Commit Graph

1098 Commits

Author SHA1 Message Date
user1
2ba40c5e52 Refactored most of controlnet code into its own method to declutter TextToLatents.invoke(), and make upcoming integration with LatentsToLatents easier. 2023-05-26 21:44:00 -04:00
user1
3ab147204c Fix to work with current stable release of controlnet_aux (v0.0.3). Turned of pre-processor params that were added post v0.0.3. Also change defaults for shuffle. 2023-05-26 21:44:00 -04:00
user1
e4c89cba9c Switched CotrolNet node modelname input from free text to default list of popular ControlNet model names. 2023-05-26 21:44:00 -04:00
user1
322ea84c4e Commented out ZoeDetector. Will re-instate once there's a controlnet-aux release that supports it. 2023-05-26 21:44:00 -04:00
user1
f2b41c60ff Cleaning up prior to submitting ControlNet PR. Mostly turning off diagnostic printing. Also fixed error when there is no controlnet input. 2023-05-26 21:44:00 -04:00
user1
754acec92f Added support for specifying which step iteration to start using
each ControlNet, and which step to end using each controlnet (specified as fraction of total steps)
2023-05-26 21:44:00 -04:00
user1
11fc7e40a5 Refactored ControNet support to consolidate multiple parameters into data struct. Also redid how multiple controlnets are handled. 2023-05-26 21:44:00 -04:00
user1
d15bb88eb2 Removed last bits of dtype and and device hardwiring from controlnet section 2023-05-26 21:44:00 -04:00
user1
70ba36eefc Cleaning up mistakes after rebase. 2023-05-26 21:44:00 -04:00
user1
7e70391c2b Cleaning up TextToLatent arg testing 2023-05-26 21:44:00 -04:00
user1
e2a94be336 Added resizing of controlnet image based on noise latent. Fixes a tensor mismatch issue. 2023-05-26 21:44:00 -04:00
user1
63a86eefb4 Refactored controlnet nodes: split out controlnet stuff into separate node, stripped controlnet stuff form image processing/analysis nodes. 2023-05-26 21:44:00 -04:00
user1
b0727b9d47 Prep for splitting pre-processor and controlnet nodes 2023-05-26 21:44:00 -04:00
user1
d96e727dd5 Added more preprocessor nodes for:
MidasDepth
      ZoeDepth
      MLSD
      NormalBae
      Pidi
      LineartAnime
      ContentShuffle
Removed pil_output options, ControlNet preprocessors should always output as PIL. Removed diagnostics and other general cleanup.
2023-05-26 21:44:00 -04:00
user1
fe480886dc changes to base class for controlnet nodes 2023-05-26 21:44:00 -04:00
user1
8031d1827b Refactored controlnet node to output ControlField that bundles control info. 2023-05-26 21:44:00 -04:00
user1
b5acdb322d Switching to ControlField for output from controlnet nodes. 2023-05-26 21:44:00 -04:00
user1
a4d1fe8819 Initial port of controlnet node support from generator-based TextToImageInvocation node to latent-based TextToLatentsInvocation node 2023-05-26 21:44:00 -04:00
user1
10b7a58887 Added first controlnet preprocessor node for canny edge detection. 2023-05-26 21:44:00 -04:00
user1
aaa093bef1 Fixed use of ControlNet control_weight parameter 2023-05-26 21:44:00 -04:00
user1
bb96543d66 Added support for using multiple control nets. Unfortunately this breaks direct usage of Control node output port ==> TextToLatent control input port -- passing through a Collect node is now required. Working on fixing this... 2023-05-26 21:44:00 -04:00
user1
a2a2cfa765 Added resizing of controlnet image based on noise latent. Fixes a tensor mismatch issue. 2023-05-26 21:44:00 -04:00
user1
18e6a2b410 Refactored controlnet nodes: split out controlnet stuff into separate node, stripped controlnet stuff form image processing/analysis nodes. 2023-05-26 21:44:00 -04:00
user1
db27263bc2 Prep for splitting pre-processor and controlnet nodes 2023-05-26 21:44:00 -04:00
user1
0e027ec3ef Added more preprocessor nodes for:
MidasDepth
      ZoeDepth
      MLSD
      NormalBae
      Pidi
      LineartAnime
      ContentShuffle
Removed pil_output options, ControlNet preprocessors should always output as PIL. Removed diagnostics and other general cleanup.
2023-05-26 21:44:00 -04:00
user1
5acbbeecaa Added HED, LineArt, and OpenPose ControlNet nodes 2023-05-26 21:44:00 -04:00
user1
6ef2168b67 changes to base class for controlnet nodes 2023-05-26 21:44:00 -04:00
user1
6d958a214c Refactored ControlNet nodes so they subclass from PreprocessedControlInvocation, and only need to override run_processor(image) (instead of reimplementing invoke()) 2023-05-26 21:44:00 -04:00
user1
4ae4bf4ff9 Resolving conflicts in rebase to origin/main 2023-05-26 21:44:00 -04:00
user1
fdef53b2de Switching to ControlField for output from controlnet nodes. 2023-05-26 21:44:00 -04:00
user1
11bd038b9d Added first controlnet preprocessor node for canny edge detection. 2023-05-26 21:44:00 -04:00
user1
c4277b0662 Moved to controlnet_aux v0.0.4, reinstated Zoe controlnet preprocessor. Also in pyproject.toml had to specify downgrade of timm to 0.6.13 _after_ controlnet-aux installs timm >= 0.9.2, because timm >0.6.13 breaks Zoe preprocessor. 2023-05-26 21:44:00 -04:00
psychedelicious
020f3ccf07 fix(nodes): controlnet input accepts list or single controlnet 2023-05-26 21:44:00 -04:00
psychedelicious
7467fa5e57 fix(ui): fix node ui type hints 2023-05-26 21:44:00 -04:00
user1
dcebd71381 Extended node-based ControlNet support to LatentsToLatentsInvocation. 2023-05-26 21:44:00 -04:00
user1
d855a65e73 Cleaning up after ControlNet refactor in TextToLatentsInvocation 2023-05-26 21:44:00 -04:00
user1
a9007c7e0f Refactored most of controlnet code into its own method to declutter TextToLatents.invoke(), and make upcoming integration with LatentsToLatents easier. 2023-05-26 21:44:00 -04:00
user1
af60304f97 Fix to work with current stable release of controlnet_aux (v0.0.3). Turned of pre-processor params that were added post v0.0.3. Also change defaults for shuffle. 2023-05-26 21:44:00 -04:00
user1
6de241eead Switched CotrolNet node modelname input from free text to default list of popular ControlNet model names. 2023-05-26 21:44:00 -04:00
user1
51032dc0b2 Commented out ZoeDetector. Will re-instate once there's a controlnet-aux release that supports it. 2023-05-26 21:44:00 -04:00
user1
297931f5d9 Cleaning up prior to submitting ControlNet PR. Mostly turning off diagnostic printing. Also fixed error when there is no controlnet input. 2023-05-26 21:44:00 -04:00
user1
f613c073c1 Added support for specifying which step iteration to start using
each ControlNet, and which step to end using each controlnet (specified as fraction of total steps)
