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
12,029 Commits 274 Branches 239 Tags 397 MiB
7e00526999
Commit Graph

7254 Commits

Author SHA1 Message Date
psychedelicious
689dc30f87 feat(ui): tweak pagination buttons 
- Fix off-by-one error when going to last page
- Update component to have minimal/no layout shift
 2024-06-27 13:48:40 +10:00
psychedelicious
1f22f6ae02 feat(ui): iterate on dynamic gallery limit 
- Simplify the gallery layout
- Set an initial gallery limit to load _some_ images immediately.
- Refactor the resize observer to use the actual rendered image component to calculate the number of images per row/col. This prevents inaccuracies caused by image padding that could result in the wrong number of images.
- Debounce the limit update to not thrash teh API
- Use absolute positioning trick to ensure the gallery container is always exactly the right size
- Minimum of `imagesPerRow` images loaded at all times
 2024-06-27 13:48:40 +10:00
psychedelicious
9c931d9ca0 fix(ui): gallery content overflow 
This is one of those unexpected CSS quirks. Flex containers need min-width or min-height for their children to not overflow. Add `minH={0}` to gallery container.
 2024-06-27 13:48:40 +10:00
Mary Hipp
e0a241fa4f wip change limit based on size of gallery 2024-06-27 13:48:40 +10:00
Mary Hipp
6a4b4ee340 trying to invalidate all the tags 2024-06-27 13:48:40 +10:00
Mary Hipp
488bf21925 fix single pagers 2024-06-27 13:48:40 +10:00
Mary Hipp
c9c39c02b6 handle generations coming in, fix pagination to use total from list query so it updates as that changes 2024-06-27 13:48:40 +10:00
Mary Hipp
5101dc4bef some cleanup, add page buttons 2024-06-27 13:48:40 +10:00
Mary Hipp
98c77a3ed1 pull in spencers work 2024-06-27 13:48:40 +10:00
psychedelicious
4fca62680d Update invokeai_version.py 2024-06-27 10:41:01 +10:00
Ryan Dick
9a3b8c6fcb Fix handling of init_timestep in StableDiffusionGeneratorPipeline and improve its documentation. 2024-06-26 12:51:51 -04:00
Ryan Dick
bd74b84cc5 Revert "Remove the redundant init_timestep parameter that was being passed around. It is simply the first element of the timesteps array." 
This reverts commit fa40061eca.
 2024-06-26 12:51:51 -04:00
Brandon Rising
dc23bebebf Run ruff 2024-06-26 21:46:59 +10:00
Kent Keirsey
38b6f90c02 Update prevention exception message 2024-06-26 21:46:59 +10:00
Ryan Dick
cd9dfefe3c Fix inpainting mask shape assertions. 2024-06-25 11:31:52 -07:00
Ryan Dick
b9946e50f9 Use image-space tile dimensions on the TiledMultiDiffusionDenoiseLatents invocation. This is more natural for many users. 2024-06-25 11:31:52 -07:00
Ryan Dick
06f49a30f6 Mark TiledMultiDiffusionDenoiseLatents as a Beta node. 2024-06-25 11:31:52 -07:00
Ryan Dick
e1af78c702 Make the tile_overlap input to MultiDiffusion *strictly* control the amount of overlap rather than being a lower bound. 2024-06-25 11:31:52 -07:00
Ryan Dick
c5588e1ff7 Add TODO comment explaining why some schedulers do not interact well with MultiDiffusion. 2024-06-25 11:31:52 -07:00
Ryan Dick
07ac292680 Consolidate _region_step() function - the separation wasn't really adding any value. 2024-06-25 11:31:52 -07:00
Ryan Dick
7c032ea604 (minor) Fix some documentation typos. 2024-06-25 11:31:52 -07:00
Ryan Dick
c5ee415607 Add progress image callbacks to TiledMultiDiffusionDenoiseLatentsInvocation. 2024-06-25 11:31:52 -07:00
Ryan Dick
fa40061eca Remove the redundant init_timestep parameter that was being passed around. It is simply the first element of the timesteps array. 2024-06-25 11:31:52 -07:00
Ryan Dick
7cafd78d6e Revert "Expose vae_decode(...) as a staticmethod on LatentsToImageInvocation." 
This reverts commit 753239b48d.
 2024-06-25 11:31:52 -07:00
Ryan Dick
8a43656cf9 (minor) Address a few small TODOs. 2024-06-25 11:31:52 -07:00
Ryan Dick
bd3b6ca11b Remove TiledStableDiffusionRefineInvocation. It was a proof-of-concept that has been superseded by TiledMultiDiffusionDenoiseLatents. 2024-06-25 11:31:52 -07:00
Ryan Dick
ceae5fe1db (minor) typo 2024-06-25 11:31:52 -07:00
Ryan Dick
25067e4f0d Delete rough notes. 2024-06-25 11:31:52 -07:00
Ryan Dick
fb0aaa3e6d Fix advanced scheduler behaviour in MultiDiffusionPipeline. 2024-06-25 11:31:52 -07:00
Ryan Dick
c22526b9d0 Fix handling of stateful schedulers in MultiDiffusionPipeline. 2024-06-25 11:31:52 -07:00
Ryan Dick
c881882f73 Connect TiledMultiDiffusionDenoiseLatents to the MultiDiffusionPipeline backend. 2024-06-25 11:31:52 -07:00
Ryan Dick
36473fc52a Remove regional conditioning logic from MultiDiffusionPipeline - it is not yet supported. 2024-06-25 11:31:52 -07:00
Ryan Dick
b9964ecc4a Initial (untested) implementation of MultiDiffusionPipeline. 2024-06-25 11:31:52 -07:00
Ryan Dick
051af802fe Remove inpainting support from MultiDiffusionPipeline. 2024-06-25 11:31:52 -07:00
Ryan Dick
3ff2e558d9 Remove IP-Adapter and T2I-Adapter support from MultiDiffusionPipeline. 2024-06-25 11:31:52 -07:00
Ryan Dick
fc187c9253 Document plan for the rest of the MultiDiffusion implementation. 2024-06-25 11:31:52 -07:00
Ryan Dick
