aboutsummaryrefslogtreecommitdiffstats
path: root/modules/textual_inversion
AgeCommit message (Collapse)AuthorLines
2024-01-31Updatewangshuai09-4/+1
2024-01-30Merge branch 'dev' into npu_supportwangshuai09-3/+7
2024-01-29Add NPU Supportwangshuai09-0/+4
2023-12-30Make Tensorboard a late import (it was implicitly installed by basicsr)Aarni Koskela-3/+7
2023-12-02remove Train/Preprocessing tab and put all its functionality into extras ↵AUTOMATIC1111-239/+0
batch images mode
2023-11-28reformat file with uniform indentationw-e-w-104/+106
2023-11-28fix Auto focal point crop for opencv >= 4.8.xw-e-w-15/+18
autocrop.download_and_cache_models in opencv >= 4.8 the face detection model was updated download the base on opencv version returns the model path or raise exception
2023-10-14remove duplicated codeAUTOMATIC1111-34/+40
2023-09-05Fix preview for textual inversion trainingAngelBottomless-2/+2
2023-08-04resolve some of circular import issues for kohakuAUTOMATIC1111-1/+3
2023-07-29textual inversion support for SDXLAUTOMATIC1111-5/+14
2023-07-15suppress printing TI embedding into console by defaultAUTOMATIC1111-1/+1
2023-07-15add textual inversion hashes to infotextAUTOMATIC1111-1/+8
2023-07-10Use closing() with processing classes everywhereAarni Koskela-2/+4
Follows up on #11569
2023-06-29sync default value of process_focal_crop_entropy_weight between ui and apihunshcn-1/+1
2023-06-27Merge pull request #11201 from akx/ruff-upgAUTOMATIC1111-4/+44
Upgrade Ruff to 0.0.272
2023-06-13textual_inversion/logging.py: clean up duplicate key from sets (and sort ↵Aarni Koskela-4/+44
them) (Ruff B033)
2023-06-13Use os.makedirs(..., exist_ok=True)Aarni Koskela-2/+1
2023-06-02Simplify a bunch of `len(x) > 0`/`len(x) == 0` style expressionsAarni Koskela-11/+11
2023-05-31rename print_error to report, use it with together with package nameAUTOMATIC-4/+3
2023-05-31Merge pull request #10780 from akx/image-emb-fontsAUTOMATIC1111-8/+13
Mark caption_image_overlay's textfont as deprecated; fix #10778
2023-05-31Merge pull request #10803 from klimaleksus/refactoring-for-embedding-mergeAUTOMATIC1111-6/+19
Refactor EmbeddingDatabase.register_embedding() to allow unregistering
2023-05-29Add & use modules.errors.print_error where currently printing exception info ↵Aarni Koskela-6/+3
by hand
2023-05-29Refactor EmbeddingDatabase.register_embedding() to allow unregisteringklimaleksus-6/+19
2023-05-28Mark caption_image_overlay's textfont as deprecated; fix #10778Aarni Koskela-8/+13
2023-05-11Autofix Ruff W (not W605) (mostly whitespace)Aarni Koskela-11/+11
2023-05-11Reindent autocrop with 4 spacesAarni Koskela-100/+102
2023-05-11Deduplicate get_font codeAarni Koskela-7/+2
2023-05-10suggestions and fixes from the PRAUTOMATIC-2/+1
2023-05-10fixes for B007AUTOMATIC-6/+6
2023-05-10ruff manual fixesAUTOMATIC-3/+3
2023-05-10ruff auto fixesAUTOMATIC-1/+1
2023-05-10imports cleanup for ruffAUTOMATIC-9/+2
2023-05-10manual fixes for ruffAUTOMATIC-1/+1
2023-05-10autofixes from ruffAUTOMATIC-1/+1
2023-05-09Fix up string formatting/concatenation to f-strings where feasibleAarni Koskela-13/+13
2023-04-29Merge pull request #8924 from kurilee/masterAUTOMATIC1111-3/+7
Add option "keep original size" to textual inversion images preprocess
2023-04-29Merge pull request #9407 from GoulartNogueira/masterAUTOMATIC1111-1/+3
Fix orientation bug on preprocess
2023-04-13sort self.word_embeddings without instantiating it a new dictBrad Smith-3/+6
2023-04-08sort embeddings by name (case insensitive)Brad Smith-2/+5
2023-04-05Pythonic way to achieve itAndre Ubuntu-17/+1
2023-04-05fix preprocess orientationAndre Ubuntu-1/+19
2023-03-25Add option "keep original size" to textual inversion images preprocesskurilee-3/+7
2023-03-25Fix None type error for TI modulebutaixianran-1/+5
When user using model_name.png as a preview image, textural_inversion.py still treat it as an embeding, and didn't handle its error, just let python throw out an None type error like following: ```bash File "D:\Work\Dev\AI\stable-diffusion-webui\modules\textual_inversion\textual_inversion.py", line 155, in load_from_file name = data.get('name', name) AttributeError: 'NoneType' object has no attribute 'get' ``` With just a simple `if data:` checking as following, there will be no error, breaks nothing, and now this module can works fine with user's preview images. Old code: ```python data = extract_image_data_embed(embed_image) name = data.get('name', name) ``` New code: ```python data = extract_image_data_embed(embed_image) if data: name = data.get('name', name) else: # if data is None, means this is not an embeding, just a preview image return ``` Also, since there is no more errors on textual inversion module, from now on, extra network can set "model_name.png" as preview image for embedings.
2023-02-19fix for #6700AUTOMATIC-1/+1
2023-02-15Add ability to choose using weighted loss or notShondoit-9/+19
2023-02-15Call weighted_forward during trainingShondoit-1/+2
2023-02-15Add PNG alpha channel as weight maps to data entriesShondoit-13/+38
2023-01-29do not display the message for TI unless the list of loaded embeddings changedAUTOMATIC-3/+7
2023-01-27add data-dir flag and set all user data directories based on itMax Audron-3/+2
generated by cgit v1.2.3 (git 2.39.1) at 2025-10-07 19:31:29 +0000