aboutsummaryrefslogtreecommitdiffstats
path: root/modules/textual_inversion
Commit message (Collapse)AuthorAgeFilesLines
* Updatewangshuai092024-01-311-4/+1
|
* Merge branch 'dev' into npu_supportwangshuai092024-01-301-3/+7
|\
| * Make Tensorboard a late import (it was implicitly installed by basicsr)Aarni Koskela2023-12-301-3/+7
| |
* | Add NPU Supportwangshuai092024-01-291-0/+4
|/
* remove Train/Preprocessing tab and put all its functionality into extras ↵AUTOMATIC11112023-12-022-239/+0
| | | | batch images mode
* reformat file with uniform indentationw-e-w2023-11-281-104/+106
|
* fix Auto focal point crop for opencv >= 4.8.xw-e-w2023-11-282-15/+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
* remove duplicated codeAUTOMATIC11112023-10-141-34/+40
|
* Fix preview for textual inversion trainingAngelBottomless2023-09-051-2/+2
|
* resolve some of circular import issues for kohakuAUTOMATIC11112023-08-041-1/+3
|
* textual inversion support for SDXLAUTOMATIC11112023-07-291-5/+14
|
* suppress printing TI embedding into console by defaultAUTOMATIC11112023-07-151-1/+1
|
* add textual inversion hashes to infotextAUTOMATIC11112023-07-151-1/+8
|
* Use closing() with processing classes everywhereAarni Koskela2023-07-101-2/+4
| | | | Follows up on #11569
* sync default value of process_focal_crop_entropy_weight between ui and apihunshcn2023-06-291-1/+1
|
* Merge pull request #11201 from akx/ruff-upgAUTOMATIC11112023-06-271-4/+44
|\ | | | | Upgrade Ruff to 0.0.272
| * textual_inversion/logging.py: clean up duplicate key from sets (and sort ↵Aarni Koskela2023-06-131-4/+44
| | | | | | | | them) (Ruff B033)
* | Use os.makedirs(..., exist_ok=True)Aarni Koskela2023-06-131-2/+1
|/
* Simplify a bunch of `len(x) > 0`/`len(x) == 0` style expressionsAarni Koskela2023-06-024-11/+11
|
* rename print_error to report, use it with together with package nameAUTOMATIC2023-05-311-4/+3
|
* Merge pull request #10780 from akx/image-emb-fontsAUTOMATIC11112023-05-311-8/+13
|\ | | | | Mark caption_image_overlay's textfont as deprecated; fix #10778
| * Mark caption_image_overlay's textfont as deprecated; fix #10778Aarni Koskela2023-05-281-8/+13
| |
* | Merge pull request #10803 from klimaleksus/refactoring-for-embedding-mergeAUTOMATIC11112023-05-311-6/+19
|\ \ | | | | | | Refactor EmbeddingDatabase.register_embedding() to allow unregistering
| * | Refactor EmbeddingDatabase.register_embedding() to allow unregisteringklimaleksus2023-05-281-6/+19
| |/
* / Add & use modules.errors.print_error where currently printing exception info ↵Aarni Koskela2023-05-291-6/+3
|/ | | | by hand
* Autofix Ruff W (not W605) (mostly whitespace)Aarni Koskela2023-05-113-11/+11
|
* Reindent autocrop with 4 spacesAarni Koskela2023-05-111-100/+102
|
* Deduplicate get_font codeAarni Koskela2023-05-111-7/+2
|
* suggestions and fixes from the PRAUTOMATIC2023-05-101-2/+1
|
* fixes for B007AUTOMATIC2023-05-102-6/+6
|
* ruff manual fixesAUTOMATIC2023-05-102-3/+3
|
* ruff auto fixesAUTOMATIC2023-05-101-1/+1
|
* imports cleanup for ruffAUTOMATIC2023-05-104-9/+2
|
* manual fixes for ruffAUTOMATIC2023-05-101-1/+1
|
* autofixes from ruffAUTOMATIC2023-05-101-1/+1
|
* Fix up string formatting/concatenation to f-strings where feasibleAarni Koskela2023-05-094-13/+13
|
* Merge pull request #8924 from kurilee/masterAUTOMATIC11112023-04-291-3/+7
|\ | | | | Add option "keep original size" to textual inversion images preprocess
| * Add option "keep original size" to textual inversion images preprocesskurilee2023-03-251-3/+7
| |
* | Merge pull request #9407 from GoulartNogueira/masterAUTOMATIC11112023-04-291-1/+3
|\ \ | | | | | | Fix orientation bug on preprocess
| * | Pythonic way to achieve itAndre Ubuntu2023-04-051-17/+1
| | |
| * | fix preprocess orientationAndre Ubuntu2023-04-051-1/+19
| |/
* | sort self.word_embeddings without instantiating it a new dictBrad Smith2023-04-141-3/+6
| |
* | sort embeddings by name (case insensitive)Brad Smith2023-04-081-2/+5
|/
* Fix None type error for TI modulebutaixianran2023-03-241-1/+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.
* fix for #6700AUTOMATIC2023-02-191-1/+1
|
* Add ability to choose using weighted loss or notShondoit2023-02-152-9/+19
|
* Call weighted_forward during trainingShondoit2023-02-151-1/+2
|
* Add PNG alpha channel as weight maps to data entriesShondoit2023-02-151-13/+38
|
* do not display the message for TI unless the list of loaded embeddings changedAUTOMATIC2023-01-291-3/+7
|
* add data-dir flag and set all user data directories based on itMax Audron2023-01-271-3/+2
|
generated by cgit v1.2.3 (git 2.25.1) at 2025-04-28 12:11:18 +0000