Commit Graph

1954 Commits

Author SHA1 Message Date
psychedelicious
6946a3871f feat(config): simplify config migrator logic
- Remove `Migrations` class - unnecessary complexity on top of `MigrationEntry`
- Move common classes to `config_common`
- Tidy docstrings, variable names
2024-05-14 16:20:40 +10:00
Lincoln Stein
2bba7f38b9
Merge branch 'main' into lstein/feat/config-migration 2024-05-03 00:04:37 -04:00
Lincoln Stein
a48abfacf4 make config migrator into an instance; refactor location of get_config() 2024-05-02 23:45:34 -04:00
psychedelicious
33a9f9a4dc fix(nodes): fix constraints in cnet processors
There were some invalid constraints with the processors - minimum of 0 for resolution or multiple of 64 for resolution.

Made minimum 1px and no multiple ofs.
2024-05-02 12:24:04 +10:00
blessedcoolant
dce8b88aaf fix: change eta only for TCD Scheduler 2024-05-01 12:47:46 +05:30
blessedcoolant
1bdcbe3284 cleanup: use dict update to actually update the scheduler keyword args 2024-05-01 12:22:39 +05:30
Lincoln Stein
d5aee87684
Merge branch 'main' into lstein/feat/config-migration 2024-04-30 18:08:46 -04:00
blessedcoolant
2ddb82200c fix: Manually update eta(gamma) to 1.0 for TCDScheduler
seems to work best with invoke at 4 steps
2024-05-01 01:20:53 +05:30
psychedelicious
e822897b1c feat(nodes): add prototype heuristic image resize node
Uses the fancy cnet resize that retains edges.
2024-04-30 08:10:59 -04:00
psychedelicious
d861bc690e feat(mm): handle PC_PATH_MAX on external drives on macOS
`PC_PATH_MAX` doesn't exist for (some?) external drives on macOS. We need error handling when retrieving this value.

Also added error handling for `PC_NAME_MAX` just in case. This does work for me for external drives on macOS, though.

Closes #6277
2024-04-30 07:57:03 -04:00
Lincoln Stein
36b14343c7
Merge branch 'main' into lstein/feat/config-migration 2024-04-28 14:32:41 -04:00
Lincoln Stein
59deef97c5 Merge branch 'main' into lstein/feat/config-migration 2024-04-28 14:31:43 -04:00
dunkeroni
f262b9032d fix: changed validation to not error on connection 2024-04-28 12:48:56 -04:00
dunkeroni
71c3197eab fix: denoise latents accepts CFG lists as input 2024-04-28 12:48:56 -04:00
psychedelicious
398f37c0ed tidy(backend): clean up controlnet_utils
- Use the our adaptation of the HWC3 function with better types
- Extraction some of the util functions, name them better, add comments
- Improve type annotations
- Remove unreachable codepaths
2024-04-25 13:20:09 +10:00
psychedelicious
5b8f77f990 tidy(nodes): move cnet mode literals to utils
Now they can be used in type signatures without circular imports.
2024-04-25 13:20:09 +10:00
Lincoln Stein
048306b417
Merge branch 'main' into lstein/feat/config-migration 2024-04-24 21:37:12 -04:00
Lincoln Stein
6eaed9a9cb check for strictly contiguous from_version->to_version ranges 2024-04-24 21:36:28 -04:00
psychedelicious
1bef13db37 feat(nodes): restore unet check on CreateGradientMaskInvocation
Special handling for inpainting models
2024-04-23 07:32:53 -04:00
dunkeroni
bc12d6654e chore: comments and ruff 2024-04-23 07:32:53 -04:00
dunkeroni
6d7c8d5f57 remove unet test 2024-04-23 07:32:53 -04:00
dunkeroni
781de914f4 fix threshhold 2024-04-23 07:32:53 -04:00
dunkeroni
c094bad233 add unet check in gradient mask node 2024-04-23 07:32:53 -04:00
dunkeroni
0063014f2b gradient mask node test for inpaint 2024-04-23 07:32:53 -04:00
psychedelicious
d12fb7db68 fix(config): fix duplicate migration logic
This was checking a `Version` object against a `MigrationEntry`, but what we want is to check the version object against `MigrationEntry.from_version`
2024-04-23 17:25:53 +10:00
psychedelicious
5d411e446a tidy(config): use a type alias for the migration function 2024-04-23 17:21:05 +10:00
psychedelicious
6f128c86b4 tidy(config): use dataclass for MigrationEntry
The only pydantic usage was to convert strings to `Version` objects. The reason to do this conversion was to allow the register decorator to accept strings. MigrationEntry is only created inside this class, so we can just create versions from each migration when instantiating MigrationEntry instead.

