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
10,911 Commits 274 Branches 239 Tags 397 MiB
5924dc6ff6
Commit Graph

6213 Commits

Author SHA1 Message Date
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
psychedelicious
7a92afc117 perf(ui): fix rerenders in nodes 
Unmemoized selector tanking perf
 2024-04-15 22:50:54 +10:00
psychedelicious
b508945b11 feat(ui): edge labels 
Add setting to render labels with format `Source Node label -> Target Node label` on edges.
 2024-04-15 22:48:46 +10:00
Lars Kappert
06bc38d3f4 Remove tag excluder 2024-04-15 09:14:49 +10:00
Lars Kappert
d3b0212da5 Scope project files to src dir (enables --production) 2024-04-15 09:14:49 +10:00
Lars Kappert
c2b79ce14c Replace @knipignore with paths config 2024-04-15 09:14:49 +10:00
Васянатор
70185b0173 translationBot(ui): update translation (Russian) 
Currently translated at 99.5% (1128 of 1133 strings)

Co-authored-by: Васянатор <ilabulanov339@gmail.com>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/ru/
Translation: InvokeAI/Web UI
 2024-04-15 09:12:38 +10:00
怀瑾
a83a0c6146 translationBot(ui): update translation (Chinese (Simplified)) 
Currently translated at 81.5% (924 of 1133 strings)

Co-authored-by: 怀瑾 <symant233@gmail.com>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/zh_Hans/
Translation: InvokeAI/Web UI
 2024-04-15 09:12:38 +10:00
Riccardo Giovanetti
12f41039cc translationBot(ui): update translation (Italian) 
Currently translated at 98.4% (1122 of 1140 strings)

translationBot(ui): update translation (Italian)

Currently translated at 98.4% (1120 of 1138 strings)

translationBot(ui): update translation (Italian)

