Lincoln Stein
67eb715093
loaders for main, controlnet, ip-adapter, clipvision and t2i
2024-03-01 10:42:33 +11:00
Lincoln Stein
8ba5360269
model loading and conversion implemented for vaes
2024-03-01 10:42:33 +11:00
psychedelicious
0f8af643d1
chore(backend): rename ModelInfo -> LoadedModelInfo
...
We have two different classes named `ModelInfo` which might need to be used by API consumers. We need to export both but have to deal with this naming collision.
The `ModelInfo` I've renamed here is the one that is returned when a model is loaded. It's the object least likely to be used by API consumers.
2024-03-01 10:42:33 +11:00
Wubbbi
1057314508
Fix ruff?
2024-02-01 20:40:28 -05:00
Wubbbi
413fe566b8
Fix imports
2024-02-01 20:40:28 -05:00
Wubbbi
c9b5f06c42
Update diffusers + hotfix
2024-02-01 20:40:28 -05:00
Brandon Rising
a769f93be0
Remove unnecessary change
2024-01-31 07:16:14 -06:00
Brandon Rising
14efc95707
Allow passing of a civit api key
2024-01-31 07:16:14 -06:00
Millun Atluri
74e644c4ba
Allow bfloat16 to be configurable in invoke.yaml ( #5469 )
...
* feat: allow bfloat16 to be configurable in invoke.yaml
* fix: `torch_dtype()` util
- Use `choose_precision` to get the precision string
- Do not reference deprecated `config.full_precision` flat (why does this still exist?), if a user had this enabled it would override their actual precision setting and potentially cause a lot of confusion.
---------
Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
2024-01-12 18:40:37 +00:00
Lincoln Stein
6460dcc7e0
use torch.bfloat16 on cuda systems
2024-01-04 23:25:52 -05:00
gogurtenjoyer
2d11d97dad
remove MacOS Sonoma check in devices.py ( #5312 )
...
* remove MacOS Sonoma check in devices.py
As of pytorch 2.1.0, float16 works with our MPS fixes on Sonoma, so the check is no longer needed.
* remove unused platform import
2023-12-22 00:42:47 +00:00
Lincoln Stein
3bfaee9c57
Merge branch 'main' into refactor/model-manager-3
2023-12-04 22:51:45 -05:00
Lincoln Stein
3c7d1fcd32
clean up get_logger() call
2023-12-04 22:41:59 -05:00
Lincoln Stein
2d2ef5d72c
ensure that setting loglevel on one logger doesn't change others
2023-12-02 11:48:51 -05:00
Lincoln Stein
ecd3dcd5df
Merge branch 'main' into refactor/model-manager-3
2023-11-27 22:15:51 -05:00
Lincoln Stein
ae82df0fda
fix a bunch of type mismatches in the logging module
2023-11-28 09:38:35 +11:00
Lincoln Stein
8ef596eac7
further changes for ruff
2023-11-26 17:13:31 -05:00
Lincoln Stein
8695ad6f59
all features implemented, docs updated, ready for review
2023-11-26 13:18:21 -05:00
Lincoln Stein
19baea1883
all backend features in place; config scanning is failing on controlnet
2023-11-24 19:37:46 -05:00
psychedelicious
4465f97cdf
Merge branch 'main' into refactor/model-manager-2
2023-11-14 07:51:57 +11:00
psychedelicious
04d8f2dfea
fix(backend): fix controlnet zip len
...
Do not use `strict=True` when scaling controlnet conditioning.
When using `guess_mode` (e.g. `more_control` or `more_prompt`), `down_block_res_samples` and `scales` are zipped.
These two objects are of different lengths, so using zip's strict mode raises an error.
In testing, `len(scales) === len(down_block_res_samples) + 1`.
It appears this behaviour is intentional, as the final "extra" item in `scales` is used immediately afterwards.
2023-11-13 15:45:03 +11:00
Lincoln Stein
8afe517204
add note about discriminated union and Body() issue; blackified
2023-11-12 16:50:05 -05:00
Lincoln Stein
2b36565e9e
awkward workaround for double-Annotated in model_record route
2023-11-10 21:32:44 -05:00
psychedelicious
6494e8e551
chore: ruff format
2023-11-11 10:55:40 +11:00
psychedelicious
513fceac82
chore: ruff check - fix pycodestyle
2023-11-11 10:55:33 +11:00
psychedelicious
99a8ebe3a0
chore: ruff check - fix flake8-bugbear
2023-11-11 10:55:28 +11:00
psychedelicious
3a136420d5
chore: ruff check - fix flake8-comprensions
2023-11-11 10:55:23 +11:00
Lincoln Stein
6b173cc66f
multiple small stylistic changes requested by reviewers
2023-11-08 16:45:26 -05:00
Lincoln Stein
edeea5237b
add sql-based model config store and api
2023-11-04 23:03:26 -04:00
psychedelicious
9646157ad5
fix: fix test imports
2023-10-12 12:15:06 -04:00
Ryan Dick
e0e001758a
Remove @slow decorator in favor of @pytest.mark.slow.
2023-10-06 18:26:06 -04:00
Ryan Dick
1c8b1fbc53
POC of a test that depends on models.
2023-10-05 15:35:58 -04:00
Lincoln Stein
25a71a1791
Merge branch 'main' into refactor/rename-get-logger
2023-09-23 14:49:07 -07:00
Lincoln Stein
0960518088
add techjedi's database maintenance script
2023-09-20 17:46:49 -04:00
Sergey Borisov
ff3150a818
Update lora hotfix to new diffusers version(scale argument added)
2023-09-15 12:19:01 -04:00
Martin Kristiansen
e467ca7f1b
Apply black, isort, flake8
2023-09-12 13:01:58 -04:00
Martin Kristiansen
caea6d11c6
isort wip 2
2023-09-12 13:01:58 -04:00
psychedelicious
58aa159a50
fix(backend): fix remaining instances of getLogger()
2023-09-05 10:43:30 +10:00
psychedelicious
d8f7c19030
Merge branch 'main' into refactor/rename-get-logger
2023-09-05 10:37:53 +10:00
psychedelicious
9cb04f6f80
chore: remove unused files
2023-09-02 11:12:19 +10:00
blessedcoolant
a12fbc7406
chore: black fix
2023-09-02 10:51:53 +12:00
Lincoln Stein
b567d65032
blackify and rerun frontend build
2023-08-31 10:35:17 -04:00
blessedcoolant
4196c669a0
chore: black / flake lint errors
2023-08-29 12:57:26 +12:00
blessedcoolant
a1398dec91
Merge branch 'main' into pr/4112
2023-08-29 12:56:59 +12:00
Sergey Borisov
2bf747caf6
Blackify
2023-08-28 18:36:27 +03:00
Sergey Borisov
bb085c5fba
Move monkeypatch for diffusers/torch bug to hotfixes.py
2023-08-28 18:29:49 +03:00
Sergey Borisov
b65c9ad612
Add monkeypatch for xformers to align unaligned attention_mask
2023-08-28 04:50:58 +03:00
Millun Atluri
24132a7950
Merge branch 'main' into refactor/rename-get-logger
2023-08-28 11:38:37 +10:00
Lincoln Stein
45d172d5a8
Merge branch 'main' into refactor/rename-get-logger
2023-08-20 16:08:32 -04:00
Lincoln Stein
ef317be1f9
blackify (again)
2023-08-20 15:46:12 -04:00
