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
2,777 Commits 274 Branches 239 Tags 397 MiB
d74c4009cb
Commit Graph

2777 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Eugene Brodsky
d423db4f82 (meta) add copyright statements for installer code 2023-01-31 23:47:36 -05:00
Eugene Brodsky
5c8c204a1b (installer) fix regression in directory selection 2023-01-31 23:47:36 -05:00
Eugene Brodsky
a03471c588 (installer) hide system and user site packages from the installer 2023-01-31 23:47:36 -05:00
Kevin Turner
6608343455
[enhancement] Print status message at startup when xformers is available (#2461) 2023-01-31 19:11:17 -08:00
Kevin Turner
abd972f099
Merge branch 'main' into feat/xformers-startup-message 2023-01-31 18:48:09 -08:00
Lincoln Stein
bd57793a65
fix img2img by working around pytorch bug (#2458) 
horribly, temporarily send the vae to `.cpu()` so that good latents can
be produced

closes #2418
 2023-01-31 21:46:05 -05:00
Kevin Turner
8cdc65effc
Merge branch 'main' into fix_2418_simplified 2023-01-31 17:45:54 -08:00
Kevin Turner
85b553c567 requirements: add xformers for CUDA platforms 
Now available from pip!
 2023-01-31 16:51:43 -08:00
Matthias Wild
af74a2d1f4
fix broken Dockerfile (#2445) 
also switch to `python:3.9-slim` since it has a ton less security issues
 2023-02-01 01:47:25 +01:00
mauwii
6fdc9ac224 re-enable INVOKE_MODEL_RECONFIGURE 2023-02-01 01:21:07 +01:00
mauwii
8107d354d9 fix broken Dockerfile 
also switch to python 3.9:slim since it has a ton less security issues
 2023-02-01 01:21:07 +01:00
mauwii
7ca8abb206
integrate required changes 
- also remove conda related things
- rename `invoke` to `invokeai`
- rename `configure_invokeai` to `invokeai-configure`
- rename venv back to common `.venv` but add `--prompt InvokeAI`
- remove outdated information
 2023-02-01 01:17:24 +01:00
Lincoln Stein
28c17613c4
feat(inpaint): add solid infill for use with inpainting model (#2441) 
A new infill method, **solid:** solid color. currently using middle
gray.

Fixes #2417

It seems like the runwayml inpainting model specifically expects those
masked areas to be blanked out like this.

I haven't tried the SD 2.0 inpainting model with it yet.
 2023-01-31 18:27:48 -05:00
mauwii
eeb7a4c28c
(ci) disable py3.9, lin-cuda-11_6 and win cuda 2023-02-01 00:24:56 +01:00
mauwii
0009d82a92
update test_path.py to also verify caution.png 2023-02-01 00:22:28 +01:00
Lincoln Stein
e6d52d7ce6
Merge branch 'main' into fix_2418_simplified 2023-01-31 18:11:56 -05:00
Lincoln Stein
8c726d3e3e
Merge branch 'main' into build/no-actions-on-draft 2023-01-31 18:08:52 -05:00
Lincoln Stein
56e2d22b6e
Merge branch 'main' into feat/solid-infill 2023-01-31 18:02:17 -05:00
Lincoln Stein
053d11fe30
fix(inpainting model): blank areas to be repainted in the masked image (#2447) 
Otherwise the model seems too reluctant to change these areas, even
though the mask channel should allow it to.

This makes the solid infill method proposed by #2441 less necessary,
though I think there's still a place for an infill method that is faster
than patchmatch and more predictable than tiles.

Even with #2441, this PR is still useful because it influences all areas
to be painted, not just the infill area.

Fixes #2417
 2023-01-31 18:01:33 -05:00
Lincoln Stein
0066187651
Merge branch 'main' into feat/solid-infill 2023-01-31 17:53:09 -05:00
Lincoln Stein
d3d24fa816 fill color is parameterized 2023-01-31 17:52:33 -05:00
Kevin Turner
4d58fed6b0
Merge branch 'main' into fix/inpainting-blank-slate 2023-01-31 11:04:56 -08:00
Kevin Turner
bde5874707
fix dimension errors when inpainting model is used with hires-fix (#2440) 2023-01-31 11:04:02 -08:00
Kevin Turner
eed802f5d9
Merge branch 'main' into fix/hires_inpaint 2023-01-31 09:34:29 -08:00
Lincoln Stein
c13e11a264 Merge branch 'dev/installer' of github.com:invoke-ai/InvokeAI into dev/installer 2023-01-31 12:26:19 -05:00
Lincoln Stein
1c377b7995 further improvements to ability to find location of data files 
- implement the following pattern for finding data files under both
  regular and editable install conditions:

  import invokeai.foo.bar as bar
  path = bar.__path__[0]

