a73f8b7251
Clean up resnet.py file ( #780 )
...
* clean up resnet.py
* make style and quality
* minor formatting
2022-10-10 08:27:50 -07:00
5af6eed9ee
debug an exception ( #638 )
...
* debug an exception
if dst_path is not a file, it will raise Exception in the function src_path.samefile:
FileNotFoundError: [Errno 2] No such file or directory: '/home/lilongwei/notebook/onnx_diffusion/vae_decoder/model.onnx'
* Update src/diffusers/onnx_utils.py
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>
2022-10-10 13:02:18 +02:00
f3983d16ee
[Tests] Fix tests ( #774 )
...
* Fix tests
* remove bogus file
2022-10-07 19:38:40 +02:00
92d7086366
[img2img, inpainting] fix fp16 inference ( #769 )
...
* handle dtype in vae and image2image pipeline
* fix inpaint in fp16
* dtype should be handled in add_noise
* style
* address review comments
* add simple fast tests to check fp16
* fix test name
* put mask in fp16
2022-10-07 17:01:51 +02:00
ec831b6a72
[schedulers] hanlde dtype in add_noise ( #767 )
...
* handle dtype in vae and image2image pipeline
* handle dtype in add noise
* don't modify vae and pipeline
* remove the if
2022-10-07 16:44:19 +02:00
cb0bf0bd0b
fix(DDIM scheduler): use correct dtype for noise ( #742 )
...
Otherwise, it crashes when eta > 0 with float16.
2022-10-07 16:02:32 +02:00
e0fece2b26
Add final latent slice checks to SD pipeline intermediate state tests ( #731 )
...
This is to ensure that the final latent slices stay somewhat consistent as more changes are introduced into the library.
Signed-off-by: James R T <jamestiotio@gmail.com>
Signed-off-by: James R T <jamestiotio@gmail.com>
2022-10-07 15:50:20 +02:00
75bb6d2d46
Fix ONNX conversion script opset argument type ( #739 )
...
The opset argument should be an `int` but was set as a `str`.
2022-10-07 15:47:43 +02:00
906e4105d7
Fix push_to_hub for dreambooth and textual_inversion ( #748 )
...
* Fix push_to_hub for dreambooth and textual_inversion
* Use repo.push_to_hub instead of push_to_hub
2022-10-07 11:50:28 +02:00
7258dc4943
remove bogus folder no.2
2022-10-07 11:21:24 +02:00
c93a8cc901
remove bogus folder
2022-10-07 11:20:26 +02:00
9a95414ea1
Bump to v0.5.0dev0
2022-10-07 11:17:55 +02:00
91ddd2a25b
Release: v0.4.1
2022-10-07 10:37:31 +02:00
fdfa7c8f15
Change fp16 error to warning ( #764 )
...
* Swap fp16 error to warning
Also remove the associated test
* Formatting
* warn -> warning
* Update src/diffusers/pipeline_utils.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* make style
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
2022-10-07 10:31:52 +02:00
d3f1a4c0f0
Revert "Bump to v0.5.0.dev0"
...
This reverts commit 9531150128
2022-10-06 20:42:14 +02:00
ae672d58ef
[Tests] Lower required memory for clip guided and fix super edge-case git pipeline module bug ( #754 )
...
* [Tests] Lower required memory
* fix
* up
* uP
2022-10-06 19:15:26 +02:00
2fa55fc7d4
Merge remote-tracking branch 'origin/main'
2022-10-06 19:12:21 +02:00
9531150128
Bump to v0.5.0.dev0
2022-10-06 19:12:01 +02:00
737195dd2e
Created using Colaboratory
2022-10-06 19:08:00 +02:00
435433cefd
Update clip_guided_stable_diffusion.py
2022-10-06 18:38:09 +02:00
970e30606c
Revert "[v0.4.0] Temporarily remove Flax modules from the public API ( #755 )"
...
This reverts commit 2e209c30cf
2022-10-06 18:35:40 +02:00
c15cda03ca
Bump to v0.4.1.dev0
2022-10-06 18:34:59 +02:00
0fe59b679e
Merge remote-tracking branch 'origin/main'
2022-10-06 18:22:08 +02:00
3b1d2ca1eb
Release: v0.4.0
2022-10-06 18:21:57 +02:00
4581f147a6
Update clip_guided_stable_diffusion.py
2022-10-06 18:12:54 +02:00
2e209c30cf
[v0.4.0] Temporarily remove Flax modules from the public API ( #755 )
...
Temporarily remove Flax modules from the public API
2022-10-06 18:10:36 +02:00
9c9462f388
Python 3.7 doesn't like keys() + keys()
2022-10-06 17:43:40 +02:00
6613a8c7ff
make CI happy
2022-10-06 17:16:01 +02:00
d9c449ea30
Custome Pipelines ( #744 )
...
* [Custom Pipelines]
* uP
* make style
* finish
* finish
* remove ipdb
* upload
* fix
* finish docs
* Apply suggestions from code review
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: apolinario <joaopaulo.passos@gmail.com>
* finish
* final uploads
* remove unnecessary test
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: apolinario <joaopaulo.passos@gmail.com>
2022-10-06 16:54:02 +02:00
f3128c8788
Actually fix the grad ckpt test ( #734 )
...