2023-05-26 21:44:00 -04:00
user1
63d248622c Refactored ControNet support to consolidate multiple parameters into data struct. Also redid how multiple controlnets are handled. 2023-05-26 21:44:00 -04:00
user1
48485fe92f Removed last bits of dtype and and device hardwiring from controlnet section 2023-05-26 21:44:00 -04:00
user1
07726af703 Cleaning up mistakes after rebase. 2023-05-26 21:44:00 -04:00
user1
ad1004b485 Cleaning up TextToLatent arg testing 2023-05-26 21:44:00 -04:00
user1
0096fb2790 Added resizing of controlnet image based on noise latent. Fixes a tensor mismatch issue. 2023-05-26 21:44:00 -04:00
user1
9c8c2e49d6 Refactored controlnet nodes: split out controlnet stuff into separate node, stripped controlnet stuff form image processing/analysis nodes. 2023-05-26 21:44:00 -04:00
user1
2005a96847 Prep for splitting pre-processor and controlnet nodes 2023-05-26 21:44:00 -04:00
user1
00a8d60c1b Added more preprocessor nodes for:
MidasDepth
      ZoeDepth
      MLSD
      NormalBae
      Pidi
      LineartAnime
      ContentShuffle
Removed pil_output options, ControlNet preprocessors should always output as PIL. Removed diagnostics and other general cleanup.
2023-05-26 21:44:00 -04:00
user1
3aa182390a changes to base class for controlnet nodes 2023-05-26 21:44:00 -04:00
user1
e44f1d6d4e Refactored controlnet node to output ControlField that bundles control info. 2023-05-26 21:44:00 -04:00
user1
dfdf8e2ead Switching to ControlField for output from controlnet nodes. 2023-05-26 21:44:00 -04:00
user1
3a645c4e80 Initial port of controlnet node support from generator-based TextToImageInvocation node to latent-based TextToLatentsInvocation node 2023-05-26 21:44:00 -04:00
user1
113129daf9 Added first controlnet preprocessor node for canny edge detection. 2023-05-26 21:44:00 -04:00
user1
714ad6dbb8 Fixed use of ControlNet control_weight parameter 2023-05-26 21:44:00 -04:00
user1
c0863fa20f Added support for using multiple control nets. Unfortunately this breaks direct usage of Control node output port ==> TextToLatent control input port -- passing through a Collect node is now required. Working on fixing this... 2023-05-26 21:44:00 -04:00
user1
5d5cdc7716 Added resizing of controlnet image based on noise latent. Fixes a tensor mismatch issue. 2023-05-26 21:44:00 -04:00
user1
93cd818f6a Refactored controlnet nodes: split out controlnet stuff into separate node, stripped controlnet stuff form image processing/analysis nodes. 2023-05-26 21:44:00 -04:00
user1
598a628790 Prep for splitting pre-processor and controlnet nodes 2023-05-26 21:44:00 -04:00
user1
f3666eda63 Added more preprocessor nodes for:
MidasDepth
      ZoeDepth
      MLSD
      NormalBae
      Pidi
      LineartAnime
      ContentShuffle
Removed pil_output options, ControlNet preprocessors should always output as PIL. Removed diagnostics and other general cleanup.
2023-05-26 21:44:00 -04:00
user1
754017b59e Added an additional "raw_processed_image" output port to controlnets, mainly so could route ImageField to a ShowImage node 2023-05-26 21:44:00 -04:00
user1
21251ce12c Added HED, LineArt, and OpenPose ControlNet nodes 2023-05-26 21:44:00 -04:00
user1
dc12fa6cd6 changes to base class for controlnet nodes 2023-05-26 21:44:00 -04:00
user1
f2f4c37f19 Refactored ControlNet nodes so they subclass from PreprocessedControlInvocation, and only need to override run_processor(image) (instead of reimplementing invoke()) 2023-05-26 21:44:00 -04:00
user1
0864fca641 Resolving conflicts in rebase to origin/main 2023-05-26 21:44:00 -04:00
user1
5e4c0217c7 Switching to ControlField for output from controlnet nodes. 2023-05-26 21:44:00 -04:00
user1
78cd106c23 Initial port of controlnet node support from generator-based TextToImageInvocation node to latent-based TextToLatentsInvocation node 2023-05-26 21:44:00 -04:00
user1
6ed0efa938 Added first controlnet preprocessor node for canny edge detection. 2023-05-26 21:44:00 -04:00
user1
ca0669c337 Resolving rebase conflict 2023-05-26 21:44:00 -04:00
Lincoln Stein
1e2db3a17f hook tiled_decode up to configuration 2023-05-25 23:28:15 -04:00
Lincoln Stein
5f8f51436a merge with main; fix conflicts 2023-05-25 22:40:45 -04:00
psychedelicious
33e13820fc feat(nodes): remove meta node field; use individual is_intermediate field instead
as suggested by @Kyle0654
2023-05-25 22:17:14 -04:00
psychedelicious
291e9cf14b fix(nodes): add is_intermediate to all image-outputting nodes 2023-05-25 22:17:14 -04:00
psychedelicious
d2c8a53c55 feat(nodes): change intermediates handling
- `ImageType` is now restricted to `results` and `uploads`.
- Add a reserved `meta` field to nodes to hold the `is_intermediate` boolean. We can extend it in the future to support other node `meta`.
- Add a `is_intermediate` column to the `images` table to hold this. (When `latents`, `conditioning` etc are added to the DB, they will also have this column.)
- All nodes default to `*not* intermediate`. Nodes must explicitly be marked `intermediate` for their outputs to be `intermediate`.
- When building a graph, you can set `node.meta.is_intermediate=True` and it will be handled as an intermediate.
- Add a new `update()` method to the `ImageService`, and a route to call it. Updates have a strict model, currently only `session_id` and `image_category` may be updated.
- Add a new `update()` method to the `ImageRecordStorageService` to update the image record using the model.
2023-05-25 22:17:14 -04:00
Kent Keirsey
05fb0ac2b2 Update latent.py 2023-05-26 10:27:33 +10:00
Kent Keirsey
d4acd49ee3 Update generate.py 2023-05-26 10:27:33 +10:00
psychedelicious
1fb307abf4 feat(nodes): restore canvas functionality (non-latents) 2023-05-24 11:30:47 -04:00
psychedelicious
ad39680feb feat(nodes): wip inpainting nodes prep 2023-05-24 11:30:47 -04:00
psychedelicious
1e0ae8404c feat(nodes): comment out seamless
this will be a model config feature when model manager is ready
2023-05-24 11:30:47 -04:00
psychedelicious
460d555a3d feat(nodes): add image mul, channel, convert nodes
also make img node names consistent
2023-05-24 11:30:47 -04:00
psychedelicious
d2c223de8f feat(nodes): move fully* to new images service
* except i haven't rebuilt inpaint in latents
2023-05-24 11:30:47 -04:00
psychedelicious
dd16f788ed fix(nodes): fix RangeOfSizeInvocation off-by-one error 2023-05-24 11:30:47 -04:00
psychedelicious
b25c1af018 feat(nodes): add RangeOfSizeInvocation
The `RangeInvocation` is a simple wrapper around `range()`, but you must provide `stop > start`.

