Commit Graph

1799 Commits

Author SHA1 Message Date
Sergey Borisov
68f993998a Add support for norm layer 2024-08-07 22:06:05 -04:00
Sergey Borisov
7da6120b39 Fix LoKR refactor bug 2024-08-07 22:06:05 -04:00
blessedcoolant
4f8a4b0f22 Merge branch 'main' into depth_anything_v2 2024-08-03 00:38:57 +05:30
blessedcoolant
a743f3c9b5 fix: implement model to func for depth anything 2024-08-03 00:37:17 +05:30
Ryan Dick
981475a624
Merge branch 'main' into ryan/grounded-sam 2024-08-01 20:30:35 +02:00
Ryan Dick
b9dc3460ba Rename SegmentAnythingModel -> SegmentAnythingPipeline. 2024-08-01 09:57:47 -04:00
Ryan Dick
63581ec980 (minor) Add None check to fix static type checking error. 2024-08-01 09:51:53 -04:00
Ryan Dick
5a9173f766 Merge branch 'main' into stalker-modular_lora 2024-07-31 15:13:22 -04:00
Ryan Dick
0bb7ed44f6 Add some docs to OriginalWeightsStorage and fix type hints. 2024-07-31 15:08:24 -04:00
blessedcoolant
daf899f9c4 fix: Move the manual image resizing out of the depth anything pipeline 2024-07-31 23:38:12 +05:30
blessedcoolant
95dde802ea fix: assert the return depth map to be a PIL image 2024-07-31 23:22:01 +05:30
Ryan Dick
fca119773b Split invokeai/backend/image_util/segment_anything/ dir into grounding_dino/ and segment_anything/ 2024-07-31 12:28:47 -04:00
Ryan Dick
0193267a53 Split GroundedSamInvocation into GroundingDinoInvocation and SegmentAnythingModelInvocation. 2024-07-31 12:20:23 -04:00
blessedcoolant
b4cf78a95d fix: make DA Pipeline a subclass of RawModel 2024-07-31 21:14:49 +05:30
Ryan Dick
73386826d6 Make GroundingDinoPipeline and SegmentAnythingModel subclasses of RawModel for type checking purposes. 2024-07-31 10:25:34 -04:00
Ryan Dick
9f448fecb7 Move invokeai/backend/grounded_sam -> invokeai/backend/image_util/grounded_sam 2024-07-31 10:00:30 -04:00
Ryan Dick
33e8604b57 Make Grounding DINO DetectionResult a Pydantic model. 2024-07-31 08:47:00 -04:00
blessedcoolant
328e58be4c
Merge branch 'main' into stalker7779/new_karras_schedulers 2024-07-31 05:56:13 +05:30
blessedcoolant
18f89ed5ed fix: Make DepthAnything work with Invoke's Model Management 2024-07-31 03:57:54 +05:30
Ryan Dick
5701c79fab Prevent Grounding DINO and Segment Anything from being moved to MPS - they don't work on MPS devices. 2024-07-30 23:04:15 +02:00
Ryan Dick
2da9f913f3 Add detection_result.py - was forgotten in a prior commit 2024-07-30 16:04:29 -04:00
Ryan Dick
918f77bce0 Move some logic from GroundedSAMInvocation to the backend classes. 2024-07-30 15:34:33 -04:00
blessedcoolant
f170697ebe Merge branch 'main' into depth_anything_v2 2024-07-31 00:53:32 +05:30
blessedcoolant
556c6a1d84 fix: Update DepthAnything to use the transformers implementation 2024-07-31 00:51:55 +05:30
Ryan Dick
aca2a2fa13 Add mask_filter and detection_threshold options to the GroundedSAMInvocation. 2024-07-30 14:22:40 -04:00
Ryan Dick
ff6398f7d8 Add a GroundedSamInvocation for image segmentation from a text prompt (Grounding DINO + Segment Anything Model). 2024-07-30 11:12:26 -04:00
Sergey Borisov
86f705bf48 Optimize weights handling 2024-07-30 03:39:01 +03:00
Sergey Borisov
1fd9631f2d Comments fix
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com>
2024-07-30 00:39:50 +03:00
Sergey Borisov
