Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity
11,118 Commits 274 Branches 239 Tags 397 MiB
1c0067f931
Commit Graph

11118 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
psychedelicious
cf4c1750cb fix(ui): caching broke layer rendering 2024-04-19 09:32:56 -04:00
psychedelicious
de7ecc8e3e feat(ui): tweak bbox styling 2024-04-19 09:32:56 -04:00
psychedelicious
6c0481ef51 fix(ui): do not reset layer position when toggling visibility 2024-04-19 09:32:56 -04:00
psychedelicious
b9d0da44eb feat(ui): wip layer transparency 2024-04-19 09:32:56 -04:00
psychedelicious
0a42d7d510 docs(ui): update docstrings for helper function 2024-04-19 09:32:56 -04:00
psychedelicious
c1aae0815d feat(ui): regional prompting layout, styling 2024-04-19 09:32:56 -04:00
psychedelicious
e7523bd1d9 fix(ui): fix layer debug 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
psychedelicious
c89a24d1ea feat(ui): add util to get blobs from layers 2024-04-19 09:32:56 -04:00
psychedelicious
52ba4966c9 feat(ui): wip regional prompting UI 
- Add eraser tool, applies per layer
 2024-04-19 09:32:56 -04:00
psychedelicious
822dfa77fc feat(ui): wip regional prompting UI 
- Arrange layers
- Layer visibility
- Layered brush preview
- Cleanup
 2024-04-19 09:32:56 -04:00
psychedelicious
83d359b681 feat(ui): wip regional prompting UI 2024-04-19 09:32:56 -04:00
psychedelicious
f87eee810b feat(ui): rough out regional prompts components 2024-04-19 09:32:56 -04:00
psychedelicious
1d1e4d02dc feat(ui): rough out regional prompts store 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
blessedcoolant
a35386f24c fix: IP Adapter Method having incorrect informational popover 2024-04-18 13:37:55 -04:00
psychedelicious
ac1071a5e5 chore: v4.1.0 2024-04-18 07:19:22 +10:00
Lincoln Stein
c3d1252892 revert to old system for doing RAM <-> VRAM transfers; new way leaks memory 2024-04-17 09:51:57 -04:00
Lincoln Stein
84f5cbdd97 make choose_torch_dtype() usable outside an invocation context 2024-04-16 19:19:19 -04:00
Riccardo Giovanetti
5295a398f3 translationBot(ui): update translation (Italian) 
Currently translated at 98.4% (1122 of 1140 strings)

Co-authored-by: Riccardo Giovanetti <riccardo.giovanetti@gmail.com>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/it/
Translation: InvokeAI/Web UI
 2024-04-17 08:41:57 +10:00
Anonymous
0c7283c82d translationBot(ui): update translation (Turkish) 
Currently translated at 50.8% (580 of 1140 strings)

translationBot(ui): update translation (Korean)

Currently translated at 43.3% (494 of 1140 strings)

translationBot(ui): update translation (Chinese (Simplified))

Currently translated at 80.9% (923 of 1140 strings)

translationBot(ui): update translation (Russian)

Currently translated at 98.8% (1127 of 1140 strings)

translationBot(ui): update translation (Dutch)

Currently translated at 63.7% (727 of 1140 strings)

translationBot(ui): update translation (Japanese)

Currently translated at 50.4% (575 of 1140 strings)

translationBot(ui): update translation (Italian)

Currently translated at 98.3% (1121 of 1140 strings)

translationBot(ui): update translation (Spanish)

Currently translated at 27.8% (317 of 1140 strings)

translationBot(ui): update translation (German)

Currently translated at 72.2% (824 of 1140 strings)

