Commit Graph

572 Commits

Author SHA1 Message Date
Phil Wang
8c003ab1e1 readme and citation 2022-07-19 09:36:45 -07:00
Phil Wang
723bf0abba complete inpainting ability using inpaint_image and inpaint_mask passed into sample function for decoder v0.26.0 2022-07-19 09:26:55 -07:00
Phil Wang
d88c7ba56c fix a bug with ddim and predict x0 objective v0.25.2 2022-07-18 19:04:26 -07:00
Phil Wang
3676a8ce78 comments 2022-07-18 15:02:04 -07:00
Phil Wang
da8e99ada0 fix sample bug v0.25.1 2022-07-18 13:50:22 -07:00
Phil Wang
6afb886cf4 complete imagen-like noise level conditioning v0.25.0 2022-07-18 13:43:57 -07:00
Phil Wang
c7fe4f2f44 project management 2022-07-17 17:27:44 -07:00
Phil Wang
a2ee3fa3cc offer way to turn off initial cross embed convolutional module, for debugging upsampler artifacts v0.24.3 2022-07-15 17:29:10 -07:00
Phil Wang
a58a370d75 takes care of a grad strides error at https://github.com/lucidrains/DALLE2-pytorch/issues/196 thanks to @YUHANG-Ma v0.24.2 2022-07-14 15:28:34 -07:00
Phil Wang
1662bbf226 protect against random cropping for base unet v0.24.1 2022-07-14 12:49:43 -07:00
Phil Wang
5be1f57448 update 2022-07-14 12:03:42 -07:00
Phil Wang
c52ce58e10 update 2022-07-14 10:54:51 -07:00
Phil Wang
a34f60962a let the neural network peek at the low resolution conditioning one last time before making prediction, for upsamplers v0.24.0 2022-07-14 10:27:04 -07:00
Phil Wang
0b40cbaa54 just always use nearest neighbor interpolation when resizing for low resolution conditioning, for https://github.com/lucidrains/DALLE2-pytorch/pull/181 v0.23.10 2022-07-13 20:59:43 -07:00
Phil Wang
f141144a6d allow for using classifier free guidance for some unets but not others, by passing in a tuple of cond_scale during sampling for decoder, just in case it is causing issues for upsamplers v0.23.9 2022-07-13 13:12:30 -07:00
Phil Wang
f988207718 hack around some inplace error, also make sure for openai clip text encoding, only tokens after eos_id is masked out v0.23.8 2022-07-13 12:56:02 -07:00
Phil Wang
b2073219f0 foolproof sampling for decoder to always use eval mode (and restore training state afterwards) v0.23.7 2022-07-13 10:21:00 -07:00
Phil Wang
cc0f7a935c fix non pixel shuffle upsample v0.23.6 2022-07-13 10:16:02 -07:00
Phil Wang
95a512cb65 fix a potential bug with conditioning with blurred low resolution image, blur should be applied only 50% of the time v0.23.5 2022-07-13 10:11:49 -07:00
Phil Wang
972ee973bc fix issue with ddim and normalization of lowres conditioning image v0.23.4 2022-07-13 09:48:40 -07:00
Phil Wang
79e2a3bc77 only use the stable layernorm for final output norm in transformer v0.23.3 2022-07-13 07:56:30 -07:00
Aidan Dempster
544cdd0b29 Reverted to using basic dataloaders (#205)
Accelerate removes the ability to collate strings. Likely since it
cannot gather strings.
2022-07-12 18:22:27 -07:00
Phil Wang
349aaca56f add yet another transformer stability measure v0.23.2 2022-07-12 17:49:16 -07:00
Phil Wang
3ee3c56d2a add learned padding tokens, same strategy as dalle1, for diffusion prior, and get rid of masking in causal transformer v0.23.1 2022-07-12 17:33:14 -07:00
Phil Wang
cd26c6b17d 0.22.3 v0.22.3 2022-07-12 17:08:31 -07:00
Phil Wang
775abc4df6 add setting to attend to all text encodings regardless of padding, for diffusion prior 2022-07-12 17:08:12 -07:00
Phil Wang
11b1d533a0 make sure text encodings being passed in has the correct batch dimension v0.22.1 2022-07-12 16:00:19 -07:00
Phil Wang
e76e89f9eb remove text masking altogether in favor of deriving from text encodings (padded text encodings must be pad value of 0.) v0.22.2 2022-07-12 15:40:31 -07:00
Phil Wang
bb3ff0ac67 protect against bad text mask being passed into decoder v0.21.3 2022-07-12 15:33:13 -07:00
Phil Wang
1ec4dbe64f one more fix for text mask, if the length of the text encoding exceeds max_text_len, add an assert for better error msg v0.21.2 2022-07-12 15:01:46 -07:00
Phil Wang
e0835acca9 generate text mask within the unet and diffusion prior itself from the text encodings, if not given v0.21.1 2022-07-12 12:54:59 -07:00
Phil Wang
e055793e5d shoutout for @MalumaDev 2022-07-11 16:12:35 -07:00
Phil Wang
1d9ef99288 add PixelShuffleUpsample thanks to @MalumaDev and @marunine for running the experiment and verifyng absence of checkboard artifacts v0.21.0 2022-07-11 16:07:23 -07:00
Phil Wang
bdd62c24b3 zero init final projection in unet, since openai and @crowsonkb are both doing it v0.20.1 2022-07-11 13:22:06 -07:00
Phil Wang
1f1557c614 make it so even if text mask is omitted, it will be derived based on whether text encodings are all 0s or not, simplify dataloading v0.20.0 2022-07-11 10:56:19 -07:00
Aidan Dempster
1a217e99e3 Unet parameter count is now shown (#202) 2022-07-10 16:45:59 -07:00
Phil Wang
7ea314e2f0 allow for final l2norm clamping of the sampled image embed v0.19.6 2022-07-10 09:44:38 -07:00
Phil Wang
4173e88121 more accurate readme 2022-07-09 20:57:26 -07:00
Phil Wang
3dae43fa0e fix misnamed variable, thanks to @nousr v0.19.5 2022-07-09 19:01:37 -07:00
Phil Wang
a598820012 do not noise for the last step in ddim v0.19.4 2022-07-09 18:38:40 -07:00
Phil Wang
4878762627 fix for small validation bug for sampling steps v0.19.3 2022-07-09 17:31:54 -07:00
Phil Wang
47ae17b36e more informative error for something that tripped me up v0.19.2 2022-07-09 17:28:14 -07:00
Phil Wang
b7e22f7da0 complete ddim integration of diffusion prior as well as decoder for each unet, feature complete for https://github.com/lucidrains/DALLE2-pytorch/issues/157 v0.19.1 2022-07-09 17:25:34 -07:00
Romain Beaumont
68de937aac Fix decoder test by fixing the resizing output size (#197) 2022-07-09 07:48:07 -07:00
Phil Wang
097afda606 0.18.0 v0.18.0 2022-07-08 18:18:38 -07:00
Aidan Dempster
5c520db825 Added deepspeed support (#195) 2022-07-08 18:18:08 -07:00
Phil Wang
3070610231 just force it so researcher can never pass in an image that is less than the size that is required for CLIP or CoCa v0.17.1 2022-07-08 18:17:29 -07:00
Aidan Dempster
870aeeca62 Fixed issue where evaluation would error when large image was loaded (#194) 2022-07-08 17:11:34 -07:00
Romain Beaumont
f28dc6dc01 setup simple ci (#193) 2022-07-08 16:51:56 -07:00
Phil Wang
081d8d3484 0.17.0 v0.17.0 2022-07-08 13:36:26 -07:00