`RangeOfSizeInvocation` replaces the `stop` parameter with `size`, so that you can just provide the `start` and `step` and get a range of `size` length.
2023-05-24 11:30:47 -04:00
psychedelicious
8f393b64b8 feat(nodes): add seed validator
If `seed>SEED_MAX`, we can still continue if we parse the seed as `seed % SEED_MAX`.
2023-05-24 11:30:47 -04:00
psychedelicious
55b3193629 fix(nodes): add RangeInvocation validator
`stop` must be greater than `start`.
2023-05-24 11:30:47 -04:00
psychedelicious
035425ef24 feat(nodes): address feedback
- Address database feedback:
  - Remove all the extraneous tables. Only an `images` table now:
  - `image_type` and `image_category` are unrestricted strings. When creating images, the provided values are checked to ensure they are a valid type and category.
  - Add `updated_at` and `deleted_at` columns. `deleted_at` is currently unused.
  - Use SQLite's built-in timestamp features to populate these. Add a trigger to update `updated_at` when the row is updated. Currently no way to update a row.
  - Rename the `id` column in `images` to `image_name`
- Rename `ImageCategory.IMAGE` to `ImageCategory.GENERAL`
- Move all exceptions outside their base classes to make them more portable.
- Add `width` and `height` columns to the database. These store the actual dimensions of the image file, whereas the metadata's `width` and `height` refer to the respective generation parameters and are nullable.
- Make `deserialize_image_record` take a `dict` instead of `sqlite3.Row`
- Improve comments throughout
- Tidy up unused code/files and some minor organisation
2023-05-24 11:30:47 -04:00
psychedelicious
5de3c41d19 feat(nodes): add metadata handling 2023-05-24 11:30:47 -04:00
psychedelicious
adde8450bc fix(nodes): remove bad import 2023-05-24 11:30:47 -04:00
psychedelicious
5bf9891553 feat(nodes): it works 2023-05-24 11:30:47 -04:00
psychedelicious
d4aa79acd7 fix(nodes): use save instead of set
`set` is a python builtin
2023-05-24 11:30:47 -04:00
psychedelicious
9c89d3452c feat(nodes): add high-level images service
feat(nodes): add ResultsServiceABC & SqliteResultsService