- this *seems* to work reliably with Python 3.9. Testing on 3.10 needs
  to be performed.
 2023-01-31 12:24:55 -05:00
mauwii
efe8dcaae9
cleanup test_path.py, enable pytest in pipeline 
temporary enable 3.9 tests as well
 2023-01-31 18:18:32 +01:00
Lincoln Stein
fc8e3dbcd3 fix crash when editing name of model 
- fixes a spurious "unknown model name" error when trying to edit the
  short name of an existing model.
- relaxes naming requirements to include the ':' and '/' characters
  in model names
 2023-01-31 09:59:58 -05:00
mauwii
ec1e83e912
add pytest to test path of frontend and configs 2023-01-31 09:06:06 +01:00
mauwii
ab9daf1241
remove frontend from configure_invokeai.py 
since it does not get accessed there at all
 2023-01-31 08:15:48 +01:00
mauwii
c061c1b1b6
fix frontend path 
point to package's path instead of searching for it
 2023-01-31 08:15:20 +01:00
Lincoln Stein
b9cc56593e print status message at startup when xformers is available 2023-01-30 22:01:06 -05:00
psychedelicious
6a0e1c8673
Merge branch 'main' into build/no-actions-on-draft 2023-01-31 12:00:38 +11:00
Kevin Turner
371edc993a
Implement .swap() against diffusers 0.12 (#2385) 2023-01-30 15:56:24 -08:00
Lincoln Stein
d71734c90d update frontend path in lint test 2023-01-30 18:48:43 -05:00
Lincoln Stein
9ad4c03277 Various fixes 
1) Downgrade numpy to avoid dependency conflict with numba
2) Move all non ldm/invoke files into `invokeai`. This includes assets, backend, frontend, and configs.
3) Fix up way that the backend finds the frontend and the generator finds the NSFW caution.png icon.
 2023-01-30 18:42:17 -05:00
Damian Stewart
5299324321 workaround for pytorch bug, fixes #2418 2023-01-30 18:45:53 +01:00
Damian Stewart
817e36f8bf Merge branch 'diffusers_cross_attention_control_reimplementation' of github.com:damian0815/InvokeAI into diffusers_cross_attention_control_reimplementation 2023-01-30 16:23:52 +01:00
Damian Stewart
d044d4c577 rename override/restore methods to better reflect what they actually do 2023-01-30 16:23:44 +01:00
Damian Stewart
3f1120e6f2
Merge branch 'main' into diffusers_cross_attention_control_reimplementation 2023-01-30 16:17:25 +01:00
Damian Stewart
17d73d09c0 Revert "with diffusers cac, always run the original prompt on the first step" 
This reverts commit 27ee939e4b.
 2023-01-30 15:38:03 +01:00
Damian Stewart
478c379534 for cac make t_start=0.1 the default 2023-01-30 15:30:01 +01:00
Damian Stewart
c5c160a788 Merge branch 'diffusers_cross_attention_control_reimplementation' of github.com:damian0815/InvokeAI into diffusers_cross_attention_control_reimplementation 2023-01-30 14:51:06 +01:00
Damian Stewart
27ee939e4b with diffusers cac, always run the original prompt on the first step 2023-01-30 14:50:57 +01:00
psychedelicious
c222cf7e64 Prevents actions from running on draft PRs 2023-01-30 22:28:05 +11:00
Eugene Brodsky
b2a3b8bbf6 (installer) fix the create_installer.sh script so it instructs the user to deactivate an active venv 2023-01-30 03:42:27 -05:00
Eugene Brodsky
11cb03f7de (installer) fall back to attempted source install if wheel not found 
if running `python3 installer/main.py` from the source distribution,
it would fail because it expected to find a wheel.

this PR tries to perform a source install by going one level up the directory
tree and checking for `pyproject.toml` and `ldm` directory entries to
confirm (to a degree) that this is an InvokeAI distribution
 2023-01-30 03:29:09 -05:00
Eugene Brodsky
6b1dc34523 (installer) improve selection of destination directory 2023-01-30 03:15:05 -05:00
Eugene Brodsky
44786b0496 (installer) improve function naming 2023-01-29 23:39:14 -05:00
Lincoln Stein
d9ed0f6005
fix documentation of huggingface cache location (#2430) 
* fix documentation of huggingface cache location

---------

Co-authored-by: Jonathan <34005131+JPPhoto@users.noreply.github.com>
 2023-01-29 20:30:50 -06:00