0b262802b8
add gradient settings to training settings log files
2023-01-12 17:31:05 -08:00
6c88eaed4f
Add script callback for fixing infotext parameters
2023-01-12 13:50:09 -08:00
88416ab5ff
Fix extension parameters not being saved to last used parameters
2023-01-12 13:46:59 -08:00
d7aec59c4e
Merge pull request #6667 from Shondoit/zero-vector-ti
...
Allow creation of zero vectors for TI
2023-01-12 22:05:10 +03:00
6ffefdcc9f
fix js errors when restarting UI
2023-01-12 19:47:44 +03:00
5623a3e7b1
fix send to inpaint sending you to wrong place
2023-01-12 19:47:33 +03:00
d48dcbd2b2
Add zero vector feature to hints.js
...
Also add the note that some tokens might be skipped. Not everyone is aware of this.
2023-01-12 09:53:35 +01:00
d52a80f7f7
Allow creation of zero vectors for TI
2023-01-12 09:22:29 +01:00
0b8911d883
img2img UI rework: obsolete --gradio-img2img-tool --gradio-inpaint-tool and always show all tools each in own tab
2023-01-11 20:33:24 +03:00
590ff5ce5b
Merge pull request #6647 from vladmandic/update-progress-api
...
add textinfo to progress api response
2023-01-11 19:06:08 +03:00
6d7f3d1072
Merge pull request #6648 from vladmandic/progress-description
...
Set TQDM progress bar and state textinfo description
2023-01-11 19:04:54 +03:00
97ff69eff3
Merge pull request #6628 from catboxanon/fix/alternating-words-emphasis
...
Fix prompt parser default step transformer
2023-01-11 18:56:24 +03:00
4bd490727e
fix for an error caused by skipping initialization, for realsies this time: TypeError: expected str, bytes or os.PathLike object, not NoneType
2023-01-11 18:54:13 +03:00
3f43d8a966
set descriptions
2023-01-11 10:28:55 -05:00
39ea251945
add textinfo to progress response
2023-01-11 10:23:51 -05:00
0b38b72d31
Remove compat option for prompt parser
2023-01-11 09:01:37 -05:00
ab388d6f8b
Remove compat option check for prompt parser
2023-01-11 08:59:47 -05:00
035f2af050
Merge branch 'AUTOMATIC1111:master' into fix/alternating-words-emphasis
2023-01-11 08:58:43 -05:00
45a8b758a7
Merge pull request #6635 from demiurge-ash/patch-1
...
Fix keyboard navigation in modal image viewer
2023-01-11 12:00:15 +03:00
b202714b65
Fix keyboard navigation in modal image viewer
2023-01-11 11:41:50 +03:00
1a23dc32ac
possible fix for fallback for fast model creation from config, attempt 2
2023-01-11 10:34:36 +03:00
4fdacd31e4
possible fix for fallback for fast model creation from config
2023-01-11 10:24:56 +03:00
954091697f
add an option to copy config from one of models in checkpoint merger
2023-01-11 09:10:07 +03:00
3e20244b0f
Merge pull request #6625 from PlasmaPower/textual-inversion-safetensors
...
Support loading textual inversion embeddings from safetensors files
2023-01-11 08:21:22 +03:00
9757c0b3b2
Merge pull request #6633 from space-nuko/expose-xy-grid-to-extensions
...
Expose XY Grid module to extensions
2023-01-11 08:06:41 +03:00
37a2301121
Expose the compiled class module of scripts to extensions
2023-01-10 20:30:09 -08:00
7e45fba55b
Fix prompt parser default step transformer w/ test
2023-01-10 21:47:03 -05:00
5830095b73
Add old prompt parser compat option
2023-01-10 21:43:24 -05:00
f9706acf43
Support loading textual inversion embeddings from safetensors files
2023-01-10 18:40:34 -07:00
9cfd10cdef
repair #6612
2023-01-11 01:27:00 +03:00
6be644fa04
Enable batch_size>1 for mixed-sized training
2023-01-11 05:31:58 +08:00
29fb532764
change color selector in settings to be part of form
2023-01-10 23:47:07 +03:00
2bd2b8b7cf
Merge pull request #6612 from mezotaken/master
...
Make VENV environment variable accept absolute path instead of relative path.
2023-01-10 23:45:34 +03:00
e2c8584f75
make VENV envvar accept absolute path instead of relative
2023-01-10 22:26:49 +03:00
50fb20cedc
Merge branch 'disable_initialization'
2023-01-10 19:11:47 +03:00
0f8603a559
add support for transformers==4.25.1
...
add fallback for when quick model creation fails
2023-01-10 17:46:59 +03:00
ce3f639ec8
add more stuff to ignore when creating model from config
...
prevent .vae.safetensors files from being listed as stable diffusion models
2023-01-10 16:51:04 +03:00
a0ef416aa7
Merge pull request #6596 from mezotaken/master
...
Fix issues with testing process
2023-01-10 15:14:03 +03:00
0c3feb202c
disable torch weight initialization and CLIP downloading/reading checkpoint to speedup creating sd model from config
2023-01-10 14:08:29 +03:00
76a21b9626
clear envvar, add assertion
2023-01-10 12:47:52 +03:00
ef75c98053
Split history ui.py to ui_progress.py
2023-01-10 12:29:45 +03:00
54dd5d6634
Split history ui.py to ui_progress.py
2023-01-10 11:54:49 +03:00
f9c2147dfb
Split history ui.py to ui_progress.py
2023-01-10 11:54:49 +03:00
27ea6949d3
Split history ui.py to ui_progress.py
2023-01-10 11:54:48 +03:00
e9f8292a3a
Split history ui.py to ui_progress.py
2023-01-10 11:54:48 +03:00
7ec275fae7
Merge pull request #6590 from aria1th/varaible-dropout-rate-rework
...
Variable dropout rate
2023-01-10 11:29:26 +03:00
a4a5475cfa
Variable dropout rate
...
Implements variable dropout rate from #4549
Fixes hypernetwork multiplier being able to modified during training, also fixes user-errors by setting multiplier value to lower values for training.
Changes function name to match torch.nn.module standard
Fixes RNG reset issue when generating previews by restoring RNG state
2023-01-10 14:56:57 +09:00
bd4587d2f5
Merge pull request #6578 from vladmandic/fix-model-load
...
allow model load if previous model failed
2023-01-10 08:22:44 +03:00
12dc8e09ca
Merge pull request #6584 from vladmandic/fix-get-memory
...
follow-up for pr #6466 to relax response type check enforcement in get_memory
2023-01-10 08:18:39 +03:00
2275f130bf
relax reponse type check enforcement
2023-01-09 21:23:58 -05:00
Josh R