**Doesn't actually work bc of circular imports. Can't even test it.**

- add a base class for ResultsService and SQLite implementation
- use `graph_execution_manager` `on_changed` callback to keep `results` table in sync

fix(nodes): fix results service bugs

chore(ui): regen api

fix(ui): fix type guards

feat(nodes): add `result_type` to results table, fix types

fix(nodes): do not shadow `list` builtin

feat(nodes): add results router

It doesn't work due to circular imports still

fix(nodes): Result class should use outputs classes, not fields

feat(ui): crude results router

fix(ui): send to canvas in currentimagebuttons not working

feat(nodes): add core metadata builder

feat(nodes): add design doc

feat(nodes): wip latents db stuff

feat(nodes): images_db_service and resources router

feat(nodes): wip images db & router

feat(nodes): update image related names

feat(nodes): update urlservice

feat(nodes): add high-level images service
2023-05-24 11:30:47 -04:00
Lincoln Stein
bdf33f13b3 fix bad merge in compel 2023-05-18 18:08:45 -04:00
Lincoln Stein
d96175d127 resolve some undefined symbols in model_cache 2023-05-18 14:31:47 -04:00
Lincoln Stein
8adff96e29
Merge branch 'main' into lstein/global-configuration 2023-05-17 14:37:09 -04:00
psychedelicious
1d9c115225 feat(nodes): add low and high to RandomIntInvocation 2023-05-16 13:50:52 +10:00
Lincoln Stein
426f4eaf7e adjusted regression tests to work with new SDModelTypes 2023-05-13 22:29:33 -04:00
Lincoln Stein
baf5451fa0
Merge branch 'main' into lstein/new-model-manager 2023-05-13 22:01:34 -04:00
Lincoln Stein
1103ab2844 merge with main 2023-05-13 21:35:19 -04:00
Sergey Borisov
039fa73269 Change SDModelType enum to string, fixes(model unload negative locks count, scheduler load error, saftensors convert, wrong logic in del_model, wrong parse metadata in web) 2023-05-14 03:06:26 +03:00
Lincoln Stein
72967bf118 convert add_model(), del_model(), list_models() etc to use bifurcated names 2023-05-13 14:44:44 -04:00
Sergey Borisov
bc96727cbe Rewrite latent nodes to new model manager 2023-05-13 16:08:03 +03:00
Sergey Borisov
3b2a054f7a Add model loader node; unet, clip, vae fields; change compel node to clip field 2023-05-13 04:37:20 +03:00
Sergey Borisov
4492044d29 Redo compel node to separate model loading 2023-05-12 23:09:33 +03:00
Eugene Brodsky
af060188bd
Merge branch 'main' into lstein/bugfix/compel 2023-05-12 08:22:18 -04:00
Lincoln Stein
2ef79b8bf3 fix bug in persistent model scheme 2023-05-12 00:14:56 -04:00
blessedcoolant
9c1e65f3a3
Merge branch 'main' into feat/nodes/add-randomintinvocation 2023-05-12 15:56:41 +12:00
psychedelicious
ebec200ba6
Remove unused import 2023-05-12 13:56:02 +10:00
Lincoln Stein
11ecf438f5 latents.py converted to use model manager service; events emitted 2023-05-11 23:33:24 -04:00
blessedcoolant
0acb8ed85d
Merge branch 'main' into feat/nodes/add-w-h-latentsoutput 2023-05-12 15:23:29 +12:00
blessedcoolant
8c1c9cd702
Merge branch 'main' into feat/nodes/add-randomintinvocation 2023-05-12 15:21:49 +12:00
blessedcoolant
af95cef7f9
Merge branch 'main' into fix/nodes/fix-imageoutput-optionals 2023-05-12 15:08:19 +12:00
Lincoln Stein
df5b968954 model manager now running as a service 2023-05-11 21:24:29 -04:00
Sergey Borisov
27dc07d95a Set zero eta by default(fix ddim scheduler error) 2023-05-11 18:49:27 +03:00
blessedcoolant
f7dc171c4f Rename default schedulers across the app 2023-05-12 03:44:20 +12:00
blessedcoolant
8a836247c8 Add DPMPP Single, Euler Karras and DPMPP2 Multi Karras Schedulers 2023-05-12 02:23:33 +12:00
blessedcoolant
9a383e456d Codesplit SCHEDULER_MAP for reusage 2023-05-12 00:40:03 +12:00
blessedcoolant
c1e7460d39
Merge branch 'main' into unipc-sched 2023-05-12 00:11:09 +12:00
blessedcoolant
3ffff023b2 Add missing key to scheduler_map
It was breaking coz the sampler was not being reset. So needs a key on each. Will simplify this later.
2023-05-12 00:08:50 +12:00
psychedelicious
6cf308004a fix(nodes): remove Optionals on ImageOutputs 2023-05-11 20:54:57 +10:00
blessedcoolant
d1029138d2 Default to DDIM if scheduler is missing 2023-05-11 22:54:35 +12:00
blessedcoolant
06b5800d28 Add UniPC Scheduler 2023-05-11 22:43:18 +12:00
psychedelicious
483f2ccb56 feat(nodes): add RandomIntInvocation
just outputs a single random int
2023-05-11 20:33:32 +10:00
psychedelicious
93ced0bec6 feat(nodes): add w/h to latents outputs
This reduces the number of nodes needed when working with latents (ie fewer plain integer value nodes)

