Commit graph

106 commits

Author SHA1 Message Date
rromb
5fd73effd3 ok val but hacked away 2022-05-31 16:12:02 +02:00
rromb
c537709d4d no val 2022-05-31 16:07:48 +02:00
rromb
fdc93bd76d fix import 2022-05-31 15:56:29 +02:00
rromb
174340dd4c prepare large-scale clip encoder training 2022-05-31 15:24:23 +02:00
rromb
de7a003484 one more handler 2022-05-31 15:21:55 +02:00
rromb
1eb0b88a8d add alstroemeria data 2022-05-31 15:20:27 +02:00
root
1dba1b17ee dev it 2022-05-31 13:18:23 +00:00
rromb
07ebb8fb2a disabled_train is set later 2022-05-31 14:18:01 +02:00
rromb
0aa5027fdc add dev configs 2022-05-31 14:16:54 +02:00
rromb
77ac91c68c add clip and t5 configs 2022-05-31 14:12:27 +02:00
rromb
17f4ca8110 fix clip encoder code 2022-05-31 12:36:26 +02:00
rromb
e637491838 clip encoder 2022-05-31 12:28:00 +02:00
rromb
3c53c6c15b add frozen t5 encoder from huggingface 2022-05-31 11:42:53 +02:00
Patrick Esser
48bbc51869 1p4B config 2022-05-30 22:52:18 +00:00
Patrick Esser
c7ea00aaf9 val loop 2022-05-30 22:16:58 +00:00
Patrick Esser
ac1ca73d69 simplify data loader 2022-05-30 20:35:27 +00:00
pesser
74797d4099 warn and continue 2022-05-30 14:09:27 +00:00
pesser
f8c559e862 ignore 2022-05-30 14:04:35 +00:00
pesser
8d6c7e34f2 pray 2022-05-30 13:48:04 +00:00
pesser
3e2e9d8e9e debug with dummy data 2022-05-30 13:09:42 +00:00
pesser
e7e1c6343a mn 2022-05-30 12:42:07 +00:00
pesser
5e4ae89c9d add req for pip virtualenv 2022-05-30 12:35:31 +00:00
pesser
075567889f add minexample 2022-05-29 21:03:42 +00:00
pesser
ddb9ce74f1 mindev 2022-05-29 20:52:31 +00:00
pesser
add2812306 relpath 2022-05-29 19:51:43 +00:00
pesser
c5c04d0b42 dev conf 2022-05-29 19:38:08 +00:00
rromb
9a419a1b14 first (in)stable steps 2022-05-27 11:46:04 +02:00
pesser
f7a6152022 laion webdataset example code 2022-05-26 21:51:29 +00:00
Robin Rombach
5a6571e384
add credit 2022-04-15 17:43:03 +02:00
Robin Rombach
4c8bff393a
Merge pull request #51 from crowsonkb/main
Add PLMS sampling and do one 2x size batch per sampling step
2022-04-15 17:35:51 +02:00
rromb
71ebe40791 do not fix num_heads to one in legacy mode 2022-04-15 17:24:11 +02:00
Katherine Crowson
add3f1bc0c
Merge branch 'CompVis:main' into main 2022-04-15 05:37:05 -07:00
Katherine Crowson
c8122e7917 Alter credit in README 2022-04-15 05:36:41 -07:00
Robin Rombach
8381e5e557
Add files via upload 2022-04-08 13:07:54 +02:00
ablattmann
b4899611c2
Merge pull request #38 from AK391/main
add web demo link on Hugging Face Spaces
2022-04-08 09:53:25 +02:00
AK391
654e31ec9a
update description for 1.45B spaces demo
Co-authored-by: ablattmann <andreas.blattmann@iwr.uni-heidelberg.de>
2022-04-08 03:51:05 -04:00
AK391
5b110b020e
add web demo link 2022-04-07 20:25:21 -04:00
Katherine Crowson
66df437e52 Combine the two classifier-free guidance model outputs into a single batch 2022-04-05 11:35:05 -07:00
Katherine Crowson
f0c4e092c1 Add PLMS sampling 2022-04-04 14:45:35 -07:00
Robin Rombach
5820f690bd
accept arbitrary s 2022-04-04 22:44:51 +02:00
Robin Rombach
32c525011b
unconditional guidance with general s!=1.0
Example: "negative weights"
2022-04-04 22:31:35 +02:00
Robin Rombach
4fa9f90f66
add news 2022-04-04 16:47:01 +02:00
Robin Rombach
65eea86b4b
Update README.md
fix link to colab notebook
2022-04-04 16:34:40 +02:00
Robin Rombach
7fb65db353
Merge pull request #27 from CompVis/public
Add new models
2022-04-04 16:20:58 +02:00
rromb
682030b8a0 Merge branch 'main' of https://github.com/CompVis/latent-diffusion into public 2022-04-04 16:18:54 +02:00
rromb
a80ed7987e add new models 2022-04-04 16:17:48 +02:00
rromb
f13bf9bf46 add vqgan loss with codebook statistic eval 2022-02-21 15:06:50 +01:00
Robin Rombach
2b46bcb98c
Update ddpm.py
clean up no.1
2022-01-17 21:24:19 +01:00
ablattmann
417d5f3dee add trainsteps to first stage table 2022-01-15 12:30:44 +01:00
ablattmann
851743597c
add LICENSE 2022-01-14 18:24:18 +01:00