605f460c7d Add detailed docstring to latents_from_embeddings(). 2024-06-25 11:31:52 -07:00
Ryan Dick
60d1e686d8 Copy StableDiffusionGeneratorPipeline as a starting point for a new MultiDiffusionPipeline. 2024-06-25 11:31:52 -07:00
Ryan Dick
22704dd542 Simplify handling of inpainting models. Improve the in-code documentation around inpainting. 2024-06-25 11:31:52 -07:00
Ryan Dick
875673c9ba Minor tidying of latents_from_embeddings(...). 2024-06-25 11:31:52 -07:00
Ryan Dick
f604575862 Consolidate latents_from_embeddings(...) and generate_latents_from_embeddings(...) into a single function. 2024-06-25 11:31:52 -07:00
Ryan Dick
80a67572f1 Fix invocation name of tiled_multi_diffusion_denoise_latents. 2024-06-25 11:31:52 -07:00
Ryan Dick
60ac937698 Improve clarity of comments regarded when 'noise' and 'latents' are expected to be set. 2024-06-25 11:31:52 -07:00
Ryan Dick
1e41949a02 Fix static check errors on imports in diffusers_pipeline.py. 2024-06-25 11:31:52 -07:00
Ryan Dick
5f0e330ed2 Remove a condition for handling inpainting models that never resolves to True. The same logic is already applied earlier by AddsMaskLatents. 2024-06-25 11:31:52 -07:00
Ryan Dick
9dd779b414 Add clarifying comment to explain why noise might be None in latents_from_embedding(). 2024-06-25 11:31:52 -07:00
Ryan Dick
fa183025ac Remove unused are_like_tensors() function. 2024-06-25 11:31:52 -07:00
Ryan Dick
d3c85aa91a Remove unused StableDiffusionGeneratorPipeline.use_ip_adapter member. 2024-06-25 11:31:52 -07:00
Ryan Dick
82619602a5 Remove unused StableDiffusionGeneratorPipeline.control_model. 2024-06-25 11:31:52 -07:00
Ryan Dick
196f3b721d Stricter typing for the is_gradient_mask: bool. 2024-06-25 11:31:52 -07:00
Ryan Dick
244c28859d Fix typing of control_data to reflect that it can be None. 2024-06-25 11:31:52 -07:00
Ryan Dick
40ae174c41 Fix typing of timesteps and init_timestep. 2024-06-25 11:31:52 -07:00
Ryan Dick
afaebdf151 Fix typing to reflect that the callback arg to latents_from_embeddings is never None. 2024-06-25 11:31:52 -07:00
Ryan Dick
d661517d94 Move seed above optional params. 2024-06-25 11:31:52 -07:00
Ryan Dick
82a69a54ac Simplify handling of AddsMaskGuidance, and fix some related type errors. 2024-06-25 11:31:52 -07:00
Ryan Dick
ffc28176fe Remove unused num_inference_steps. 2024-06-25 11:31:52 -07:00
Ryan Dick
230e205541 WIP TiledMultiDiffusionDenoiseLatents. Updated parameter list and first half of the logic. 2024-06-25 11:31:52 -07:00
Ryan Dick
7e94350351 Tidy DenoiseLatentsInvocation.prep_control_data(...) and fix some type errors. 2024-06-25 11:31:52 -07:00
Ryan Dick
c4e8549c73 Make DenoiseLatentsInvocation.prep_control_data(...) a staticmethod so that it can be called externally. 2024-06-25 11:31:52 -07:00
Ryan Dick
350a210835 Copy TiledStableDiffusionRefineInvocation as a starting point for TiledMultiDiffusionDenoiseLatents.py 2024-06-25 11:31:52 -07:00
Ryan Dick
ed781dbb0c Change tiling strategy to make TiledStableDiffusionRefineInvocation work with more tile shapes and overlaps. 2024-06-25 11:31:52 -07:00
Ryan Dick
b41ea963e7 Expose a few more params from TiledStableDiffusionRefineInvocation. 2024-06-25 11:31:52 -07:00
Ryan Dick
da5d105049 Add support for LoRA models in TiledStableDiffusionRefineInvocation. 2024-06-25 11:31:52 -07:00
Ryan Dick
5301770525 Add naive ControlNet support to TiledStableDiffusionRefineInvocation 2024-06-25 11:31:52 -07:00
Ryan Dick
d08e405017 Fix ControlNetModel type hint import source. 2024-06-25 11:31:52 -07:00
Ryan Dick
534640ccde Rough prototype of TiledStableDiffusionRefineInvocation is working. 2024-06-25 11:31:52 -07:00
Ryan Dick
d5ab8cab5c WIP - TiledStableDiffusionRefine 2024-06-25 11:31:52 -07:00
Ryan Dick
4767301ad3 Minor improvements to LatentsToImageInvocation type hints. 2024-06-25 11:31:52 -07:00
Ryan Dick
21d7ca45e6 Expose vae_decode(...) as a staticmethod on LatentsToImageInvocation. 2024-06-25 11:31:52 -07:00
Ryan Dick
020e8eb413 Fix return type of prepare_noise_and_latents(...). 2024-06-25 11:31:52 -07:00
Ryan Dick
3d49541c09 Make init_scheduler() a staticmethod on DenoiseLatentsInvocation so that it can be called externally. 2024-06-25 11:31:52 -07:00
Ryan Dick
1ef266845a Only allow a single positive/negative prompt conditioning input for tiled refine. 2024-06-25 11:31:52 -07:00
Ryan Dick
a37589ca5f WIP on TiledStableDiffusionRefine 2024-06-25 11:31:52 -07:00
Ryan Dick
171a505f5e Convert several methods in DenoiseLatentsInvocation to staticmethods so that they can be called externally. 2024-06-25 11:31:52 -07:00
Ryan Dick
8004a0d5f5 Simplify the logic in prepare_noise_and_latents(...). 2024-06-25 11:31:52 -07:00
Ryan Dick
610a1fd611 Split out the prepare_noise_and_latents(...) logic in DenoiseLatentsInvocation so that it can be called from other invocations. 2024-06-25 11:31:52 -07:00
Ryan Dick
43108eec13 (minor) Add a TODO note to get_scheduler(...). 2024-06-25 11:31:52 -07:00
Lincoln Stein
b03073d888
[MM] Add support for probing and loading SDXL VAE checkpoint files (#6524) 
* add support for probing and loading SDXL VAE checkpoint files