Currently translated at 98.4% (1115 of 1133 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
 2024-04-15 09:12:38 +10:00
Daniel Abrao
b3b5b7e261 Include hardcoded count of one to avoid translation issues on missing keys 2024-04-15 09:10:15 +10:00
Daniel Abrao
f706a13230 Adjust gallery image length handling 2024-04-15 09:10:15 +10:00
Daniel Abrao
22c6400bb8 Refactor i18n pluralization 2024-04-15 09:10:15 +10:00
Daniel Abrao
1ca152f6c8 Apply eslint/prettier fixes 2024-04-15 09:10:15 +10:00
Daniel Abrao
982e255878 Add dynamic label to delete button located at the top toolbar 2024-04-15 09:10:15 +10:00
Daniel Abrao
7899149144 Remove unnecessary word 2024-04-15 09:10:15 +10:00
Daniel Abrao
bef97b46bf Apply eslint/prettier fixes 2024-04-15 09:10:15 +10:00
Daniel Abrao
cc256fee0e Modify the modal title to include selected image array length 2024-04-15 09:10:15 +10:00
Daniel Abrao
ec69a58c8d Include plural variation for delete image modal title 2024-04-15 09:10:15 +10:00
Daniel Abrao
ec67ba61db Pass an array of selected images instead of imageDTO 2024-04-15 09:10:15 +10:00
Daniel Abrao
66126996e7 Import image selection 2024-04-15 09:10:15 +10:00
Jennifer Player
4eb66a9198 remove hires fix badge from settings when using sdxl 2024-04-15 07:57:58 +10:00
Daniel Abrao
14e41a1fd9 Remove unnecessary whitespace 2024-04-15 07:54:36 +10:00
Daniel Abrao
fc55522003 Import hook in the main App script 2024-04-15 07:54:36 +10:00
Daniel Abrao
cd6d8ae9cc Add a hook as a singleton to update favicon and title upon queueSize change 2024-04-15 07:54:36 +10:00
Daniel Abrao
2933eb594d Remove unnecessary code 2024-04-15 07:54:36 +10:00
Daniel Abrao
4e08fab3f5 Apply brand red color and a black border 2024-04-15 07:54:36 +10:00
Daniel Abrao
8bca7e2aa2 Apply eslint/prettier fixes 2024-04-15 07:54:36 +10:00
Daniel Abrao
3706cf0ad4 Add JSDoc strings 2024-04-15 07:54:36 +10:00
Daniel Abrao
a459361376 Modify the processing to consider the active queue length instead of in_progress only 2024-04-15 07:54:36 +10:00
Daniel Abrao
bb330d50a6 Increase favicon alert detail size 2024-04-15 07:54:36 +10:00
Daniel Abrao
102cb62960 Apply eslint/prettier fixes 2024-04-15 07:54:36 +10:00
Daniel Abrao
8eeab22ecd Replace let with const 2024-04-15 07:54:36 +10:00
Daniel Abrao
4343852b83 Update HTML page title and favicon upon queue item event 2024-04-15 07:54:36 +10:00
Daniel Abrao
0a9bf25bff Implement updatePageTitle and updatePageFavicon methods 2024-04-15 07:54:36 +10:00
Daniel Abrao
4cd09850b8 Add ID to the HTML link element 2024-04-15 07:54:36 +10:00
Daniel Abrao
dbc586e0b2 Add alert variation for Invoke favicon 2024-04-15 07:54:36 +10:00
blessedcoolant
8426f1e7b2 fix(experimental): Possible fix for conflict with regional embed length mismatch 
Pushing this so people can test it out and see if this needs to be handled in a different way.
 2024-04-14 12:19:19 +05:30
Jennifer Player
c2e3c61f28 fix recall all when loras, controls, or hrf arent present 2024-04-14 16:49:14 +10:00
Jennifer Player
77b3281f08 prettier 2024-04-14 15:22:33 +10:00
Jennifer Player
bd7c8cd517 added info popover back to model, updated description hover to combobox only 2024-04-14 15:22:33 +10:00
Jennifer Player
489d485907 added missing description to control adapters hover 2024-04-14 15:22:33 +10:00
Jennifer Player
6eed5ad531 added button for hiding bounding box 2024-04-14 15:22:33 +10:00
blessedcoolant
9cb0f63c44 refactor: fix a bunch of type issues in custom_attention 2024-04-13 14:17:25 +05:30
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
blessedcoolant
f50b156511 chore: do not include custom nodes in schema 2024-04-13 12:43:49 +05:30
blessedcoolant
9fc73743b2 feat: support SD1.5 2024-04-13 12:30:39 +05:30
blessedcoolant
d4393e4170 chore: linter fixes 2024-04-13 12:14:45 +05:30
blessedcoolant
7a67fd6a06 Revert "chore: ruff fixes" 
This reverts commit af36fe8c1e.
 2024-04-13 12:10:20 +05:30
blessedcoolant
af36fe8c1e chore: ruff fixes 2024-04-13 12:08:52 +05:30
blessedcoolant
e9f16ac8c7 feat: add UI for IP Adapter Method 2024-04-13 12:06:59 +05:30
blessedcoolant
6ea183f0d4 wip: Initial Implementation IP Adapter Style & Comp Modes 2024-04-13 11:09:45 +05:30
Mark E. Shoulson
24f2cde862 Remove type="submit" from all tsx files. 
Fixes a problem on firefox, at least for me.
 2024-04-12 09:09:32 +10:00
psychedelicious
b18442ded4 fix(queue): poll queue on finished queue item 
When a queue item is finished (completed, canceled, failed), immediately poll the queue for the next queue item.

Closes #6189
 2024-04-12 07:31:47 +10:00
Lincoln Stein
651c0b39b1 clear cache on all exceptions 2024-04-12 07:19:16 +10:00
Lincoln Stein
46d23cd868 catch RunTimeError during model to() call rather than OutOfMemoryError 2024-04-12 07:19:16 +10:00
Lincoln Stein
dedf0c6ffa fix ruff issues 2024-04-12 07:19:16 +10:00
Lincoln Stein
579082ac10 [mm] clear the cache entry for a model that got an OOM during loading 2024-04-12 07:19:16 +10:00
psychedelicious
7bc77ddb40 fix(nodes): doubly-noised latents 
When using refiner with a mask (i.e. inpainting), we don't have noise provided as an input to the node.

This situation uniquely hits a code path that wasn't reviewed when gradient denoising was implemented.

That code path does two things wrong:
- It lerp'd the input latents. This was fixed in 5a1f4cb1ce.
- It added noise to the latents an extra time. This is fixed in this change.