2227a2357f Suggested changes + simplify weights logic in patching
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com>
2024-07-30 00:34:37 +03:00
Sergey Borisov
58e7ab157d Ruff format 2024-07-29 22:59:17 +03:00
Sergey Borisov
8d16fa6a49 Remove dpmpp_3s schedulers as it bugged now 2024-07-29 22:55:45 +03:00
Sergey Borisov
55e810efa3 Add dpmpp_3 schedulers 2024-07-29 22:52:15 +03:00
Ryan Dick
693a3eaff5 Merge branch 'main' into stalker-modular_inpaint-2 2024-07-29 10:14:45 -04:00
Sergey Borisov
86a92bb6b5 Add more karras schedulers 2024-07-29 15:14:34 +03:00
Sergey Borisov
8500bac3ca Use logger for warning 2024-07-28 22:51:52 +03:00
Ryan Dick
310719eb4c Merge branch 'main' into stalker-modular_t2i_adapter 2024-07-28 15:30:00 -04:00
Ryan Dick
c57a7afb87
Merge branch 'main' into stalker7779/modular_seamless 2024-07-28 13:49:43 -04:00
Sergey Borisov
84d028898c Revert wrong comment copy 2024-07-27 13:20:58 +03:00
Sergey Borisov
ed0174fbc6 Suggested changes
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com>
2024-07-27 13:18:28 +03:00
Sergey Borisov
9e582563eb Suggested changes
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com>
2024-07-27 04:25:15 +03:00
Sergey Borisov
faa88f72bf Make lora as separate extensions 2024-07-27 02:39:53 +03:00
Sergey Borisov
5b84e117b2 Suggested changes
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com>
2024-07-26 20:51:12 +03:00
Sergey Borisov
5810cee6c9 Suggested changes
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com>
2024-07-26 19:47:28 +03:00
Sergey Borisov
adf1a977ea Suggested changes
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com>
2024-07-26 19:22:26 +03:00
psychedelicious
102b47190f feat(ui): update qr code cnet starter model
- For SD1.5, use the new V2 version
- Add the SDXL version
2024-07-26 13:34:32 +10:00
psychedelicious
74cef38bcf fix(backend): add refiner to single-file load_classes
Fixes single-file refiner loading.
2024-07-26 05:08:01 +10:00
blessedcoolant
e5d9ca013e fix: use v1 models for large and base versions 2024-07-25 17:24:12 +05:30
blessedcoolant
4166c756ce wip: depth_anything_v2 init lint fixes 2024-07-25 14:41:22 +05:30
blessedcoolant
4f0dfbd34d wip: depth_anything_v2 initial implementation 2024-07-25 13:53:06 +05:30
Sergey Borisov
46c632e7cc Change layer detection keys according to LyCORIS repository 2024-07-25 02:10:47 +03:00
Sergey Borisov
653f63ae71 Add layer keys check 2024-07-25 02:03:08 +03:00
Sergey Borisov
8a9e2f57a4 Handle bias in full/diff lora layer 2024-07-25 02:02:37 +03:00
Sergey Borisov
31949ed2f2 Refactor code a bit 2024-07-25 02:00:30 +03:00
Sergey Borisov
0ccb304b8b Ruff format 2024-07-24 16:01:29 +03:00
Sergey Borisov
ab0bfa709a Handle loras in modular denoise 2024-07-24 05:07:29 +03:00
Sergey Borisov
6af659b1da Handle t2i adapter in modular denoise 2024-07-24 02:55:33 +03:00
Sergey Borisov
416d29fb83 Ruff format 2024-07-24 01:17:28 +03:00
Sergey Borisov
19c00241c6 Use non-inverted mask generally(except inpaint model handling) 2024-07-24 00:59:13 +03:00
Lincoln Stein
633bbb4e85
[MM2] Use typed ModelRecordChanges for model_install() rather than untyped dict (#6645)
* [MM2] replace untyped config dict passed to install_model with typed ModelRecordChanges