Also correct a few mistakes in the fields
2023-05-11 20:32:55 +10:00
psychedelicious
4333852c37 fix(nodes): fix missing context arg in LatentsToLatents 2023-05-11 19:28:42 +10:00
Eugene Brodsky
3baa230077
Merge branch 'main' into lstein/bugfix/compel 2023-05-11 00:50:45 -04:00
Lincoln Stein
8ad8c5c67a resolve conflicts with main 2023-05-11 00:19:20 -04:00
Lincoln Stein
4627910c5d added a wrapper model_manager_service and model events 2023-05-11 00:09:19 -04:00
psychedelicious
f488b1a7f2 fix(nodes): fix usage of Optional 2023-05-11 11:55:51 +10:00
psychedelicious
34f3a0f0e3 feat(nodes): improve default model choosing output 2023-05-11 11:55:51 +10:00
psychedelicious
d0bac1675e fix(nodes): fix ImageOutput Config 2023-05-11 11:55:51 +10:00
psychedelicious
4e56c962f4 fix(nodes): fix infill docstrings 2023-05-11 11:55:51 +10:00
psychedelicious
4ef0e43759 fix(nodes): remove dataURL invocation 2023-05-11 11:55:51 +10:00
psychedelicious
a7786d5ff2 fix(nodes): restore seamless to TextToLatents 2023-05-11 11:55:51 +10:00
psychedelicious
6c1de975d9 feat(nodes): add infill nodes 2023-05-11 11:55:51 +10:00
psychedelicious
a1079e455a feat(nodes): cleanup unused params, seed generation 2023-05-11 11:55:51 +10:00
psychedelicious
da4eacdffe feat(nodes): add InfillInvocation 2023-05-11 11:55:51 +10:00
psychedelicious
6102e560ba feat(nodes): add LatentsToImage node (VAE encode) 2023-05-11 11:55:51 +10:00
psychedelicious
206e6b1730 feat(nodes): wip inpaint node 2023-05-11 11:55:51 +10:00
psychedelicious
357cee2849 fix(nodes): fix cfg scale min value 2023-05-11 11:55:51 +10:00
psychedelicious
e0b9b5cc6c feat(nodes): add dataURL to image node 2023-05-11 11:55:51 +10:00
Lincoln Stein
aca4770481 fixed compel.py as requested 2023-05-10 21:40:44 -04:00
Lincoln Stein
fa6a580452 merge with main 2023-05-10 00:03:32 -04:00
Lincoln Stein
4649920074 adjust t2i to work with new model structure 2023-05-07 19:06:49 -04:00
Lincoln Stein
42d938fda5 remove debugging statement 2023-05-06 23:54:11 -04:00
Lincoln Stein
25ce47c44f remove reference to globals in compel.py 2023-05-06 22:49:35 -04:00
Lincoln Stein
a8cfa3565c Merge branch 'lstein/new-model-manager' of github.com:invoke-ai/InvokeAI into lstein/new-model-manager 2023-05-06 08:14:15 -04:00
Lincoln Stein
e0214a32bc mostly ported to new manager API; needs testing 2023-05-06 00:44:12 -04:00
StAlKeR7779
a80fe05e23 Rename compel node 2023-05-05 21:30:16 +03:00
StAlKeR7779
58d7833c5c Review changes 2023-05-05 21:09:29 +03:00
StAlKeR7779
5012f61599 Separate conditionings back to positive and negative 2023-05-05 15:47:51 +03:00
blessedcoolant
85c33823c3
Merge branch 'main' into feat/compel_node 2023-05-05 14:41:45 +12:00
psychedelicious
e04ada1319
Merge branch 'main' into patch-1 2023-05-05 10:38:45 +10:00
StAlKeR7779
81ec476f3a Revert seed field addition 2023-05-04 21:50:40 +03:00
StAlKeR7779
7d221e2518 Combine conditioning to one field(better fits for multiple type conditioning like perp-neg) 2023-05-04 20:14:22 +03:00
StAlKeR7779
56d3cbead0
Merge branch 'main' into feat/compel_node 2023-05-04 00:28:33 +03:00
Lincoln Stein
4687ad4ed6
Merge branch 'main' into enhance/invokeai-logs 2023-05-03 13:36:06 -04:00
psychedelicious
3264d30b44 feat(nodes): allow multiples of 8 for dimensions 2023-05-02 12:01:52 +10:00
psychedelicious
b49d76ebee feat(nodes): fix image to image fit param
it was ignored previously.
2023-05-01 17:28:22 +10:00
Lincoln Stein
974841926d logger is a interchangeable service 2023-04-29 10:48:50 -04:00
Lincoln Stein
8db20e0d95 rename log to logger throughout 2023-04-29 09:43:40 -04:00
Lincoln Stein
6b79e2b407 Merge branch 'main' into enhance/invokeai-logs
- resolve conflicts
- remove unused code identified by pyflakes
2023-04-28 10:09:46 -04:00
psychedelicious
4a924c9b54 feat(nodes): hardcode resize latents downsampling 2023-04-28 09:52:09 +10:00
psychedelicious
0453d60c64 fix(nodes): fix slatents and rlatents bugs 2023-04-28 09:52:09 +10:00
psychedelicious
c4f4f8b1b8 fix(nodes): remove unused width and height from t2l 2023-04-28 09:52:09 +10:00
psychedelicious
3e80eaa342 feat(nodes): add resize and scale latents nodes
- this resize/scale latents is what is needed for hires fix
- also remove unused `seed` from t2l
2023-04-28 09:52:09 +10:00
Andy Luhrs
0f95f7cea3
Fix inpaint node
Seems like this is the only change needed for the existing inpaint node to work.
2023-04-27 11:03:07 -07:00
StAlKeR7779
37916a22ad Use textual inversion manager from pipeline, remove extra conditioning info for uc 2023-04-25 12:53:13 +03:00
StAlKeR7779
8cb2fa8600 Restore log_tokenization check 2023-04-25 04:29:17 +03:00
StAlKeR7779
8f460b92f1 Make latent generation nodes use conditions instead of prompt 2023-04-25 04:21:03 +03:00
StAlKeR7779
d99a08a441 Add compel node and conditioning field type 2023-04-25 03:48:44 +03:00
psychedelicious
5f498e10bd
Partial migration of UI to nodes API (#3195)
* feat(ui): add axios client generator and simple example

