Commit Graph

164 Commits

Author SHA1 Message Date
Phil Wang
0283556608 fix example in readme, since api changed 2022-04-29 13:40:55 -07:00
Phil Wang
5063d192b6 now completely OpenAI CLIP compatible for training
just take care of the logic for AdamW and transformers

used namedtuples for clip adapter embedding outputs
2022-04-29 13:05:01 -07:00
Phil Wang
f4a54e475e add some training fns 2022-04-29 09:44:55 -07:00
Phil Wang
fb662a62f3 fix another bug thanks to @xiankgx 0.0.65 2022-04-29 07:38:32 -07:00
Phil Wang
587c8c9b44 optimize for clarity 2022-04-28 21:59:13 -07:00
Phil Wang
aa900213e7 force first unet in the cascade to be conditioned on image embeds 0.0.64 2022-04-28 20:53:15 -07:00
Phil Wang
cb26187450 vqgan-vae codebook dims should be 256 or smaller 0.0.63 2022-04-28 08:59:03 -07:00
Phil Wang
625ce23f6b 🐛 0.0.62 2022-04-28 07:21:18 -07:00
Phil Wang
dbf4a281f1 make sure another CLIP can actually be passed in, as long as it is wrapped in an adapter extended from BaseClipAdapter 0.0.61 2022-04-27 20:45:27 -07:00
Phil Wang
4ab527e779 some extra asserts for text encoding of diffusion prior and decoder 0.0.60 2022-04-27 20:11:43 -07:00
Phil Wang
d0cdeb3247 add ability for DALL-E2 to return PIL images with return_pil_images = True on forward, for those who have no clue about deep learning 2022-04-27 19:58:06 -07:00
Phil Wang
8c610aad9a only pass text encodings conditioning in diffusion prior if specified on initialization 0.0.58 2022-04-27 19:48:16 -07:00
Phil Wang
6700381a37 prepare for ability to integrate other clips other than x-clip 0.0.57 2022-04-27 19:35:05 -07:00
Phil Wang
20377f889a todo 2022-04-27 17:22:14 -07:00
Phil Wang
6edb1c5dd0 fix issue with ema class 0.0.56 2022-04-27 16:40:02 -07:00
Phil Wang
b093f92182 inform what is possible 2022-04-27 08:25:16 -07:00
Phil Wang
fa3bb6ba5c make sure cpu-only still works 0.0.55 2022-04-27 08:02:10 -07:00
Phil Wang
2705e7c9b0 attention-based upsampling claims unsupported by local experiments, removing 2022-04-27 07:51:04 -07:00
Phil Wang
77141882c8 complete vit-vqgan from https://arxiv.org/abs/2110.04627 0.0.54 2022-04-26 17:20:47 -07:00
Phil Wang
4075d02139 nevermind, it could be working, but only when i stabilize it with the feedforward layer + tanh as proposed in vit-vqgan paper (which will be built into the repository later for the latent diffusion) 2022-04-26 12:43:31 -07:00
Phil Wang
de0296106b be able to turn off warning for use of LazyLinear by passing in text embedding dimension for unet 0.0.52 2022-04-26 11:42:46 -07:00
Phil Wang
eafb136214 suppress a warning 0.0.51 2022-04-26 11:40:45 -07:00
Phil Wang
bfbcc283a3 DRY a tiny bit for gaussian diffusion related logic 2022-04-26 11:39:12 -07:00
Phil Wang
c30544b73a no CLIP altogether for training DiffusionPrior 0.0.50 2022-04-26 10:23:41 -07:00
Phil Wang
bdf5e9c009 todo 2022-04-26 09:56:54 -07:00
Phil Wang
9878be760b have researcher explicitly state upfront whether to condition with text encodings in cascading ddpm decoder, have DALLE-2 class take care of passing in text if feature turned on 0.0.49 2022-04-26 09:47:09 -07:00
Phil Wang
7ba6357c05 allow for training the Prior network with precomputed CLIP embeddings (or text encodings) 0.0.48 2022-04-26 09:29:51 -07:00
Phil Wang
76e063e8b7 refactor so that the causal transformer in the diffusion prior network can be conditioned without text encodings (for Laions parallel efforts, although it seems from the paper it is needed) 0.0.47 2022-04-26 09:00:11 -07:00
Phil Wang
4d25976f33 make sure non-latent diffusion still works 0.0.46 2022-04-26 08:36:00 -07:00
Phil Wang
0b28ee0d01 revert back to old upsampling, paper does not work 2022-04-26 07:39:04 -07:00
Phil Wang
45262a4bb7 bring in the exponential moving average wrapper, to get ready for training 2022-04-25 19:24:13 -07:00
Phil Wang
13a58a78c4 scratch off todo 2022-04-25 19:01:30 -07:00
Phil Wang
f75d49c781 start a file for all attention-related modules, use attention-based upsampling in the unets in dalle-2 0.0.45 2022-04-25 18:59:10 -07:00
Phil Wang
3b520dfa85 bring in attention-based upsampling to strengthen vqgan-vae, seems to work as advertised in initial experiments in GAN 0.0.44 2022-04-25 17:27:45 -07:00
Phil Wang
79198c6ae4 keep readme simple for reader 2022-04-25 17:21:45 -07:00
Phil Wang
77a246b1b9 todo 2022-04-25 08:48:28 -07:00
Phil Wang
f93a3f6ed8 reprioritize 2022-04-25 08:44:27 -07:00
Phil Wang
8f2a0c7e00 better naming 0.0.43 2022-04-25 07:44:33 -07:00
Phil Wang
863f4ef243 just take care of the logic for setting all latent diffusion to predict x0, if needed 0.0.42 2022-04-24 10:06:42 -07:00
Phil Wang
fb8a66a2de just in case latent diffusion performs better with prediction of x0 instead of epsilon, open up the research avenue 0.0.41 2022-04-24 10:04:22 -07:00
Phil Wang
579d4b42dd does not seem right to clip for the prior diffusion part 0.0.40 2022-04-24 09:51:18 -07:00
Phil Wang
473808850a some outlines to the eventual CLI endpoint 2022-04-24 09:27:15 -07:00
Phil Wang
d5318aef4f todo 2022-04-23 08:23:08 -07:00
Phil Wang
f82917e1fd prepare for turning off gradient penalty, as shown in GAN literature, GP needs to be only applied 1 out of 4 iterations 0.0.39 2022-04-23 07:52:10 -07:00
Phil Wang
05b74be69a use null container pattern to cleanup some conditionals, save more cleanup for next week 0.0.38 2022-04-22 15:23:18 -07:00
Phil Wang
a8b5d5d753 last tweak of readme 2022-04-22 14:16:43 -07:00
Phil Wang
976ef7f87c project management 2022-04-22 14:15:42 -07:00
Phil Wang
fd175bcc0e readme 2022-04-22 14:13:33 -07:00
Phil Wang
76b32f18b3 first pass at complete DALL-E2 + Latent Diffusion integration, latent diffusion on any layer(s) of the cascading ddpm in the decoder. 2022-04-22 13:53:13 -07:00
Phil Wang
f2d5b87677 todo 2022-04-22 11:39:58 -07:00