* broaden regexp probe for SDXL VAEs

---------

Co-authored-by: Lincoln Stein <lstein@gmail.com>
 2024-06-20 02:57:27 +00:00
steffylo
a43d602f16 fix(queue): add clear_queue_on_startup config to clear problematic queues 2024-06-19 11:39:25 +10:00
Ryan Dick
79ceac2f82 (minor) Use SilenceWarnings as a decorator rather than a context manager to save an indentation level. 2024-06-18 15:06:22 -04:00
Ryan Dick
8e47e005a7 Tidy SilenceWarnings context manager: 
- Fix type errors
- Enable SilenceWarnings to be used as both a context manager and a decorator
- Remove duplicate implementation
- Check the initial verbosity on __enter__() rather than __init__()
 2024-06-18 15:06:22 -04:00
Ryan Dick
d13aafb514 Tidy denoise_latents.py imports to all use absolute import paths. 2024-06-18 15:06:22 -04:00
Brandon Rising
63a7e19dbf Run ruff 2024-06-18 10:38:29 -04:00
Brandon Rising
fbc5a8ec65 Ignore validation on improperly formatted hashes (pytest) 2024-06-18 10:38:29 -04:00
Brandon Rising
8ce6e4540e Run ruff 2024-06-18 10:38:29 -04:00
Brandon Rising
f14f377ede Update validator list 2024-06-18 10:38:29 -04:00
Brandon Rising
1925f83f5e Update validator list 2024-06-18 10:38:29 -04:00
Brandon Rising
3a5ad6d112 Update validator list 2024-06-18 10:38:29 -04:00
Brandon Rising
41a6bb45f3 Initial functionality 2024-06-18 10:38:29 -04:00
psychedelicious
cd70937b7f feat(api): improved model install confirmation page styling & messaging 2024-06-17 10:51:08 +10:00
psychedelicious
f002bca2fa feat(ui): handle new model_install_download_started event 
When a model install is initiated from outside the client, we now trigger the model manager tab's model install list to update.