* fix(ui): update client & nodes test code w/ new Edge type

* chore(ui): organize generated files

* chore(ui): update .eslintignore, .prettierignore

* chore(ui): update openapi.json

* feat(backend): fixes for nodes/generator

* feat(ui): generate object args for api client

* feat(ui): more nodes api prototyping

* feat(ui): nodes cancel

* chore(ui): regenerate api client

* fix(ui): disable OG web server socket connection

* fix(ui): fix scrollbar styles typing and prop

just noticed the typo, and made the types stronger.

* feat(ui): add socketio types

* feat(ui): wip nodes

- extract api client method arg types instead of manually declaring them
- update example to display images
- general tidy up

* start building out node translations from frontend state and add notes about missing features

* use reference to sampler_name

* use reference to sampler_name

* add optional apiUrl prop

* feat(ui): start hooking up dynamic txt2img node generation, create middleware for session invocation

* feat(ui): write separate nodes socket layer, txt2img generating and rendering w single node

* feat(ui): img2img implementation

* feat(ui): get intermediate images working but types are stubbed out

* chore(ui): add support for package mode

* feat(ui): add nodes mode script

* feat(ui): handle random seeds

* fix(ui): fix middleware types

* feat(ui): add rtk action type guard

* feat(ui): disable NodeAPITest

This was polluting the network/socket logs.

* feat(ui): fix parameters panel border color

This commit should be elsewhere but I don't want to break my flow

* feat(ui): make thunk types more consistent

* feat(ui): add type guards for outputs

* feat(ui): load images on socket connect

Rudimentary

* chore(ui): bump redux-toolkit

* docs(ui): update readme

* chore(ui): regenerate api client

* chore(ui): add typescript as dev dependency

I am having trouble with TS versions after vscode updated and now uses TS 5. `madge` has installed 3.9.10 and for whatever reason my vscode wants to use that. Manually specifying 4.9.5 and then setting vscode to use that as the workspace TS fixes the issue.

* feat(ui): begin migrating gallery to nodes

Along the way, migrate to use RTK `createEntityAdapter` for gallery images, and separate `results` and `uploads` into separate slices. Much cleaner this way.

* feat(ui): clean up & comment results slice

* fix(ui): separate thunk for initial gallery load so it properly gets index 0

* feat(ui): POST upload working

* fix(ui): restore removed type

* feat(ui): patch api generation for headers access

* chore(ui): regenerate api

* feat(ui): wip gallery migration

* feat(ui): wip gallery migration

* chore(ui): regenerate api

* feat(ui): wip refactor socket events

* feat(ui): disable panels based on app props

* feat(ui): invert logic to be disabled

* disable panels when app mounts

* feat(ui): add support to disableTabs

* docs(ui): organise and update docs

* lang(ui): add toast strings

* feat(ui): wip events, comments, and general refactoring

* feat(ui): add optional token for auth

* feat(ui): export StatusIndicator and ModelSelect for header use

* feat(ui) working on making socket URL dynamic

* feat(ui): dynamic middleware loading

* feat(ui): prep for socket jwt

* feat(ui): migrate cancelation

also updated action names to be event-like instead of declaration-like

sorry, i was scattered and this commit has a lot of unrelated stuff in it.