Also, pydantic doesn't provide runtime time checking for arbitrary classes like Version, so we don't get any real benefit.
2024-04-23 17:19:54 +10:00
psychedelicious
aca9e44a3a fix(config): use TypeAlias instead of TypeVar
TypeVar is for generics, but the usage here is as an alias
2024-04-23 17:12:19 +10:00
psychedelicious
2cee436ecf tidy(app): remove unused class 2024-04-23 17:12:14 +10:00
psychedelicious
e6386d969f fix(app): only clear tempdirs if ephemeral and before creating tempdir
Also, this needs to happen in init, else it deletes the temp dir created in init
2024-04-23 17:12:14 +10:00
psychedelicious
4b2b983646 tidy(api): reverted unnecessary changes in dependencies.py 2024-04-23 17:12:14 +10:00
Lincoln Stein
53808149fb moved cleanup routine into object_serializer_disk.py 2024-04-23 17:12:14 +10:00
Lincoln Stein
21ba55d0a6 add an initialization function that removes dangling tmpdirs from outputs/tensors 2024-04-23 17:12:14 +10:00
psychedelicious
e39f035264 tidy(config): removed extraneous ABC
We don't need separate implementations for this class, let's not complicate it with an ABC
2024-04-23 17:11:13 +10:00
psychedelicious
b612c73954 tidy(config): remove unused TYPE_CHECKING block 2024-04-23 17:09:50 +10:00
psychedelicious
a00e703144 feat(nodes): image mask to tensor invocation
Thanks @JPPhoto!
2024-04-20 11:32:08 -04:00
psychedelicious
ea527f5fe1 feat(nodes): add beta classification to mask tensor nodes 2024-04-19 09:32:56 -04:00
psychedelicious
aace364677 feat(nodes): add InvertTensorMaskInvocation 2024-04-19 09:32:56 -04:00
psychedelicious
602a59066e fix(nodes): handle invert in alpha_mask_to_tensor 2024-04-19 09:32:56 -04:00
psychedelicious
8911017bd1 feat(ui): selectable & draggable layers 2024-04-19 09:32:56 -04:00
psychedelicious
fc26f3e430 feat(nodes): add alpha mask to tensor invocation 2024-04-19 09:32:56 -04:00
Lincoln Stein
2b9f06dc4c
Re-enable app shutdown actions (#6244)
* closes #6242

* only override sigINT during slow model scanning

* fix ruff formatting

---------

Co-authored-by: Lincoln Stein <lstein@gmail.com>
2024-04-19 06:45:42 -04:00
Lincoln Stein
36495b730d use packaging.version rather than version-parse 2024-04-18 23:07:54 -04:00
Lincoln Stein
6ad1948a44 add InvokeAIAppConfig schema migration system 2024-04-18 21:33:54 -04:00
blessedcoolant
6bab040d24 Merge branch 'main' into ip-adapter-style-comp 2024-04-16 21:14:06 +05:30
Lincoln Stein
fce6b3e44c maybe solve race issue 2024-04-16 13:09:26 +10:00
blessedcoolant
b39ce642b6 cleanup: raise ValueErrors when target_blocks dont match base model 2024-04-16 04:12:30 +05:30
Lincoln Stein
e93f4d632d
[util] Add generic torch device class (#6174)
* introduce new abstraction layer for GPU devices

* add unit test for device abstraction

* fix ruff

* convert TorchDeviceSelect into a stateless class

* move logic to select context-specific execution device into context API

* add mock hardware environments to pytest

* remove dangling mocker fixture

* fix unit test for running on non-CUDA systems

* remove unimplemented get_execution_device() call

* remove autocast precision

* Multiple changes:

1. Remove TorchDeviceSelect.get_execution_device(), as well as calls to
   context.models.get_execution_device().
2. Rename TorchDeviceSelect to TorchDevice
3. Added back the legacy public API defined in `invocation_api`, including
   choose_precision().
4. Added a config file migration script to accommodate removal of precision=autocast.

* add deprecation warnings to choose_torch_device() and choose_precision()

* fix test crash

* remove app_config argument from choose_torch_device() and choose_torch_dtype()

---------

Co-authored-by: Lincoln Stein <lstein@gmail.com>
2024-04-15 13:12:49 +00:00
blessedcoolant
2d5786d3bb fix: Incorrect composition blocks for SD1.5 2024-04-13 13:52:10 +05:30
blessedcoolant
27466ffa1a chore: update the ip adapter node version 2024-04-13 13:39:08 +05:30