...
·
Apr 15, 2022
0.0.16
a95de929
·
fix bug with @jihoonerd
·
Apr 15, 2022
0.0.15
6e27f617
·
use t5 relative positional bias in prior network causal transformer, since it...
·
Apr 14, 2022
Prev
1
…
13
14
15
16
17
18
Next