* use_deterministic_algorithms for grad ckpt test
* remove eval
* Apply suggestions from code review
* Update tests/test_models_unet.py
2022-10-06 16:04:00 +02:00
088396824d
Better steps deprecation for LMS ( #753 )
...
* Better steps deprecation for LMS
* upd
2022-10-06 15:51:25 +02:00
6c64741933
Raise an error when moving an fp16 pipeline to CPU ( #749 )
...
* Raise an error when moving an fp16 pipeline to CPU
* Raise an error when moving an fp16 pipeline to CPU
* style
* Update src/diffusers/pipeline_utils.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
* Update src/diffusers/pipeline_utils.py
Co-authored-by: Suraj Patil <surajp815@gmail.com>
* Improve the message
* cuda
* Update tests/test_pipelines.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Suraj Patil <surajp815@gmail.com>
2022-10-06 15:51:03 +02:00
3383f77441
update the clip guided PR according to the new API ( #751 )
2022-10-06 15:43:48 +02:00
df9c070174
Add back-compatibility to LMS timesteps ( #750 )
...
* Add back-compatibility to LMS timesteps
* style
2022-10-06 14:43:55 +02:00
c119dc4c04
allow multiple generations per prompt ( #741 )
...
* compute text embeds per prompt
* don't repeat uncond prompts
* repeat separatly
* update image2image
* fix repeat uncond embeds
* adapt inpaint pipeline
* ifx uncond tokens in img2img
* add tests and fix ucond embeds in im2img and inpaint pipe
2022-10-06 14:01:45 +02:00
367a671a06
remove use_auth_token from for TI test ( #747 )
...
remove auth token from for TI test
2022-10-06 11:13:24 +02:00
916754ea5e
make style
2022-10-06 00:51:11 +02:00
4deb16e830
[Docs] Advertise fp16 instead of autocast ( #740 )
...
up
2022-10-05 22:20:53 +02:00
5493524b71
Replace messages that have empty backquotes ( #738 )
...
Replace message with empty backquotes.
This was part of #733 , I was too slow to review :)
2022-10-05 20:16:30 +02:00
19e559d5e9
remove use_auth_token from remaining places ( #737 )
...
remove use_auth_token
2022-10-05 17:40:49 +02:00
78744b6a8f
No more use_auth_token=True ( #733 )
...
* up
* uP
* uP
* make style
* Apply suggestions from code review
* up
* finish
2022-10-05 17:16:15 +02:00
3dcc75cbd4
Removing `autocast` for `35-25% speedup`. (`autocast` considered harmful). ( #511 )
...
* Removing `autocast` for `35-25% speedup`.
* iQuality
* Adding a slow test.
* Fixing mps noise generation.
* Raising error on wrong device, instead of just casting on behalf of user.
* Quality.
* fix merge
Co-authored-by: Nouamane Tazi <nouamane98@gmail.com>
2022-10-05 15:33:13 +02:00
6b09f370c4
[Scheduler design] The pragmatic approach ( #719 )
...
* init
* improve add_noise
* [debug start] run slow test
* [debug end]
* quick revert
* Add docstrings and warnings + API tests
* Make the warning less spammy
2022-10-05 14:41:19 +02:00
726aba089d
[Pytorch] pytorch only timesteps ( #724 )
...
* pytorch timesteps
* style
* get rid of if-else
* fix test
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
2022-10-05 12:55:51 +02:00
60c9634a5e
Avoid negative strides for tensors ( #717 )
...
* Avoid negative strides for tensors
* Changed not to make torch.tensor
* Removed a needless copy
2022-10-05 12:45:01 +02:00
b9eea06e9f
Include CLIPTextModel parameters in conversion ( #695 )
2022-10-05 12:22:07 +02:00
08d4fb6e9f
[dreambooth] Using already created `Path` in dataset ( #681 )
...
using already created `Path` in dataset
2022-10-05 12:14:30 +02:00
a8a3a20d36
[Tests] Add accelerate to testing ( #729 )
...
* fix accelerate for testing
* fix copies
* uP
2022-10-05 11:35:02 +02:00
7265dd8cc8
renamed x to meaningful variable in resnet.py ( #677 )
...
* renamed single letter variables
* renamed x to meaningful variable in resnet.py
Hello @patil-suraj can you verify it
Thanks
* Reformatted using black
* renamed x to meaningful variable in resnet.py
Hello @patil-suraj can you verify it
Thanks
* reformatted the files
* modified unboundlocalerror in line 374
* removed referenced before error
* renamed single variable x -> hidden_state, p-> pad_value
Co-authored-by: Nikhil A V <nikhilav@Nikhils-MacBook-Pro.local>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Suraj Patil <surajp815@gmail.com>
2022-10-04 23:52:24 +02:00
14b9754923
[train_unconditional] fix applying clip_grad_norm_ ( #721 )
...
fix clip_grad_norm_
2022-10-04 19:04:05 +02:00
Nathan Lambert