- Handle new `model_install_download_started` event
- Handle `model_install_download_complete` event (this event is not new but was never handled)
- Update optimistic updates/cache invalidation logic to efficiently update the model install list
 2024-06-17 10:07:10 +10:00
psychedelicious
56771de856 feat(ui): add redux actions for model_install_download_started event 2024-06-17 09:52:46 +10:00
psychedelicious
c11478a94a chore(ui): typegen 2024-06-17 09:51:18 +10:00
psychedelicious
fb694b3e17 feat(app): add model_install_download_started event 
Previously, we used `model_install_download_progress` for both download starting and progressing. When handling this event, we don't know which actual thing it represents.

Add `model_install_download_started` event to explicitly represent a model download started event.
 2024-06-17 09:50:25 +10:00
psychedelicious
1bc98abc76 docs(ui): explain model install events 2024-06-17 09:33:46 +10:00
chainchompa
7f03b04b2f
Merge branch 'main' into chainchompa/model-install-deeplink 2024-06-14 17:16:25 -04:00
chainchompa
4029972530 formatting 2024-06-14 17:15:55 -04:00
chainchompa
328f160e88 refetch model installs when a new model install starts 2024-06-14 17:09:07 -04:00
chainchompa
aae318425d added route for installing huggingface model from model marketplace 2024-06-14 17:08:39 -04:00
Ryan Dick
785bb1d9e4 Fix all comparisons against the DEFAULT_PRECISION constant. DEFAULT_PRECISION is a torch.dtype. Previously, it was compared to a str in a number of places where it would always resolve to False. This is a bugfix that results in a change to the default behavior. In practice, this will not change the behavior for many users, because it only causes a change in behavior if a users has configured float32 as their default precision. 2024-06-14 11:26:10 -07:00
Lincoln Stein
a3cb5da130
Improve RAM<->VRAM memory copy performance in LoRA patching and elsewhere (#6490) 
* allow model patcher to optimize away the unpatching step when feasible

* remove lazy_offloading functionality

* allow model patcher to optimize away the unpatching step when feasible

* remove lazy_offloading functionality

* do not save original weights if there is a CPU copy of state dict

* Update invokeai/backend/model_manager/load/load_base.py

Co-authored-by: Ryan Dick <ryanjdick3@gmail.com>

* documentation fixes requested during penultimate review

* add non-blocking=True parameters to several torch.nn.Module.to() calls, for slight performance increases

