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
2,192 Commits 274 Branches 239 Tags 397 MiB
206101f59d
Commit Graph

2192 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
damian0815
206101f59d revert initializer words for embeddings 2022-11-13 15:47:28 -05:00
Damian Stewart
9bf6013fdd
refactor(cross_attention_control): remove outer CrossAttentionControl class (#1459) 
I was working on attention control in #1384, started making a few
changes to improve the typing and make it easier to work with. Then the
whitespace changes touched so many lines it seemed worth separating out
these refactoring operations to this PR so they don't get mixed up with
other functional changes.

It would be helpful to merge this to `development` before continuing
work on attention control in #1384

The github diff isn't good at showing these together since they changed
whitespace on so many lines. It may be easier to review by looking at
the individual commits, and/or toggling the "hide whitespace
differences" option in the view.
 2022-11-13 14:20:18 +01:00
blessedcoolant
1d11e06e6f Remove gfpgan_dir 
+ Update GFPGAN Model Path Defaults
>  Update them to match the new file heirarchy
 2022-11-12 19:24:11 -05:00
Kevin Turner
47e6f94111 refactor(cross_attention_control): type hints and other lint 🚮 2022-11-12 11:25:39 -08:00
Kevin Turner
810fad9e06 refactor(cross_attention_control): re-order enum class for easier reference 2022-11-12 11:05:33 -08:00
Kevin Turner
853c6af623 refactor(cross_attention_control): remove outer CrossAttentionControl class 
Python has modules. We don't need to use a class to provide a namespace.
 2022-11-12 11:01:10 -08:00
Lincoln Stein
1b6bbfb4db Merge branch 'lstein-outcrop-improvements' of github.com:/invoke-ai/InvokeAI into lstein-outcrop-improvements 2022-11-12 15:41:16 +00:00
Lincoln Stein
67e25624b9 simplify logic around negative seeds 2022-11-12 15:41:01 +00:00
Lincoln Stein
9c218788e2
Merge branch 'development' into lstein-outcrop-improvements 2022-11-12 10:39:57 -05:00
Lincoln Stein
bb084a844b simplify logic around negative seeds 2022-11-12 15:39:03 +00:00
Lincoln Stein
0a88243911
Revert "Outcrop improvements" (#1449) 
Reverts invoke-ai/InvokeAI#1414

- missed review comments from @Kyle0654
 2022-11-11 15:38:02 -05:00
Lincoln Stein
8a0a90d0f3 Merge branch 'lstein-outcrop-improvements' of github.com:/invoke-ai/InvokeAI into lstein-outcrop-improvements 2022-11-11 20:37:13 +00:00
Lincoln Stein
9141132a5c enhance outcropping with ability to direct contents of new regions 
This commit does several things that improve the customizability of the CLI `outcrop` command:

1. When outcropping an image you can now add a `--new_prompt` option, to specify a new prompt to be applied to the outpainted region instead of the prompt used to generate the image.
2. Similarly you can provide a new seed using `--seed` (or `-S`). A seed less than zero will pick one randomly.
3. The metadata written into the outcropped file is now more informative about what was previously stored.
4. This PR also fixes the crash that happened when trying to outcrop an image  that does not contain InvokeAI metadata.

Other changes:

- add error checking suggested by @Kyle0654
- add special case in invoke.py to allow -1 to be passed as seed.
  This now only occurs for postprocessing commands. Previously, -1
  caused previous seed to be used, and this still applies to generate
  operations.
 2022-11-11 20:34:21 +00:00
Lincoln Stein
78f7bef1a3 Revert "enable outcropping of random JPG/PNG images" 
This reverts commit 48aa6416dc.
 2022-11-11 10:30:44 -05:00
Lincoln Stein
1fb7b50be7 Revert "enhance outcropping with ability to direct contents of new regions" 
This reverts commit 8aa94d5774.
 2022-11-11 10:30:44 -05:00
Kyle Schouviller
b57c81ab38 Remove editable flag from clipseg in requirements 2022-11-11 09:32:07 -05:00
Lincoln Stein
af040e97af prevent two models from being marked default in models.yaml 2022-11-11 09:28:17 -05:00
Kyle Schouviller
8dc7f119e5 Fix performance issue introduced by torch cuda cache clear during generation 2022-11-10 23:01:32 -08:00
Lincoln Stein
4b4111a802 fix invoke.py crash if no models.yaml file present 
- Script will now offer the user the ability to create a
  minimal models.yaml and then gracefully exit.
- Closes #1420
 2022-11-10 21:54:26 -05:00
Lincoln Stein
832f183320 fix #1402 2022-11-10 21:54:13 -05:00
Lincoln Stein
8aa94d5774 enhance outcropping with ability to direct contents of new regions 
- When outcropping an image you can now add a `--new_prompt` option, to specify
  a new prompt to be used instead of the original one used to generate the image.

- Similarly you can provide a new seed using `--seed` (or `-S`). A seed of zero
  will pick one randomly.

- This PR also fixes the crash that happened when trying to outcrop an image
  that does not contain InvokeAI metadata.
 2022-11-10 21:53:52 -05:00
Lincoln Stein
48aa6416dc enable outcropping of random JPG/PNG images 
- Works best with runwayML inpainting model
- Numerous code changes required to propagate seed to final metadata.
  Original code predicated on the image being generated within InvokeAI.
 2022-11-10 21:53:52 -05:00
Lincoln Stein
47ddda1f64 Revert "Log strength with hires" 
This reverts commit 82d4904c07.
 2022-11-10 16:50:00 -05:00
Lincoln Stein
c248ae44d4 Revert "Resize hires as an image" 
This reverts commit d05b1b3544.
 2022-11-10 16:50:00 -05:00
Mike DiGiovanni
9e4545b2fc Fixes typos in README.md 2022-11-10 09:15:29 -05:00
mauwii
8cf3883adc re-change TencentARC/GFPGAN to invoke-ai/GFPGAN 2022-11-09 12:53:36 -05:00
mauwii
e06a6ed4c8 add changes required by @tildebyte 2022-11-09 12:53:36 -05:00
mauwii
12a33f6e2d fix conflict in environment-linux-aarch64.yml 2022-11-09 12:53:36 -05:00
mauwii
6d9638ba31 remove PIP_EXISTS_ACTION from env 2022-11-09 12:53:36 -05:00
mauwii
c54eb00055 update python version 2022-11-09 12:53:36 -05:00
mauwii
72338506ed update environment.yml 2022-11-09 12:53:36 -05:00
mauwii
78c1d07c4b update environment-linux-aarch64.yml 2022-11-09 12:53:36 -05:00
mauwii
143b18af8a update pip dependencies 
- remove realesrgan
- add git+https://github.com/invoke-ai/Real-ESRGAN.git
- remove git+https://github.com/CompVis/taming-transformers.git
- add taming-transformers-rom1504
- change TencentARC/GFPGAN to invoke-ai/GFPGAN
 2022-11-09 12:53:36 -05:00
mauwii
9d39d6ecb3 add PIP_EXISTS_ACTION=w to test-invoke-conda`s env 2022-11-09 12:53:36 -05:00
mauwii
9686bf0ea8 switch back to getpass_asterisk... ... until preload_models.py is ready 2022-11-09 12:53:36 -05:00
mauwii
7aa7be6b24 use taming-transformers-rom1504, remove -e ... 
... to address required changes
 2022-11-09 12:53:36 -05:00
mauwii
443c9110f1 remove push triggers, since pr trigger is enough 2022-11-09 12:53:36 -05:00
mauwii
ae0ce82609 add 2 missed versions 
unpinned them for testing purpose with linux container, 4got to re-pin
 2022-11-09 12:53:36 -05:00
mauwii
f1982cb6d8 update push triggers in test-invoke-conda.yml 2022-11-09 12:53:36 -05:00
mauwii
af62958323 update environment-mac.yml 2022-11-09 12:53:36 -05:00
Lincoln Stein
9342ad8d97 prevent crash when switching to an invalid model 2022-11-09 10:07:15 -05:00
damian0815
5214742d02 don't suppress exceptions when doing cross-attention control 2022-11-09 07:21:21 -05:00
damian0815
178f0c78d8 Fix #1362 by improving VRAM usage patterns when doing .swap() 
commit ef3f7a26e242b73c2beb0195c7fd8f654ef47f55
Author: damian0815 <null@damianstewart.com>
Date:   Tue Nov 8 12:18:37 2022 +0100