- adjusted frontend to work with new schema
- used this facility to assign "starter model" names and descriptions to the installed
  models.

* documentation fix

* [MM2] replace untyped config dict passed to install_model with typed ModelRecordChanges

- adjusted frontend to work with new schema
- used this facility to assign "starter model" names and descriptions to the installed
  models.

* documentation fix

* remove v9 pnpm lockfile

* [MM2] replace untyped config dict passed to install_model with typed ModelRecordChanges

- adjusted frontend to work with new schema
- used this facility to assign "starter model" names and descriptions to the installed
  models.

* [MM2] replace untyped config dict passed to install_model with typed ModelRecordChanges

- adjusted frontend to work with new schema
- used this facility to assign "starter model" names and descriptions to the installed
  models.

* remove v9 pnpm lockfile

* regenerate schema.ts

* prettified

---------

Co-authored-by: Lincoln Stein <lstein@gmail.com>
2024-07-23 21:41:00 +00:00
Sergey Borisov
c323a760a5 Suggested changes
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com>
2024-07-23 23:34:28 +03:00
Sergey Borisov
ca21996a97 Remove old seamless class 2024-07-23 18:04:33 +03:00
Sergey Borisov
62aa064e56 Handle seamless in modular denoise 2024-07-23 18:03:59 +03:00
Ryan Dick
e2e47fd606 Merge branch 'main' into stalker-modular_controlnet 2024-07-23 10:19:12 -04:00
Ryan Dick
db52f5606f Merge branch 'main' into stalker-modular_freeu 2024-07-23 09:53:32 -04:00
Ryan Dick
39e804d0f8 Use consistent param names in patch_extension(...) functions: context -> ctx. 2024-07-23 09:18:04 -04:00
Sergey Borisov
4e8dcb7a1a Suggested changes
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com>
2024-07-23 01:46:29 +03:00
Sergey Borisov
3cb13d6288 Rename as suggested in other PRs
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com>
2024-07-23 01:01:18 +03:00
Sergey Borisov
5003e5d763 Same changes as in other PRs, add check for running inpainting on inpaint model without source image
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com>
2024-07-22 23:47:39 +03:00
Sergey Borisov
5f0fe3c8a9 Suggested changes
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com>
2024-07-22 23:09:11 +03:00
Sergey Borisov
1b359b55cb Suggested changes
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com>
2024-07-22 22:17:29 +03:00
Sergey Borisov
58f3072b91 Handle inpainting on normal models 2024-07-21 22:17:29 +03:00
Sergey Borisov
9e7b470189 Handle inpaint models 2024-07-21 20:45:55 +03:00
Sergey Borisov
42356ec866 Add ControlNet support to denoise 2024-07-21 20:01:30 +03:00
Sergey Borisov
1748848b7b Ruff fixes 2024-07-21 18:37:20 +03:00
Sergey Borisov
5772965f09 Fix slightly different output with old backend 2024-07-21 18:31:30 +03:00
Sergey Borisov
e046e60e1c Add FreeU support to denoise 2024-07-21 18:31:10 +03:00
Sergey Borisov
9a1420280e Add rescale cfg support to denoise 2024-07-21 17:33:43 +03:00
Mary Hipp
930ff559e4 add sdxl tile to starter models 2024-07-19 16:49:33 -04:00
Ryan Dick
78d2b1b650 Merge branch 'main' into stalker-backend_base 2024-07-19 16:25:20 -04:00
Sergey Borisov
39e10d894c Add invocation cancellation logic to patchers 2024-07-19 23:17:01 +03:00
Ryan Dick
e16faa6370 Add gradient blending to tile seams in MultiDiffusion. 2024-07-19 13:05:50 -07:00
Ryan Dick
83a86abce2 Add unit tests for ExtensionsManager and ExtensionBase. 2024-07-19 14:15:46 -04:00
Sergey Borisov
0c56d4a581 Ryan's suggested changes to extension manager/extensions
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com>
2024-07-18 23:49:44 +03:00
Lincoln Stein
97a7f51721
don't use cpu state_dict for model unpatching when executing on cpu (#6631)
Co-authored-by: Lincoln Stein <lstein@gmail.com>
2024-07-18 15:34:01 -04:00
StAlKeR7779
710dc6b487
Merge branch 'main' into stalker7779/backend_base 2024-07-18 01:08:04 +03:00
Sergey Borisov
2ef3b49a79 Add run cancelling logic to extension manager 2024-07-17 04:39:15 +03:00
Sergey Borisov
3f79467f7b Ruff format 2024-07-17 04:24:45 +03:00
Sergey Borisov
2c2ec8f0bc Comments, a bit refactor 2024-07-17 04:20:31 +03:00
Sergey Borisov
79e35bd0d3 Minor fixes 2024-07-17 03:48:37 +03:00
Sergey Borisov
137202b77c Remove patch_unet logic for now 2024-07-17 03:40:27 +03:00
Sergey Borisov
03e22c257b Convert conditioning_mode to enum 2024-07-17 03:37:11 +03:00
Sergey Borisov
ae6d4fbc78 Move out _concat_conditionings_for_batch submethods 2024-07-17 03:31:26 +03:00
Sergey Borisov
cd1bc1595a Rename sequential as private variable 2024-07-17 03:24:11 +03:00
Ryan Dick
f866b49255 Add some ESRGAN and SwinIR upscale models to the starter models list. 2024-07-16 15:55:10 -04:00
Sergey Borisov
b7c6c63005 Added some comments 2024-07-16 22:52:44 +03:00
Ryan Dick
6b0ca88177
Merge branch 'main' into ryan/spandrel-upscale-tiling 2024-07-16 15:40:14 -04:00
Ryan Dick
81991e072b Merge branch 'main' into ryan/spandrel-upscale 2024-07-16 15:14:08 -04:00
Sergey Borisov
cec345cb5c Change attention processor apply logic 2024-07-16 20:03:29 +03:00
Sergey Borisov
608cbe3f5c Separate inputs in denoise context 2024-07-16 19:30:29 +03:00
psychedelicious
38343917f8 fix(backend): revert non-blocking device transfer
In #6490 we enabled non-blocking torch device transfers throughout the model manager's memory management code. When using this torch feature, torch attempts to wait until the tensor transfer has completed before allowing any access to the tensor. Theoretically, that should make this a safe feature to use.

This provides a small performance improvement but causes race conditions in some situations. Specific platforms/systems are affected, and complicated data dependencies can make this unsafe.

- Intermittent black images on MPS devices - reported on discord and #6545, fixed with special handling in #6549.
- Intermittent OOMs and black images on a P4000 GPU on Windows - reported in #6613, fixed in this commit.

On my system, I haven't experience any issues with generation, but targeted testing of non-blocking ops did expose a race condition when moving tensors from CUDA to CPU.

One workaround is to use torch streams with manual sync points. Our application logic is complicated enough that this would be a lot of work and feels ripe for edge cases and missed spots.

Much safer is to fully revert non-locking - which is what this change does.
2024-07-16 08:59:42 +10:00