* fix(ui): fix img2img type

* chore(ui): regenerate api client

* feat(ui): improve InvocationCompleteEvent types

* feat(ui): increase StatusIndicator font size

* fix(ui): fix middleware order for multi-node graphs

* feat(ui): add exampleGraphs object w/ iterations example

* feat(ui): generate iterations graph

* feat(ui): update ModelSelect for nodes API

* feat(ui): add hi-res functionality for txt2img generations

* feat(ui): "subscribe" to particular nodes

feels like a dirty hack but oh well it works

* feat(ui): first steps to node editor ui

* fix(ui): disable event subscription

it is not fully baked just yet

* feat(ui): wip node editor

* feat(ui): remove extraneous field types

* feat(ui): nodes before deleting stuff

* feat(ui): cleanup nodes ui stuff

* feat(ui): hook up nodes to redux

* fix(ui): fix handle

* fix(ui): add basic node edges & connection validation

* feat(ui): add connection validation styling

* feat(ui): increase edge width

* feat(ui): it blends

* feat(ui): wip model handling and graph topology validation

* feat(ui): validation connections w/ graphlib

* docs(ui): update nodes doc

* feat(ui): wip node editor

* chore(ui): rebuild api, update types

* add redux-dynamic-middlewares as a dependency

* feat(ui): add url host transformation

* feat(ui): handle already-connected fields

* feat(ui): rewrite SqliteItemStore in sqlalchemy

* fix(ui): fix sqlalchemy dynamic model instantiation

* feat(ui, nodes): metadata wip

* feat(ui, nodes): models

* feat(ui, nodes): more metadata wip

* feat(ui): wip range/iterate

* fix(nodes): fix sqlite typing

* feat(ui): export new type for invoke component

* tests(nodes): fix test instantiation of ImageField

* feat(nodes): fix LoadImageInvocation

* feat(nodes): add `title` ui hint

* feat(nodes): make ImageField attrs optional

* feat(ui): wip nodes etc

* feat(nodes): roll back sqlalchemy

* fix(nodes): partially address feedback

* fix(backend): roll back changes to pngwriter

* feat(nodes): wip address metadata feedback

* feat(nodes): add seeded rng to RandomRange

* feat(nodes): address feedback

* feat(nodes): move GET images error handling to DiskImageStorage

* feat(nodes): move GET images error handling to DiskImageStorage

* fix(nodes): fix image output schema customization

* feat(ui): img2img/txt2img -> linear

- remove txt2img and img2img tabs
- add linear tab
- add initial image selection to linear parameters accordion

* feat(ui): tidy graph builders

* feat(ui): tidy misc

* feat(ui): improve invocation union types

* feat(ui): wip metadata viewer recall

* feat(ui): move fonts to normal deps

* feat(nodes): fix broken upload

* feat(nodes): add metadata module + tests, thumbnails

- `MetadataModule` is stateless and needed in places where the `InvocationContext` is not available, so have not made it a `service`
- Handles loading/parsing/building metadata, and creating png info objects
- added tests for MetadataModule
- Lifted thumbnail stuff to util

* fix(nodes): revert change to RandomRangeInvocation

* feat(nodes): address feedback

- make metadata a service
- rip out pydantic validation, implement metadata parsing as simple functions
- update tests
- address other minor feedback items

* fix(nodes): fix other tests

* fix(nodes): add metadata service to cli

* fix(nodes): fix latents/image field parsing

* feat(nodes): customise LatentsField schema

* feat(nodes): move metadata parsing to frontend

* fix(nodes): fix metadata test

---------

Co-authored-by: maryhipp <maryhipp@gmail.com>
Co-authored-by: Mary Hipp <maryhipp@Marys-MacBook-Air.local>
2023-04-22 13:10:20 +10:00
Lincoln Stein
b164330e3c replaced remaining print statements with log.*() 2023-04-18 20:49:00 -04:00
Eugene
3daaddf15b nodes: remove duplicate LatentsToLatentsInvocation 2023-04-16 09:39:33 -04:00
Kyle Schouviller
23d65e7162
[nodes] Add subgraph library, subgraph usage in CLI, and fix subgraph execution (#3180)
* Add latent to latent (img2img equivalent)
Fix a CLI bug with multiple links per node

* Using "latents" instead of "latent"

* [nodes] In-progress implementation of graph library

* Add linking to CLI for graph nodes (still broken)

* Fix subgraph execution, fix subgraph linking in CLI

* Fix LatentsToLatents
2023-04-14 06:41:06 +00:00
psychedelicious
d923d1d66b fix(nodes): fix naming of CvInvocationConfig 2023-04-11 12:13:53 +10:00
psychedelicious
1f2c1e14db fix(nodes): move InvocationConfig to baseinvocation.py 2023-04-11 12:13:53 +10:00
psychedelicious
07e3a0ec15 feat(nodes): add invocation schema customisation, add model selection
- add invocation schema customisation

done via fastapi's `Config` class and `schema_extra`. when using `Config`, inherit from `InvocationConfig` to get type hints.

where it makes sense - like for all math invocations - define a `MathInvocationConfig` class and have all invocations inherit from it.

this customisation can provide any arbitrary additional data to the UI. currently it provides tags and field type hints.

this is necessary for `model` type fields, which are actually string fields. without something like this, we can't reliably differentiate  `model` fields from normal `string` fields.

can also be used for future field types.

all invocations now have tags, and all `model` fields have ui type hints.