    remove log spam

commit 7189d649622d4668b120b0dd278388ad672142c4
Author: damian0815 <null@damianstewart.com>
Date:   Tue Nov 8 12:10:28 2022 +0100

    change the way saved slicing strategy is applied

commit 01c40f751ab72955140165c16f95ae411732265b
Author: damian0815 <null@damianstewart.com>
Date:   Tue Nov 8 12:04:43 2022 +0100

    fix slicing_strategy_getter callsite

commit f8cfe25150a346958903316bc710737d99839923
Author: damian0815 <null@damianstewart.com>
Date:   Tue Nov 8 11:56:22 2022 +0100

    cleanup, consistent dim=0 also tested

commit 5bf9b1e890d48e962afd4a668a219b68271e5dc1
Author: damian0815 <null@damianstewart.com>
Date:   Tue Nov 8 11:34:09 2022 +0100

    refactored context, tested with non-sliced cross attention control

commit d58a46e39bf562e7459290d2444256e8c08ad0b6
Author: damian0815 <null@damianstewart.com>
Date:   Sun Nov 6 00:41:52 2022 +0100

    cleanup

commit 7e2c658b4c06fe239311b65b9bb16fa3adec7fd7
Author: damian0815 <null@damianstewart.com>
Date:   Sat Nov 5 22:57:31 2022 +0100

    disable logs

commit 20ee89d93841b070738b3d8a4385c93b097d92eb
Author: damian0815 <null@damianstewart.com>
Date:   Sat Nov 5 22:36:58 2022 +0100

    slice saved attention if necessary

commit 0a7684a22c880ec0f48cc22bfed4526358f71546
Author: damian0815 <null@damianstewart.com>
Date:   Sat Nov 5 22:32:38 2022 +0100

    raise instead of asserting

commit 7083104c7f3a0d8fd96e94a2f391de50a3c942e4
Author: damian0815 <null@damianstewart.com>
Date:   Sat Nov 5 22:31:00 2022 +0100

    store dim when saving slices

commit f7c0808ed383ec1dc70645288a798ed2aa4fa85c
Author: damian0815 <null@damianstewart.com>
Date:   Sat Nov 5 22:27:16 2022 +0100

    don't retry on exception

commit 749a721e939b3fe7c1741e7998dab6bd2c85a0cb
Author: damian0815 <null@damianstewart.com>
Date:   Sat Nov 5 22:24:50 2022 +0100

    stuff

commit 032ab90e9533be8726301ec91b97137e2aadef9a
Author: damian0815 <null@damianstewart.com>
Date:   Sat Nov 5 22:20:17 2022 +0100

    more logging

commit 3dc34b387f033482305360e605809d95a40bf6f8
Author: damian0815 <null@damianstewart.com>
Date:   Sat Nov 5 22:16:47 2022 +0100

    logs

commit 901c4c1aa4b9bcef695a6551867ec8149e6e6a93
Author: damian0815 <null@damianstewart.com>
Date:   Sat Nov 5 22:12:39 2022 +0100

