psychedelicious
d6a959b000
feat(nodes): tidy controlnet processor nodes & improve descriptions
2023-06-04 22:34:58 +10:00
Lincoln Stein
31e97ead2a
move invokeai.db to ~/invokeai/databases
...
- The invokeai.db database file has now been moved into
`INVOKEAIROOT/databases`. Using plural here for possible
future with more than one database file.
- Removed a few dangling debug messages that appeared during
testing.
- Rebuilt frontend to test web.
2023-06-03 20:25:34 -04:00
Lincoln Stein
98773b20ac
merge with main
2023-06-01 18:09:49 -04:00
Sergey Borisov
b47786e846
First working TI draft
2023-05-31 02:12:27 +03:00
psychedelicious
a9a2bd90c2
fix(nodes): set min and max for l2l strength
2023-05-30 09:06:13 -04:00
psychedelicious
47ca71a7eb
fix(nodes): set cfg_scale min to 1 in latents
2023-05-30 09:06:13 -04:00
Sergey Borisov
420a76ecdd
Add lora loader node
2023-05-30 02:12:33 +03:00
Sergey Borisov
79de9047b5
First working lora implementation
2023-05-30 01:11:00 +03:00
psychedelicious
bbb4e8f5ef
feat(nodes): add resize image and scale image nodes
2023-05-29 09:07:46 -04:00
psychedelicious
08a14ee6d5
fix(nodes): fix conflicts with controlnet
2023-05-28 20:19:56 -04:00
psychedelicious
160267c71a
feat(nodes): refactor image types
...
- Remove `ImageType` entirely, it is confusing
- Create `ResourceOrigin`, may be `internal` or `external`
- Revamp `ImageCategory`, may be `general`, `mask`, `control`, `user`, `other`. Expect to add more as time goes on
- Update images `list` route to accept `include_categories` OR `exclude_categories` query parameters to afford finer-grained querying. All services are updated to accomodate this change.
The new setup should account for our types of images, including the combinations we couldn't really handle until now:
- Canvas init and masks
- Canvas when saved-to-gallery or merged
2023-05-28 20:19:56 -04:00
user1
9a796364da
Fixed controlnet preprocessors and controlnet handling in TextToLatents to work with revised Image services.
2023-05-26 21:44:00 -04:00
user1
d9b1e4a98c
Added nodes for float params: ParamFloatInvocation and FloatCollectionOutput. Also added FloatOutput.
2023-05-26 21:44:00 -04:00
user1
a4dec8c1d6
Fixed bug where MediapipFaceProcessorInvocation was ignoring max_faces and min_confidence params.
2023-05-26 21:44:00 -04:00
user1
8960ceb98b
Added Mediapipe image processor for use as ControlNet preprocessor.
...
Also hacked in ability to specify HF subfolder when loading ControlNet models from string.
2023-05-26 21:44:00 -04:00
psychedelicious
be79d088c0
fix(nodes): controlnet input accepts list or single controlnet
2023-05-26 21:44:00 -04:00
psychedelicious
009407ea3f
fix(ui): fix node ui type hints
2023-05-26 21:44:00 -04:00
user1
324e9eb74b
Extended node-based ControlNet support to LatentsToLatentsInvocation.
2023-05-26 21:44:00 -04:00
user1
56cff40362
Cleaning up after ControlNet refactor in TextToLatentsInvocation
2023-05-26 21:44:00 -04:00
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