Co-authored-by: Anonymous <noreply@weblate.org>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/de/
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/es/
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/it/
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/ja/
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/ko/
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/nl/
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/ru/
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/tr/
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/zh_Hans/
Translation: InvokeAI/Web UI
 2024-04-17 08:41:57 +10:00
Mary Hipp
73ad173c74 update labels for Style Only and CompositionOnly to be designated as beta 2024-04-17 08:29:10 +10:00
Lincoln Stein
edac01d4fb reverse stupid hack 2024-04-16 18:13:59 -04:00
Lincoln Stein
d04c880cce fix ValueError on model manager install 2024-04-16 17:57:40 -04:00
Lincoln Stein
763a2e2632 added more unit tests 2024-04-16 17:18:51 -04:00
Lincoln Stein
eaadc55c7d make pause/resume work in multithreaded environment 2024-04-16 16:55:56 -04:00
Lincoln Stein
89f8326c0b Merge branch 'lstein/feat/multi-gpu' of github.com:invoke-ai/InvokeAI into lstein/feat/multi-gpu 2024-04-16 16:27:08 -04:00
Lincoln Stein
99558de178 device selection calls go through TorchDevice 2024-04-16 16:26:58 -04:00
Lincoln Stein
77130f108d
Merge branch 'main' into lstein/feat/multi-gpu 2024-04-16 16:14:27 -04:00
Lincoln Stein
371f5bc782 simplify logic for retrieving execution devices 2024-04-16 15:52:03 -04:00
Lincoln Stein
fb9b7fb63a make object_serializer._new_name() thread-safe; add max_threads config 2024-04-16 15:23:49 -04:00
Lincoln Stein
bd833900a3 add tid to cache name to avoid non-safe uuid4 on windows 2024-04-16 15:02:06 -04:00
Kent Keirsey
c828a4e59f
Add IP Adapter Style & Composition Modes (#6213) 
## Summary

Until now IP Adapter had complete control on the contents of the output.
With this PR, users are now able to select "Style Only" or "Composition
Only" to draw just the style or layout of the reference image.

Based off: https://arxiv.org/abs/2404.02733

### New IP Method Option

- `Full` - Both style and layout of the refence image are used.
- `Style Only` - Only the style of the image is used
- `Composition Only` - Only the composition of the image is used.


![opera_0BkqZTwObO](https://github.com/invoke-ai/InvokeAI/assets/54517381/1b2fbbba-44c9-4c25-87cb-3711a17d13e3)

### Example Result


![demo](https://github.com/invoke-ai/InvokeAI/assets/54517381/703f3de5-e685-4691-acda-9338a4c10796)

### Notes

- Supports both SDXL and SD1.5

### Testing

- Just check and test if it works as expected with all IP Adapter models
- both SDXL and SD1.5

## Merge Plan

Good to merge once tested for all edge cases.
 2024-04-16 14:23:36 -04:00
blessedcoolant
6bab040d24 Merge branch 'main' into ip-adapter-style-comp 2024-04-16 21:14:06 +05:30
blessedcoolant
f46bbaf8c4 fix: make ip-adapter weights not be optional 2024-04-16 21:12:45 +05:30
Lincoln Stein
fce6b3e44c maybe solve race issue 2024-04-16 13:09:26 +10:00
Lincoln Stein
a84f3058e2 revert object_serializer_forward_cache.py 2024-04-15 22:28:48 -04:00
Lincoln Stein
f7436f3bae fixup config_default; patch TorchDevice to work dynamically 2024-04-15 22:15:50 -04:00
Lincoln Stein
7dd93cb810 fix merge issues; likely nonfunctional 2024-04-15 21:16:21 -04:00
blessedcoolant
d27907cc6d fix: entire reshaping block needs to be skipped 2024-04-16 04:29:53 +05:30
blessedcoolant
7ee3fef2db cleanup: better var names for the ip adapter weight collection block 2024-04-16 04:23:50 +05:30
blessedcoolant
b39ce642b6 cleanup: raise ValueErrors when target_blocks dont match base model 2024-04-16 04:12:30 +05:30
blessedcoolant
a148c4322c fix: IP Adapter weights being incorrectly applied 
They were being overwritten rather than being appended
 2024-04-16 04:10:41 +05:30
blessedcoolant
f6b7bc5d98 fix: Dynamically adapt height of control adapter opts 2024-04-16 01:18:43 +05:30
blessedcoolant
5f6c6abf9c chore: change IPAdapterAttentionWeights to a dataclass 2024-04-15 23:38:55 +05:30
blessedcoolant
cd76a31a8f fix: IP Adapter method not being recalled 2024-04-15 22:29:32 +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
psychedelicious
5a8489bbfc perf(ui): memoize infill components 2024-04-15 22:50:54 +10:00
psychedelicious
a24c9d0f7a perf(ui): optimize useFeatureStatus 2024-04-15 22:50:54 +10:00