* fix ruff errors

* prevent crash on non-cuda-enabled systems

---------

Co-authored-by: Lincoln Stein <lstein@gmail.com>
Co-authored-by: Kent Keirsey <31807370+hipsterusername@users.noreply.github.com>
Co-authored-by: Ryan Dick <ryanjdick3@gmail.com>
 2024-06-13 17:10:03 +00:00
blessedcoolant
568a4844f7 fix: other recursive imports 2024-06-10 04:12:20 -07:00
blessedcoolant
b1e56e2485 fix: SchedulerOutput not being imported correctly 2024-06-10 04:12:20 -07:00
Lincoln Stein
7d19af2caa
Merge branch 'main' into lstein/feat/simple-mm2-api 2024-06-08 18:55:06 -04:00
Ryan Dick
52c0c4a32f Rename latent.py -> denoise_latents.py. 2024-06-07 09:28:42 -04:00
Ryan Dick
8f1afc032a Move SchedulerInvocation to a new file. No functional changes. 2024-06-07 09:28:42 -04:00
Ryan Dick
854bca668a Move CreateDenoiseMaskInvocation to its own file. No functional changes. 2024-06-07 09:28:42 -04:00
Ryan Dick
fea9013cad Move CreateGradientMaskInvocation to its own file. No functional changes. 2024-06-07 09:28:42 -04:00
Ryan Dick
045caddee1 Move LatentsToImageInvocation to its own file. No functional changes. 2024-06-07 09:28:42 -04:00
Ryan Dick
58697141bf Move ImageToLatentsInvocation to its own file. No functional changes. 2024-06-07 09:28:42 -04:00
Ryan Dick
5e419dbb56 Move ScaleLatentsInvocation and ResizeLatentsInvocation to their own file. No functional changes. 2024-06-07 09:28:42 -04:00
Ryan Dick
595096bdcf Move BlendLatentsInvocation to its own file. No functional changes. 2024-06-07 09:28:42 -04:00
Ryan Dick
ed03d281e6 Move CropLatentsCoreInvocation to its own file. No functional changes. 2024-06-07 09:28:42 -04:00
Ryan Dick
0b37496c57 Move IdealSizeInvocation to its own file. No functional changes. 2024-06-07 09:28:42 -04:00
psychedelicious
fde58ce0a3 Merge remote-tracking branch 'origin/main' into lstein/feat/simple-mm2-api 2024-06-07 14:23:41 +10:00
Lincoln Stein
dc134935c8 replace load_and_cache_model() with load_remote_model() and load_local_odel() 2024-06-07 14:12:16 +10:00
Lincoln Stein
f81b8bc9f6 add support for generic loading of diffusers directories 2024-06-07 13:54:30 +10:00
psychedelicious
6d067e56f2 fix(ui): on page load, if CA processed image no longer exists, re-process it 2024-06-07 10:32:28 +10:00
Lincoln Stein
2871676f79
LoRA patching optimization (#6439) 
* allow model patcher to optimize away the unpatching step when feasible

* remove lazy_offloading functionality

* allow model patcher to optimize away the unpatching step when feasible

* remove lazy_offloading functionality

* do not save original weights if there is a CPU copy of state dict

* Update invokeai/backend/model_manager/load/load_base.py

Co-authored-by: Ryan Dick <ryanjdick3@gmail.com>

* documentation fixes added during penultimate review

---------

Co-authored-by: Lincoln Stein <lstein@gmail.com>
Co-authored-by: Kent Keirsey <31807370+hipsterusername@users.noreply.github.com>
Co-authored-by: Ryan Dick <ryanjdick3@gmail.com>
 2024-06-06 13:53:35 +00:00
psychedelicious
1c5c3cdbd6 tidy(ui): organize control layers konva logic 
- More comments, docstrings
- Move things into saner, less-coupled locations
 2024-06-06 07:45:13 +10:00
psychedelicious
3db69af220 refactor(ui): generalize stage event handlers 
Create intermediary nanostores for values required by the event handlers. This allows the event handlers to be purely imperative, with no reactivity: instead of recreating/setting the handlers when a dependent piece of state changes, we use nanostores' imperative API to access dependent state.

For example, some handlers depend on brush size. If we used the standard declarative `useSelector` API, we'd need to recreate the event handler callback each time the brush size changed. This can be costly.

An intermediate `$brushSize` nanostore is set in a `useLayoutEffect()`, which responds to changes to the redux store. Then, in the event handler, we use the imperative API to access the brush size: `$brushSize.get()`.

This change allows the event handler logic to be shared with the pending canvas v2, and also more easily tested. It's a noticeable perf improvement, too, especially when changing brush size.
 2024-06-06 07:45:13 +10:00
psychedelicious
1823e446ac fix(ui): conditionally render CL preview 
This fixes an issue where it sometimes gets out of sync, and fixes some konva errors.
 2024-06-06 07:45:13 +10:00
psychedelicious
311e44ad19 tidy(ui): clean up control layers renderers, docstrings 2024-06-06 07:45:13 +10:00
jstnlowe
848ca79da8 Changed translated labels to static suffixes, cleanup. 2024-06-05 14:45:43 +10:00
jstnlowe
9cba0dfac9 Providing fileName string directly to DataViewer as suggested 2024-06-05 14:45:43 +10:00
jstnlowe
37b1f21bcf ... and the workflow 2024-06-05 14:45:43 +10:00
jstnlowe
b2e005f6b5 Just realized we might want the same change made for the Graph JSON 2024-06-05 14:45:43 +10:00
jstnlowe
52aac954c0 Prefixed JSON filenames with the image UUID #6469 2024-06-05 14:45:43 +10:00
psychedelicious
ff01ceae99 Update invokeai_version.py 2024-06-05 05:53:19 +10:00
hugoalh
669d92d8db translationBot(ui): update translation (Chinese (Traditional)) 
Currently translated at 14.1% (179 of 1261 strings)

Co-authored-by: hugoalh <hugoalh@users.noreply.hosted.weblate.org>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/zh_Hant/
Translation: InvokeAI/Web UI
 2024-06-05 00:08:03 +10:00
Ettore Atalan
2903060154 translationBot(ui): update translation (German) 
Currently translated at 67.0% (834 of 1243 strings)

