05deeb68fa
feat(ui): draft of graph helper for regional prompts
2024-04-19 09:32:56 -04:00
602a59066e
fix(nodes): handle invert in alpha_mask_to_tensor
2024-04-19 09:32:56 -04:00
d1db6198b5
perf(ui): memoize & otherwise optimize regional prompts ui
2024-04-19 09:32:56 -04:00
944fa1a847
chore(ui): lint
2024-04-19 09:32:56 -04:00
52e7daffe7
feat(ui): selected layer styling
2024-04-19 09:32:56 -04:00
cf4c1750cb
fix(ui): caching broke layer rendering
2024-04-19 09:32:56 -04:00
de7ecc8e3e
feat(ui): tweak bbox styling
2024-04-19 09:32:56 -04:00
6c0481ef51
fix(ui): do not reset layer position when toggling visibility
2024-04-19 09:32:56 -04:00
b9d0da44eb
feat(ui): wip layer transparency
2024-04-19 09:32:56 -04:00
0a42d7d510
docs(ui): update docstrings for helper function
2024-04-19 09:32:56 -04:00
c1aae0815d
feat(ui): regional prompting layout, styling
2024-04-19 09:32:56 -04:00
e7523bd1d9
fix(ui): fix layer debug
2024-04-19 09:32:56 -04:00
8911017bd1
feat(ui): selectable & draggable layers
2024-04-19 09:32:56 -04:00
fc26f3e430
feat(nodes): add alpha mask to tensor invocation
2024-04-19 09:32:56 -04:00
c89a24d1ea
feat(ui): add util to get blobs from layers
2024-04-19 09:32:56 -04:00
52ba4966c9
feat(ui): wip regional prompting UI
...
- Add eraser tool, applies per layer
2024-04-19 09:32:56 -04:00
822dfa77fc
feat(ui): wip regional prompting UI
...
- Arrange layers
- Layer visibility
- Layered brush preview
- Cleanup
2024-04-19 09:32:56 -04:00
83d359b681
feat(ui): wip regional prompting UI
2024-04-19 09:32:56 -04:00
f87eee810b
feat(ui): rough out regional prompts components
2024-04-19 09:32:56 -04:00
1d1e4d02dc
feat(ui): rough out regional prompts store
2024-04-19 09:32:56 -04:00
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
a35386f24c
fix: IP Adapter Method having incorrect informational popover
2024-04-18 13:37:55 -04:00
ac1071a5e5
chore: v4.1.0
2024-04-18 07:19:22 +10:00
c3d1252892
revert to old system for doing RAM <-> VRAM transfers; new way leaks memory
2024-04-17 09:51:57 -04:00
84f5cbdd97
make choose_torch_dtype() usable outside an invocation context
2024-04-16 19:19:19 -04:00
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
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
73ad173c74
update labels for Style Only and CompositionOnly to be designated as beta
2024-04-17 08:29:10 +10:00
edac01d4fb
reverse stupid hack
2024-04-16 18:13:59 -04:00
d04c880cce
fix ValueError on model manager install
2024-04-16 17:57:40 -04:00
763a2e2632
added more unit tests
2024-04-16 17:18:51 -04:00
eaadc55c7d
make pause/resume work in multithreaded environment
2024-04-16 16:55:56 -04:00
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
99558de178
device selection calls go through TorchDevice
2024-04-16 16:26:58 -04:00
77130f108d
Merge branch 'main' into lstein/feat/multi-gpu
2024-04-16 16:14:27 -04:00
371f5bc782
simplify logic for retrieving execution devices
2024-04-16 15:52:03 -04:00
fb9b7fb63a
make object_serializer._new_name() thread-safe; add max_threads config
2024-04-16 15:23:49 -04:00
bd833900a3
add tid to cache name to avoid non-safe uuid4 on windows
2024-04-16 15:02:06 -04:00
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.
### Example Result
### 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
6bab040d24
Merge branch 'main' into ip-adapter-style-comp
2024-04-16 21:14:06 +05:30
f46bbaf8c4
fix: make ip-adapter weights not be optional
2024-04-16 21:12:45 +05:30
fce6b3e44c
maybe solve race issue
2024-04-16 13:09:26 +10:00
a84f3058e2
revert object_serializer_forward_cache.py
2024-04-15 22:28:48 -04:00
f7436f3bae
fixup config_default; patch TorchDevice to work dynamically
2024-04-15 22:15:50 -04:00
7dd93cb810
fix merge issues; likely nonfunctional
2024-04-15 21:16:21 -04:00
d27907cc6d
fix: entire reshaping block needs to be skipped
2024-04-16 04:29:53 +05:30
7ee3fef2db
cleanup: better var names for the ip adapter weight collection block
2024-04-16 04:23:50 +05:30
b39ce642b6
cleanup: raise ValueErrors when target_blocks dont match base model
2024-04-16 04:12:30 +05:30
a148c4322c
fix: IP Adapter weights being incorrectly applied
...
They were being overwritten rather than being appended
2024-04-16 04:10:41 +05:30
f6b7bc5d98
fix: Dynamically adapt height of control adapter opts
2024-04-16 01:18:43 +05:30