We don't need to add noise in `latents_from_embeddings` because we do it just a lines later in `AddsMaskGuidance`.

- Remove the extraneous call to `add_noise`
- Make `seed` a required arg. We never call the function without seed anyways. If we refactor this in the future, it will be clearer that we need to look at how seed is handled.
- Move the call to create the noise to a deeper conditional, just before we call `AddsMaskGuidance`. The created noise tensor is now only used in that function, no need to create it every time.

Note: Whether or not having both noise and latents as inputs on the node is correct is a separate conversation. This change just fixes the issue with the current setup.
 2024-04-11 07:21:50 -04:00
psychedelicious
026d095afe fix(nodes): do not set seed on output latents from denoise latents 
`LatentsField` objects have an optional `seed` field. This should only be populated when the latents are noise, generated from a seed.

`DenoiseLatentsInvocation` needs a seed value for scheduler initialization. It's used in a few places, and there is some logic for determining the seed to use with a series of fallbacks:
- Use the seed from the noise (a `LatentsField` object)
- Use the seed from the latents (a `LatentsField` object - normally it won't have a seed)
- Use `0` as a final fallback

In `DenoisLatentsInvocation`, we set the seed in the `LatentsOutput`, even though the output latents are not noise.

This is normally fine, but when we use refiner, we re-use the those same latents for the refiner denoise. This causes that characteristic same-seed-fried look on the refiner pass.

Simple fix - do not set the field in the output latents.
 2024-04-11 07:21:50 -04:00
psychedelicious
7e2ade50e1 fix(ui): canvas staging area & batch handling fixes 
Handful of intertwined fixes.