    actually set save_slicing_strategy to True

commit f780e0a0a7c6b6a3db320891064da82589358c8a
Author: damian0815 <null@damianstewart.com>
Date:   Sat Nov 5 22:10:35 2022 +0100

    store slicing strategy

commit 93bb6d566fd18c5c69ef7dacc8f74ba2cf671cb7
Author: damian <git@damianstewart.com>
Date:   Sat Nov 5 20:43:48 2022 +0100

    still not it

commit 5e3a9541f8ae00bde524046963910323e20c40b7
Author: damian <git@damianstewart.com>
Date:   Sat Nov 5 17:20:02 2022 +0100

    wip offloading attention slices on-demand

commit 4c2966aa856b6f3b446216da3619ae931552ef08
Author: damian0815 <null@damianstewart.com>
Date:   Sat Nov 5 15:47:40 2022 +0100

    pre-emptive offloading, idk if it works

commit 572576755e9f0a878d38e8173e485126c0efbefb
Author: root <you@example.com>
Date:   Sat Nov 5 11:25:32 2022 +0000

    push attention slices to cpu. slow but saves memory.

commit b57c83a68f2ac03976ebc89ce2ff03812d6d185f
Author: damian0815 <null@damianstewart.com>
Date:   Sat Nov 5 12:04:22 2022 +0100

    verbose logging

commit 3a5dae116f110a96585d9eb71d713b5ed2bc3d2b
Author: damian0815 <null@damianstewart.com>
Date:   Sat Nov 5 11:50:48 2022 +0100

    wip fixing mem strategy crash (4 test on runpod)

commit 3cf237db5fae0c7b0b4cc3c47c81830bdb2ae7de
Author: damian0815 <null@damianstewart.com>
Date:   Fri Nov 4 09:02:40 2022 +0100

    wip, only works on cuda
 2022-11-09 07:21:21 -05:00
Lincoln Stein
2487040ae3 enhance outcropping with ability to direct contents of new regions 
- When outcropping an image you can now add a `--new_prompt` option, to specify
  a new prompt to be used instead of the original one used to generate the image.

- Similarly you can provide a new seed using `--seed` (or `-S`). A seed of zero
  will pick one randomly.

- This PR also fixes the crash that happened when trying to outcrop an image
  that does not contain InvokeAI metadata.
 2022-11-08 17:27:42 +00:00
Lincoln Stein
5606af5083 enable outcropping of random JPG/PNG images 
- Works best with runwayML inpainting model
- Numerous code changes required to propagate seed to final metadata.
  Original code predicated on the image being generated within InvokeAI.
 2022-11-08 15:22:32 +00:00
Lincoln Stein
4b5a96501d load favorite options from ~/.invokeai init file 2022-11-08 13:55:42 +00:00
Lincoln Stein
ededeaed86 Merge branch 'add-invokeai-initfile' into development 2022-11-08 13:41:11 +00:00
Lincoln Stein
636620b1d5 change initfile to ~/.invokeai 
- adjust documentation
- also fix 'clipseg_models' to 'clipseg', which seems to be working now
 2022-11-08 03:26:16 +00:00
Lincoln Stein
21961f0c32 Revert "Use array slicing to calc ddim timesteps" 
This reverts commit 1f0c5b4cf1.
 2022-11-07 15:37:53 -05:00
Lincoln Stein
1fe41146f0 add support for an initialization file, invokeai.init 
- Place preferred startup command switches in a file named
  "invokeai.init". The file can consist of a single line of switches
  such as "--web --steps=28", a series of switches on each
  line, or any combination of the two.

 Example:
 ```
   --web
   --host=0.0.0.0
   --steps=28
   --grid
   -f 0.6 -C 11.0 -A k_euler_a
```

- The following options, which were previously only available within
  the CLI, are now available on the command line as well:

  --steps
  --strength
  --cfg_scale
  --width
  --height
  --fit
 2022-11-06 22:02:45 -05:00