9e9d2dbc59
Fix np.abs
2022-07-20 17:38:03 +02:00
8b4371f70f
Refactor pipeline outputs, return LDM guidance_scale ( #110 )
2022-07-20 17:28:06 +02:00
ad9d252596
Add a decorator for register_to_config ( #108 )
...
* Add a decorator for register_to_config
* All models and test
2022-07-20 15:42:50 +02:00
3a32b8c916
align API
2022-07-19 16:54:10 +00:00
8c31925b3b
Get diffusers ready 🚀 🚀 🚀 ( #101 )
...
* big purge
* more fixes
* finish for now
2022-07-19 18:02:12 +02:00
37fe8e00b2
upload
2022-07-19 15:05:40 +00:00
182b164f32
Fix VE SDE tests, clean API ( #95 )
...
* clean ddpm api to match ddim
* correct ve sde class
* update pipeline API for ve sde
* make style
* Apply suggestions from code review
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
2022-07-19 12:12:45 +02:00
8b42c7cecc
make all tests pass
2022-07-19 00:24:10 +00:00
66d5a1804c
small fixes
2022-07-19 00:08:41 +00:00
d5acb4110a
Finalize ldm ( #96 )
...
* upload
* make checkpoint work
* finalize
2022-07-19 02:02:23 +02:00
6cabc599a2
DDPM Conversion ( #94 )
...
* DDPM
* Fixes
* Edit tests
2022-07-19 01:59:58 +02:00
f82ebb9a03
fix some model tests
2022-07-18 01:29:40 +00:00
63c68d979a
VE/VP SDE updates ( #90 )
...
* improve comments for sde_ve scheduler, init tests
* more comments, tweaking pipelines
* timesteps --> num_training_timesteps, some comments
* merge cpu test, add m1 data
* fix scheduler tests with num_train_timesteps
* make np compatible, add tests for sde ve
* minor default variable fixes
* make style and fix-copies
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
2022-07-18 03:08:08 +02:00
ba3c9a9a3a
[SDE] Merge to unconditional model ( #89 )
...
* up
* more
* uP
* make dummy test pass
* save intermediate
* p
* p
* finish
* finish
* finish
2022-07-18 02:52:37 +02:00
b5c684f042
fix flaky cpu test
2022-07-15 19:49:05 +00:00
da8e87e201
use real checkpoint
2022-07-15 19:13:39 +00:00
43bbc78123
adapt test
2022-07-15 18:37:15 +00:00
9d2fc6b535
some fixes
2022-07-15 17:22:28 +00:00
f448360bd0
Finish scheduler API ( #91 )
...
* finish
* up
2022-07-15 15:04:01 +02:00
97e1e3ba76
finalize model API
2022-07-15 10:48:30 +00:00
6d5ef87e6b
[DDPM] Make DDPM work ( #88 )
...
* up
* finish
* uP
2022-07-14 19:46:04 +02:00
e7fe901e5e
save intermediate ( #87 )
...
* save intermediate
* up
* up
2022-07-14 12:29:06 +02:00
2a69c0b7b8
The big purge -> remove everything except vision for now
2022-07-13 11:42:40 +00:00
c8c0c0e846
quick fix
2022-07-13 10:28:46 +00:00
5e12d5c691
Clean uncond unet more ( #85 )
...
* up
* finished clean up
* remove @
2022-07-13 12:21:11 +02:00
8aed37c1bd
some more refactor
2022-07-12 19:35:47 +00:00
06c79730d0
Add unconditional image generation ( #79 )
...
* uP
* finish downsampling layers
* finish major refactor
* remove bugus file
2022-07-12 18:34:41 +02:00
d9316bf8bc
Fix mutable proj_out weight in the Attention layer ( #73 )
...
* Catch unused params in DDP
* Fix proj_out, add test
2022-07-04 12:36:37 +02:00
4e2674934f
add tests for 1D Up/Downsample blocks ( #72 )
2022-07-04 11:41:04 +02:00
321f9791d6
Downsample / Upsample - clean to 1D and 2D ( #68 )
...
