2c5ca706a7
Remove no longer necessary parts and add vae_file safeguard
2022-11-19 12:01:41 +07:00
0663706d44
Option to use selected VAE as default fallback instead of primary option
2022-11-19 11:49:06 +07:00
028b67b635
Use underscore naming for "private" functions in sd_vae
2022-11-19 11:47:54 +07:00
9fdc343dca
Fix model caching requiring deepcopy
2022-11-19 11:44:37 +07:00
c7be83bf02
Misc
...
Misc
2022-11-19 11:44:37 +07:00
abc1e79a5d
Fix base VAE caching was done after loading VAE, also add safeguard
2022-11-19 11:41:41 +07:00
8ab4927452
Fix model wasn't restored even when choosing "None"
2022-11-19 11:41:21 +07:00
694611cbd8
Apply suggestions from code review
...
Use last version of setup-python action
Remove unnecesarry multicommand from run
Remove current directory from artifact paths
Co-authored-by: Margen67 <Margen67@users.noreply.github.com>
2022-11-19 00:56:08 +03:00
17e4432820
cleanly undo circular hijack #4818
2022-11-18 21:22:55 +11:00
c8c40c8a64
Add interrupt button to preprocessing
2022-11-17 18:05:29 -08:00
a5106a7cdc
Remove extra .to(device)
2022-11-17 00:08:45 -05:00
abfa22c16f
Revert "MPS Upscalers Fix"
...
This reverts commit 768b95394a8500da639b947508f78296524f1836.
2022-11-17 00:08:21 -05:00
9bbe1e3c2e
Fix unbounded prompt growth scripts that loop
2022-11-16 19:19:00 +02:00
72b52fbb77
add css override
2022-11-16 13:08:03 +09:00
8f2ff861d3
feat: add http basic authentication for api
2022-11-15 16:12:34 +08:00
3405acc6a4
Give --server-name priority over --listen and add check for --server-name in addition to --share and --listen
2022-11-14 14:07:13 -06:00
a071079000
Use empty model as CLIP weights
2022-11-14 19:22:06 +03:00
4a35c3744c
remove test requiring codeformers
2022-11-14 18:57:14 +03:00
9e4f68acad
Stop exporting cl args and upload stdout and stderr as artifacts
2022-11-14 18:40:15 +03:00
5808241dd7
Use 80 port on launch
2022-11-14 15:14:52 +03:00
7416ac8d3c
Use localhost with 80 port, count errors as well
2022-11-14 14:55:39 +03:00
0646040667
Propagate test error and try it without localhost
2022-11-14 14:36:07 +03:00
3ffc1c6cee
skip cuda test
2022-11-14 13:45:21 +03:00
93d6c0209a
Tests separated for github-actions CI
2022-11-14 13:39:22 +03:00
40ae95d532
Fix retrieving value for 'x/y plot' script.
2022-11-14 18:05:59 +10:00
9a1aff645a
resolve [name] after resolving [filewords] in training
2022-11-13 13:49:28 -06:00
671c0e42b4
Fix docker tmp/ and extensions/ handling for docker. might also work for symlinks
2022-11-13 13:39:41 -05:00
6fa891b934
Add 'Inpainting strength' to the 'generation_params' dictionary of 'infotext' which is saved into the 'params.txt' or png chunks.
...
Value appears only if 'Denoising strength' appears too.
2022-11-14 00:25:38 +10:00
084cf04390
Fix env var names
2022-11-12 22:41:22 -05:00
d20dbe47e0
fix the model name error of Real-ESRGAN in the opts default value
2022-11-13 10:31:03 +08:00
d671d1d45d
Fix: `error: Your local changes to the following files would be overwritten by merge` when run `pull()` method,
...
because WSL2 Docker set 755 file permissions instead of 644, this results to the error.
Updated `Extension` class: replaced `pull()` with `fetch_and_reset_hard()` method.
Updated `apply_and_restart()` function: replaced `ext.pull()` with `ext.fetch_and_reset_hard()` function.
2022-11-12 21:44:42 +03:00
007f4f7314
Tests cleaned up
2022-11-12 15:12:15 +03:00
f4a488f585
Set device for facelib/facexlib and gfpgan
...
* FaceXLib/FaceLib doesn't pass the device argument to RetinaFace but instead chooses one itself and sets it to a global - in order to use a device other than its internally chosen default it is necessary to manually replace the default value
* The GFPGAN constructor needs the device argument to work with MPS or a CUDA device ID that differs from the default
2022-11-12 03:34:13 -05:00
98947d173e
run installers for newly installed extensions
2022-11-12 11:11:47 +03:00
a1a376331c
make existing script loading and new preload code use same code for loading modules
...
limit extension preload scripts to just one file named preload.py
2022-11-12 10:56:06 +03:00
e5690d0bf2
Merge pull request #4488 from d8ahazard/ExtensionPreload
...
Add option to preload extensions
2022-11-12 10:29:15 +03:00
0ab0a50f9a
change formatting to match the main program in devices.py
2022-11-12 10:00:49 +03:00
c62d17aee3
use the new devices.has_mps() function in register_buffer for DDIM/PLMS fix for OSX
2022-11-12 10:00:22 +03:00
526f0aa556
Merge pull request #4623 from fumiama/mps
...
Fix wrong mps fallback
2022-11-12 09:51:33 +03:00
1130d5df66
Update devices.py
2022-11-12 11:09:28 +08:00
76ab31e188
Fix wrong mps selection below MasOS 12.3
2022-11-12 11:02:40 +08:00
7ba3923d5b
move DDIM/PLMS fix for OSX out of the file with inpainting code.
2022-11-11 18:20:18 +03:00
bb2e2c82ce
Merge pull request #4233 from thesved/patch-1
...
Make DDIM and PLMS work on Mac OS
2022-11-11 18:01:58 +03:00
b8a2e38758
Merge pull request #4543 from tong-zeng/master
...
Fix a bug in list_files_with_name
2022-11-11 18:00:13 +03:00
6165f07e74
Merge branch 'master' into patch-1
2022-11-11 21:14:10 +07:00
e666220ee4
Merge pull request #4514 from cluder/4448_fix_ckpt_cache
...
#4448 fix checkpoint cache usage
2022-11-11 16:04:17 +03:00
6a2044f566
Merge pull request #4563 from JingShing/master
...
Add username and password in ngrok
2022-11-11 15:57:24 +03:00
ec95ced6fb
Merge pull request #4573 from liamkerr/4415-update-generation-info
...
4415 update generation info
2022-11-11 15:51:14 +03:00
73776907ec
Merge pull request #4117 from TinkTheBoush/master
...
Adding optional tag shuffling for training
2022-11-11 15:46:20 +03:00
6585cba200
Merge pull request #4395 from snowmeow2/master
...
Add DeepDanbooru to the interrogate API
2022-11-11 15:41:30 +03:00
Muhammad Rizqi Nur