Co-authored-by: Ettore Atalan <atalanttore@googlemail.com>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/de/
Translation: InvokeAI/Web UI
 2024-06-05 00:08:03 +10:00
gallegonovato
4af8699a00 translationBot(ui): update translation (Spanish) 
Currently translated at 34.3% (427 of 1243 strings)

Co-authored-by: gallegonovato <fran-carro@hotmail.es>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/es/
Translation: InvokeAI/Web UI
 2024-06-05 00:08:03 +10:00
Bruno Castillejo
71fedd1a07 translationBot(ui): update translation (Spanish) 
Currently translated at 34.3% (427 of 1243 strings)

Co-authored-by: Bruno Castillejo <soybrunocastillejo@gmail.com>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/es/
Translation: InvokeAI/Web UI
 2024-06-05 00:08:03 +10:00
Riccardo Giovanetti
6bb1189c88 translationBot(ui): update translation (Italian) 
Currently translated at 98.5% (1243 of 1261 strings)

translationBot(ui): update translation (Italian)

Currently translated at 98.5% (1243 of 1261 strings)

translationBot(ui): update translation (Italian)

Currently translated at 98.5% (1225 of 1243 strings)

translationBot(ui): update translation (Italian)

Currently translated at 98.5% (1225 of 1243 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
 2024-06-05 00:08:03 +10:00
Васянатор
c7546bc82e translationBot(ui): update translation (Russian) 
Currently translated at 100.0% (1261 of 1261 strings)

translationBot(ui): update translation (Russian)

Currently translated at 100.0% (1243 of 1243 strings)

Co-authored-by: Васянатор <ilabulanov339@gmail.com>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/ru/
Translation: InvokeAI/Web UI
 2024-06-05 00:08:03 +10:00
psychedelicious
14372e3818 fix(nodes): blend latents with weight=0 with DPMSolverSDEScheduler 
- Pass the seed from `latents_a` to the output latents. Fixed an issue where using `BlendLatentsInvocation` could result in different outputs during denoising even when the alpha or slerp weight was 0.

## Explanation

`LatentsField` has an optional `seed` field. During denoising, if this `seed` field is not present, we **fall back to 0 for the seed**. The seed is used during denoising in a few ways:

1. Initializing the scheduler.

The seed is used in two places in `invokeai/app/invocations/latent.py`.

The `get_scheduler()` utility function has special handling for `DPMSolverSDEScheduler`, which appears to need a seed for deterministic outputs.

`DenoiseLatentsInvocation.init_scheduler()` has special handling for schedulers that accept a generator - the generator needs to be seeded in a particular way. At the time of this commit, these are the Invoke-supported schedulers that need this seed:
  - DDIMScheduler
  - DDPMScheduler
  - DPMSolverMultistepScheduler
  - EulerAncestralDiscreteScheduler
  - EulerDiscreteScheduler
  - KDPM2AncestralDiscreteScheduler
  - LCMScheduler
  - TCDScheduler

2. Adding noise during inpainting.

If a mask is used for denoising, and we are not using an inpainting model, we add noise to the unmasked area. If, for some reason, we have a mask but no noise, the seed is used to add noise.

I wonder if we should instead assert that if a mask is provided, we also have noise.

This is done in `invokeai/backend/stable_diffusion/diffusers_pipeline.py` in `StableDiffusionGeneratorPipeline.latents_from_embeddings()`.

When we create noise to be used in denoising, we are expected to set `LatentsField.seed` to the seed used to create the noise. This introduces some awkwardness when we manipulate any "latents" that will be used for denoising. We have to pass the seed along for every operation.

If the wrong seed or no seed is passed along, we can get unexpected outputs during denoising. One notable case relates to blending latents (slerping tensors).

If we slerp two noise tensors (`LatentsField`s) _without_ passing along the seed from the source latents, when we denoise with a seed-dependent scheduler*, the schedulers use the fallback seed of 0 and we get the wrong output. This is most obvious when slerping with a weight of 0, in which case we expect the exact same output after denoising.

*It looks like only the DPMSolver* schedulers are affected, but I haven't tested all of them.

Passing the seed along in the output fixes this issue.
 2024-06-05 00:02:52 +10:00
psychedelicious
64523c4b1b fix(ui): handle concat when recalling prompts 
This required some minor reworking of of the logic to recall multiple items. I split this into a utility function that includes some special handling for concat.