- fix model handling for invocations

added a helper to fall back to the default model if an invalid model name is chosen. model names in graphs now work.

- fix latents progress callback

noticed this wasn't correct while working on everything else.
2023-04-11 12:13:53 +10:00
psychedelicious
427db7c7e2 feat(nodes): fix typo in PasteImageInvocation 2023-04-10 21:33:08 +10:00
psychedelicious
dad3a7f263 fix(nodes): sampler_name --> scheduler
the name of this was changed at some point. nodes still used the old name, so scheduler selection did nothing. simple fix.
2023-04-10 19:54:09 +10:00
psychedelicious
34402cc46a feat(nodes): add list_images endpoint
- add `list_images` endpoint at `GET api/v1/images`
- extend `ImageStorageBase` with `list()` method, implemented it for `DiskImageStorage`
- add `ImageReponse` class to for image responses, which includes urls, metadata
- add `ImageMetadata` class (basically a stub at the moment)
- uploaded images now named `"{uuid}_{timestamp}.png"`
- add `models` modules. besides separating concerns more clearly, this helps to mitigate circular dependencies
- improve thumbnail handling
2023-04-09 13:48:44 +10:00
psychedelicious
111d674e71 fix(nodes): use correct torch device in NoiseInvocation 2023-04-08 12:32:03 +10:00
Kyle Schouviller
85b020f76c
[nodes] Add latent nodes, storage, and fix iteration bugs (#3091)
* Add latents nodes.
* Fix iteration expansion.
* Add collection generator nodes, math nodes.
* Add noise node.
* Add some graph debug commands to the CLI.
* Fix negative id linking in CLI.
* Fix a CLI bug with multiple links per node.
2023-04-06 04:06:05 +00:00
psychedelicious
4221cf7731 fix(nodes): fix schema generation for output classes
All output classes need to have their properties flagged as `required` for the schema generation to work as needed.
2023-03-26 17:20:10 +11:00
psychedelicious
c34ac91ff0 fix(nodes): fix cancel; fix callback for img2img, inpaint 2023-03-26 17:07:40 +11:00
Lincoln Stein
dac3c158a5 Merge branch 'main' into feat/preview_predicted_x0
- resolve conflicts with generate.py invocation
- remove unused symbols that pyflakes complains about
- add **untested** code for passing intermediate latent image to the
  step callback in the format expected.
2023-03-25 16:07:18 -04:00
psychedelicious
67f8f222d9 fix(nodes): fix step_callback + fast latents generation
this depends on the small change in #2957
2023-03-16 20:03:08 +11:00
Kyle Schouviller
0c3b1fe3c4 [nodes] Fixes calls into image to image and inpaint from nodes 2023-03-12 22:12:42 -07:00
Kevin Turner
288cee9611 Merge remote-tracking branch 'origin/main' into feat/preview_predicted_x0
# Conflicts:
#	invokeai/app/invocations/generate.py
2023-03-12 20:56:02 -07:00
Lincoln Stein
8ca91b1774 add restoration services to nodes 2023-03-11 17:00:00 -05:00
Lincoln Stein
d612f11c11 initialize InvokeAIGenerator object with model, not manager 2023-03-11 09:06:46 -05:00
Lincoln Stein
95954188b2 remove factory pattern
Factory pattern is now removed. Typical usage of the InvokeAIGenerator is now:

```
from invokeai.backend.generator import (
    InvokeAIGeneratorBasicParams,
    Txt2Img,
    Img2Img,
    Inpaint,
)
    params = InvokeAIGeneratorBasicParams(
        model_name = 'stable-diffusion-1.5',
        steps = 30,
        scheduler = 'k_lms',
        cfg_scale = 8.0,
        height = 640,
        width = 640
        )
    print ('=== TXT2IMG TEST ===')
    txt2img = Txt2Img(manager, params)
    outputs = txt2img.generate(prompt='banana sushi', iterations=2)

    for i in outputs:
        print(f'image={output.image}, seed={output.seed}, model={output.params.model_name}, hash={output.model_hash}, steps={output.params.steps}')
```

The `params` argument is optional, so if you wish to accept default
parameters and selectively override them, just do this:

```
    outputs = Txt2Img(manager).generate(prompt='banana sushi',
                                        steps=50,
					scheduler='k_heun',
					model_name='stable-diffusion-2.1'
					)
```
2023-03-10 19:33:04 -05:00
Kevin Turner
fe6858f2d9 feat: use the predicted denoised image for previews
Some schedulers report not only the noisy latents at the current timestep,
but also their estimate so far of what the de-noised latents will be.

It makes for a more legible preview than the noisy latents do.
2023-03-09 20:28:06 -08:00
Lincoln Stein
5d37fa6e36 node-based txt2img working without generate 2023-03-09 00:18:29 -05:00
Lincoln Stein
ab35c241c2 protect invocations against black autoformatting 2023-03-03 15:25:08 -05:00
Lincoln Stein
6477e31c1e revert and disable auto-formatting of invocations 2023-03-03 14:59:17 -05:00
Lincoln Stein
60a98cacef all vestiges of ldm.invoke removed 2023-03-03 01:02:00 -05:00
Lincoln Stein
6a990565ff all files migrated; tweaks needed 2023-03-03 00:02:15 -05:00