* make unet rl work
* uploaad files / code
* upload files
* make style correct
* finish
2022-07-03 22:26:33 +02:00
f26d3011c7
fix ldm uncond pipeline
2022-07-01 17:19:26 +02:00
db7ec72dd8
up
2022-06-30 22:29:18 +00:00
efe1e60e12
merge glide into resnets
2022-06-30 22:24:22 +00:00
db934c6750
fix more tests
2022-06-30 21:47:40 +00:00
c1c4dea98d
correct tests ncsnpp
2022-06-30 15:54:00 +00:00
3dbd6a8f4d
up
2022-06-30 14:54:31 +00:00
859ffea2b1
add test for ldm uncond
2022-06-29 15:25:51 +02:00
333a8da678
add tests for AutoencoderKL
2022-06-29 13:52:04 +02:00
bae04ea9d8
add test for VQModel
2022-06-29 12:34:24 +02:00
31d1f3c8c0
final fix
2022-06-28 22:59:21 +00:00
79db3eb6ca
fix tests
2022-06-28 17:36:56 +00:00
c45fd7498c
merge unet attention into glide attention
2022-06-28 17:31:44 +00:00
bdecc3cffd
move pipelines into folders
2022-06-28 10:47:47 +00:00
a859b1992b
fix rl model tests
2022-06-28 09:50:21 +00:00
3a5c87055c
add RL test, remove conds from RL model input
2022-06-27 14:48:15 -04:00
a2b72faff7
Merge branch 'main' of https://github.com/huggingface/diffusers into main
2022-06-27 17:20:20 +00:00
c9504bba10
add tests for sde ve vp models
2022-06-27 17:20:15 +00:00
26ea58d4e1
Merge branch 'main' of https://github.com/huggingface/diffusers into main
2022-06-27 18:04:49 +02:00
7b9b946cb2
add tests for downsample block
2022-06-27 18:03:51 +02:00
4261c3aadf
Make style
2022-06-27 15:59:04 +00:00
932ce05d97
cancel einops
2022-06-27 15:39:41 +00:00
abcb25978a
Merge branch 'main' of https://github.com/huggingface/diffusers into main
2022-06-27 16:25:52 +02:00
183056f243
consolidate Upsample
2022-06-27 16:25:47 +02:00
dc7c49e4e4
add tests for upsample blocks
2022-06-27 15:50:54 +02:00
3986741b8b
add another ldm fast test
2022-06-27 13:25:26 +00:00
6846ee2ac4
finalize position embeddings
2022-06-27 11:43:08 +00:00
c7a39d38ad
refactor all sinus embeddings
2022-06-27 11:37:37 +00:00
02a76c2c81
consolidate timestep embeds
2022-06-27 10:14:54 +00:00
9b9afc9726
actually fix test_ldm_text2img_fast
2022-06-27 11:46:50 +02:00
b7f0ce5b39
fix test_ldm_text2img_fast
2022-06-27 11:44:05 +02:00
6921393ae2
add fast test for ldm
2022-06-27 11:42:52 +02:00
17bf65e186
skip test_ldm_text2img for now
2022-06-27 11:39:19 +02:00
1a0331a78a
fix some tests on gpu
2022-06-27 09:07:57 +00:00
45a09bebf3
add first files
2022-06-27 10:46:39 +02:00
ba264419f4
finish vp
2022-06-27 00:07:57 +00:00
dc6d028654
add vp sampler
2022-06-26 23:41:55 +00:00
433cb3f801
clean up sde ve more
2022-06-25 18:25:43 +00:00
f941fc9917
refactor tts sampler a bit
2022-06-22 23:15:57 +02:00
0244e2af4c
correct diffusion test
2022-06-22 18:41:14 +02:00
48269070d2
more fixes
2022-06-22 13:40:08 +00:00
d0032c6095
refactor naming
2022-06-22 12:38:36 +00:00
e3bf932404
don't hardcode device in tests
2022-06-21 12:02:21 +02:00
ac00dad756
add GLIDETextToImageUNetModelTests
2022-06-21 12:01:07 +02:00
9c82c32ba7
make style
2022-06-21 10:43:40 +02:00
80898b5234
add UNetGradTTSModelTests
2022-06-20 15:57:58 +02:00
e5675fad5d
remove prints from tests
2022-06-20 14:47:13 +02:00
95a45f5b3a
add UNetLDMModelTests
2022-06-20 14:45:58 +02:00
646e16fe06
fix test_output_pretrained for GLIDESuperResUNetModel
2022-06-20 14:27:37 +02:00
08c852290a
add license disclaimers to schedulers
2022-06-20 13:06:31 +02:00
e007c797b1
add GLIDESuperResUNetModel
2022-06-17 19:04:07 +02:00
12da0fe10d
Merge branch 'main' into model-tests
2022-06-17 16:37:45 +02:00
cf6cd39572
finish tests for UNet
2022-06-17 16:36:51 +02:00
1997b90838
image->sample in schedule tests
2022-06-17 15:51:33 +02:00
b2274ece73
finish pndm scheduler
2022-06-17 15:51:03 +02:00
7dc71897b3
add UnetModelTests
2022-06-17 13:49:26 +02:00
d76bc43720
add skeleton for model tests
2022-06-17 13:36:59 +02:00
8c1f51978c
make clip name shorter
2022-06-17 12:11:40 +02:00
13a78b3cd3
rename image to sample
2022-06-17 12:09:13 +02:00
fe7d136324
correct dict
2022-06-17 11:55:02 +02:00
5e6f500038
rename register to register_to_config
2022-06-17 10:58:43 +02:00
17c574a16d
remove torchvision dependency
2022-06-15 12:35:47 +02:00
cfe6eb1611
Training example parameterization
2022-06-15 11:21:02 +02:00
542c78686f
Merge branch 'main' of https://github.com/huggingface/diffusers into main
2022-06-14 12:51:40 +02:00
147d8e0702
add test for loading model from pipeline module
2022-06-14 12:50:40 +02:00
57243fd565
GLIDE integration test
2022-06-14 12:37:28 +02:00
bb30664285
Move the training example
2022-06-14 11:33:24 +02:00
809591b7b6
improve pndm
2022-06-13 16:29:22 +00:00
27266abc9f
rename schedulers
2022-06-13 10:39:53 +02:00
12b10cbe09
finish refactor
2022-06-12 21:20:39 +00:00
2d97544dc7
add more tests schedulers
2022-06-12 19:56:13 +00:00
anton-l