Closes #6478
 2024-06-04 06:01:01 +10:00
psychedelicious
89a764a359 fix(ui): improve model metadata parsing fallback 
When the model in metadata's key no longer exists, fall back to fetching by name, base and type. This was the intention all along but the logic was never put in place.
 2024-06-04 06:01:01 +10:00
Lincoln Stein
756108f6bd Update invokeai/app/invocations/latent.py 
Co-authored-by: Ryan Dick <ryanjdick3@gmail.com>
 2024-06-03 11:41:47 -07:00
Lincoln Stein
68d628dc14 use zip to iterate over image prompts and adapters 2024-06-03 11:41:47 -07:00
Lincoln Stein
93c9852142 fix ruff 2024-06-03 11:41:47 -07:00
Lincoln Stein
493f81788c added a few comments to document design choices 2024-06-03 11:41:47 -07:00
Lincoln Stein
f13427e3f4 refactor redundant code and fix typechecking errors 2024-06-03 11:41:47 -07:00
Lincoln Stein
e28737fc8b add check for congruence between # of ip_adapters and image_prompts 2024-06-03 11:41:47 -07:00
Lincoln Stein
7391c126d3 handle case of no IP adapters requested 2024-06-03 11:41:47 -07:00
Lincoln Stein
1c59fce6ad reduce peak VRAM memory usage of IP adapter 2024-06-03 11:41:47 -07:00
psychedelicious
a9962fd104 chore: ruff 2024-06-03 11:53:20 +10:00
psychedelicious
e7513f6088 docs(mm): add comment in move_model_to_device 2024-06-03 10:56:04 +10:00
psychedelicious
c7f22b6a3b tidy(mm): remove extraneous docstring 
It's inherited from the ABC.
 2024-06-03 10:46:28 +10:00
psychedelicious
99413256ce tidy(mm): pass enum member instead of string 2024-06-03 10:43:09 +10:00
psychedelicious
aa9695e377 tidy(download): _download_job -> _multifile_job 2024-06-03 10:15:53 +10:00
psychedelicious
c58ac1e80d tidy(mm): minor formatting 2024-06-03 10:11:08 +10:00
psychedelicious
6cc6a45274 feat(download): add type for callback_name 
Just a bit of typo protection in lieu of full type safety for these methods, which is difficult due to the typing of `DownloadEventHandler`.
 2024-06-03 10:05:52 +10:00
psychedelicious
521f907f58 tidy(nodes): infill 
- Set `self._context=context` instead of passing it as an arg
 2024-06-03 09:43:25 +10:00
psychedelicious
ccdecf21a3 tidy(nodes): cnet processors 
- Set `self._context=context` instead of changing the type signature of `run_processor`
- Tidy a few typing things
 2024-06-03 09:41:17 +10:00
psychedelicious
b124440023 tidy(mm): move load_model_from_url from mm to invocation context 2024-06-03 08:51:21 +10:00
psychedelicious
e3a70e598e docs(app): simplify docstring in invocation_context 2024-06-03 08:40:29 +10:00
psychedelicious
132bbf330a tidy(app): remove unnecessary changes in invocation_context 
- Any mypy issues are a misconfiguration of mypy
- Use simple conditionals instead of ternaries
- Consistent & standards-compliant docstring formatting
- Use `dict` instead of `typing.Dict`
 2024-06-03 08:35:23 +10:00
Lincoln Stein
2276f327e5
Merge branch 'main' into lstein/feat/simple-mm2-api 2024-06-02 09:45:31 -04:00
psychedelicious
6b24424727 feat(ui): add help icon to compare toolbar 2024-06-02 15:30:00 +10:00
psychedelicious
7153d846a9 feat(ui): add hotkey to cycle compare modes 2024-06-02 15:30:00 +10:00
psychedelicious
9a0b77ad38 feat(ui): add hotkey to swap comparison images 2024-06-02 15:30:00 +10:00
psychedelicious
220d45967e fix(ui): typo 2024-06-02 15:30:00 +10:00
psychedelicious
038a482ef0 feat(ui): rework visibility conditions for image viewer 2024-06-02 15:30:00 +10:00
psychedelicious
c325ad3432 feat(ui): add hotkey hint to exit compare button 2024-06-02 15:30:00 +10:00
psychedelicious
449bc4dbe5 feat(ui): abstract out and share logic between comparisons 2024-06-02 15:30:00 +10:00
psychedelicious
34d68a3663 feat(ui): hover comparison mode 2024-06-02 15:30:00 +10:00
psychedelicious
8bb9571485 feat(ui): tweak slider divider styling 2024-06-02 15:30:00 +10:00
psychedelicious
08bcc71e99 fix(ui): workflows fit on load 2024-06-02 15:30:00 +10:00
psychedelicious
ff2b2fad83 feat(ui): revise drop zones 
The main viewer area has two drop zones:
- Select for Viewer
- Select for Compare