- Create and use helper function to reset staging area.
- Clear staging area when queue items are canceled, failed, cleared, etc. Fixes a bug where the bbox ends up offset and images are put into the wrong spot.
- Fix a number of similar bugs where canvas would "forget" it had pending generations, but they continued to generate. Canvas needs to track batches that should be displayed in it using `state.canvas.batchIds`, and this was getting cleared without actually canceling those batches.
- Disable the `discard current image` button on canvas if there is only one image. Prevents accidentally canceling all canvas batches if you spam the button.
 2024-04-10 21:48:34 +10:00
psychedelicious
c0d54d5414 Revert "always enqueue with fresh bounding box" 
This reverts commit fae51da278b39c61cbbea5de88661b4bc546f1ce.
 2024-04-10 21:48:34 +10:00
Mary Hipp
98bfbb73ac always enqueue with fresh bounding box 2024-04-10 21:48:34 +10:00
Ryan Dick
f9af32a6d1 Fix the padding behavior when max-pooling regional IP-Adapter masks to mirror the downscaling behavior of SD and SDXL. Prior to this change, denoising with input latent dimensions that were not evenly divisible by 8 would raise an exception. 2024-04-09 16:50:43 -04:00
Ryan Dick
fba40eb1bd Fix the padding behavior when max-pooling regional prompt masks to mirror the downscaling behavior of SD and SDXL. Prior to this change, denoising with input latent dimensions that were not evenly divisible by 8 would raise an exception. 2024-04-09 16:50:43 -04:00
Jonathan
80d631118d
Fix field ordering 
Changed fields to go in w/h x/y order.
 2024-04-09 14:17:55 -05:00
Ryan Dick
0c6dd32ece (minor) Fix IP-Adapter conditional logic in CustomAttnProcessor2_0. 2024-04-09 15:06:51 -04:00
Ryan Dick
0bdbfd4d1d Add support for IP-Adapter masks. 2024-04-09 15:06:51 -04:00
Ryan Dick
2e27ed5f3d Pass IP-Adapter scales through the cross_attn_kwargs pathway, since they are the same for all attention layers. This change also helps to prepare for adding IP-Adapter region masks. 2024-04-09 15:06:51 -04:00
Ryan Dick
babdc64b17 (minor) Fix typo in IP-Adapter field description. 2024-04-09 15:06:51 -04:00
Ryan Dick
4a828818da Remove support for Prompt-to-Prompt cross-attention control (aka .swap()). This feature is not widely used. It does not work with SDXL and is incompatible with IP-Adapter and regional prompting. The implementation is also intertwined with both text embedding and the UNet attention layers, resulting in a high maintenance burden. For all of these reasons, we have decided to drop support. 2024-04-09 10:57:02 -04:00
psychedelicious
fe386252f3 Revert "feat(nodes): add prompt region from image nodes" 
This reverts commit 3a531c5097.
 2024-04-09 08:12:12 -04:00
Ryan Dick
182810337c Add utility to_standard_float_mask(...) to convert various mask formats to a standardized format. 2024-04-09 08:12:12 -04:00
Ryan Dick
338bf808d6 Rename MaskField to be a generice TensorField. 2024-04-09 08:12:12 -04:00
Ryan Dick
5b5a4204a1 Fix dimensions of mask produced by ExtractMasksAndPromptsInvocation. Also, added a clearer error message in case the same error is introduced in the future. 2024-04-09 08:12:12 -04:00
Ryan Dick
75ef473748 Pull the upstream changes from diffusers' AttnProcessor2_0 into CustomAttnProcessor2_0. This fixes a bug in CustomAttnProcessor2_0 that was being triggered when peft was not installed. The bug was present in a block of code that was previously copied from diffusers. The bug seems to have been introduced during diffusers' migration to PEFT for their LoRA handling. The upstream bug was fixed in 531e719163. 2024-04-09 08:12:12 -04:00
psychedelicious
926b8d0efe feat(nodes): add prompt region from image nodes 2024-04-09 08:12:12 -04:00
Ryan Dick
9d9d1761f3 (minor) The latest ruff version has _slightly_ different formatting preferences. 2024-04-09 08:12:12 -04:00
Ryan Dick
a78df8123f Update the diffusion logic to use the new regional prompting feature. 2024-04-09 08:12:12 -04:00
Ryan Dick
7ca677578e Create a UNetAttentionPatcher for patching UNet models with CustomAttnProcessor2_0 modules. 2024-04-09 08:12:12 -04:00
Ryan Dick
31c456c1e6 Update CustomAttention to support both IP-Adapters and regional prompting. 2024-04-09 08:12:12 -04:00
Ryan Dick
2ce79b61f5 Initialize a RegionalPromptAttnProcessor2_0 class by copying AttnProcessor2_0 from diffusers. 2024-04-09 08:12:12 -04:00
Ryan Dick
109e3f0e7f Add RegionalPromptData class for managing prompt region masks. 2024-04-09 08:12:12 -04:00
Ryan Dick
dc64fec771 Add support for lists of prompt embeddings to be passed to the DenoiseLatents invocation, and add handling of the conditioning region masks in DenoiseLatents. 2024-04-09 08:12:12 -04:00
Ryan Dick
d1e45585d0 Add TextConditioningRegions to the TextConditioningData data structure. 2024-04-09 08:12:12 -04:00
Ryan Dick
aba023e0c5 Improve documentation of conditioning_data.py. 2024-04-09 08:12:12 -04:00
Ryan Dick
e354c29b52 Rename ConditioningData -> TextConditioningData. 2024-04-09 08:12:12 -04:00
Ryan Dick
a7f363e654 Split ip_adapter_conditioning out from ConditioningData. 2024-04-09 08:12:12 -04:00
Ryan Dick
9b2162e564 Remove scheduler_args from ConditioningData structure. 2024-04-09 08:12:12 -04:00
Ryan Dick
4e64b26702 Update compel nodes to accept an optional prompt mask. 2024-04-09 08:12:12 -04:00
Ryan Dick
c22d772062 Add RectangleMaskInvocation. 2024-04-09 08:12:12 -04:00
Ryan Dick
d6be7662c9 Add a MaskField primitive, and add a mask to the ConditioningField primitive type. 2024-04-09 08:12:12 -04:00
blessedcoolant
95050088d1 chore: lint fixes 2024-04-09 14:13:10 +10:00
blessedcoolant
94b5084cd5 fix: one man's max is another man's min 2024-04-09 14:13:10 +10:00
blessedcoolant
ca0d60bee6 fix: set coherence denoise to 0.2 min for refiner models 2024-04-09 14:13:10 +10:00
blessedcoolant
fd1f240853 fix: SDXL Refiner not working properly with Inpainting 2024-04-09 14:13:10 +10:00