These do what you'd imagine they would do.
 2024-06-02 15:30:00 +10:00
psychedelicious
0f0a6852f1 fix(ui): make compare image scale with first image when using contain fit 2024-06-02 15:30:00 +10:00
psychedelicious
745140fa6b feat(ui): "first image"/"second image" -> "viewer image"/"compare image" 2024-06-02 15:30:00 +10:00
psychedelicious
405fc46888 feat(ui): z/esc first exit compare before closing viewer 2024-06-02 15:30:00 +10:00
psychedelicious
ca728ca29f fix(ui): ignore context menu in slider view 
It doesn't make sense to allow context menu here, because the context menu will technically be on a div and not an image - there won't be any image options there.
 2024-06-02 15:30:00 +10:00
psychedelicious
d0fca53e67 fix(ui): only clear comparison image on alt click of gallery image 
This logic can't e in the reducer else it applies to dnd events which isn't right
 2024-06-02 15:30:00 +10:00
psychedelicious
ad9740d72d feat(ui): alt-click comparison image exits compare 2024-06-02 15:30:00 +10:00
psychedelicious
1c9c982b63 feat(ui): use appropriate cursor on slider 2024-06-02 15:30:00 +10:00
psychedelicious
3cfd2755c2 fix(ui): when changing viewer state, always clear compare image 2024-06-02 15:30:00 +10:00
psychedelicious
8ea4067f83 feat(ui): rework compare toolbar 2024-06-02 15:30:00 +10:00
psychedelicious
940de6a5c5 fix(ui): allow drop of currently-selected image for compare 2024-06-02 15:30:00 +10:00
psychedelicious
dd74e89127 fix(ui): close context menu on click select for compare 2024-06-02 15:30:00 +10:00
psychedelicious
69da67e920 fix(ui): dnd on board 
Copy-paste error broke this
 2024-06-02 15:30:00 +10:00
psychedelicious
76b1f241d7 fix(ui): useGalleryNavigation callback typing issue 2024-06-02 15:30:00 +10:00
psychedelicious
0e5336d8fa feat(ui): rework comparison activation, add hotkeys 2024-06-02 15:30:00 +10:00
psychedelicious
3501636018 feat(ui): add fill mode for slider comparison 2024-06-02 15:30:00 +10:00
psychedelicious
e4ce188500 feat(ui): image selection gallery state & tweaks 2024-06-02 15:30:00 +10:00
psychedelicious
e976571fba build(ui): remove unused dep 2024-06-02 15:30:00 +10:00
psychedelicious
0da36c1238 feat(ui): use IAIDndImage for compare mode 2024-06-02 15:30:00 +10:00
psychedelicious
4ef8cbd9d0 fix(ui): use isValidDrop in imageDropped listener 
It was possible for a drop event to be invalid but still processed. Fixed by slightly changing the signature of isValidDrop.
 2024-06-02 15:30:00 +10:00
psychedelicious
8f8ddd620b feat(ui): add comparison modes, side-by-side view 2024-06-02 15:30:00 +10:00
psychedelicious
1af53aed60 feat(ui): fix image comparison slider resizing/aspect ratio jank 2024-06-02 15:30:00 +10:00
psychedelicious
7a4bbd092e feat(ui): revised image comparison slider 
Should work for any components and image now.
 2024-06-02 15:30:00 +10:00
psychedelicious
72bbcb2d94 feat(ui): slider working for all aspect ratios 2024-06-02 15:30:00 +10:00
psychedelicious
c2eef93476 feat(ui): wip slider implementations 2024-06-02 15:30:00 +10:00
psychedelicious
a983f27aad fix(ui): update types 2024-05-30 12:03:38 +10:00
psychedelicious
7cb32d3d83 chore(ui): typegen 2024-05-30 12:03:38 +10:00
psychedelicious
ac56ab79a7 fix(app): add dynamic validator to AnyInvocation & AnyInvocationOutput 
This fixes the tests and slightly changes output types.
 2024-05-30 12:03:38 +10:00
psychedelicious
50d3030471 feat(app): dynamic type adapters for invocations & outputs 
Keep track of whether or not the typeadapter needs to be updated. Allows for dynamic invocation and output unions.
 2024-05-30 12:03:38 +10:00
psychedelicious
5beec8211a feat(api): sort openapi schemas 
Reduces the constant changes to the frontend client types due to inconsistent ordering of pydantic models.
 2024-05-30 12:03:38 +10:00
psychedelicious
5a4d10467b feat(ui): use updated types 2024-05-30 12:03:38 +10:00