aboutsummaryrefslogtreecommitdiff
path: root/modules/textual_inversion/textual_inversion.py
AgeCommit message (Collapse)Author
2023-05-10suggestions and fixes from the PRAUTOMATIC
2023-05-10fixes for B007AUTOMATIC
2023-05-10ruff auto fixesAUTOMATIC
2023-05-10imports cleanup for ruffAUTOMATIC
2023-05-10autofixes from ruffAUTOMATIC
2023-05-09Fix up string formatting/concatenation to f-strings where feasibleAarni Koskela
2023-04-13sort self.word_embeddings without instantiating it a new dictBrad Smith
2023-04-08sort embeddings by name (case insensitive)Brad Smith
2023-03-25Fix None type error for TI modulebutaixianran
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.
2023-02-15Add ability to choose using weighted loss or notShondoit
2023-02-15Call weighted_forward during trainingShondoit
2023-01-29do not display the message for TI unless the list of loaded embeddings changedAUTOMATIC
2023-01-25allow symlinks in the textual inversion embeddings folderAlex "mcmonkey" Goodwin
2023-01-21extra networks UIAUTOMATIC
rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight>
2023-01-18add option to show/hide warningsAUTOMATIC
removed hiding warnings from LDSR fixed/reworked few places that produced warnings
2023-01-15big rework of progressbar/preview system to allow multiple users to prompts ↵AUTOMATIC
at the same time and do not get previews of each other
2023-01-14change hash to sha256AUTOMATIC
2023-01-13fix a bug caused by mergeAUTOMATIC
2023-01-13Merge branch 'master' into tensorboardAUTOMATIC1111
2023-01-13print bucket sizes for training without resizing images #6620AUTOMATIC
fix an error when generating a picture with embedding in it
2023-01-12Allow creation of zero vectors for TIShondoit
2023-01-11set descriptionsVladimir Mandic
2023-01-10Support loading textual inversion embeddings from safetensors filesLee Bousfield
2023-01-09make a dropdown for prompt template selectionAUTOMATIC
2023-01-09remove/simplify some changes from #6481AUTOMATIC
2023-01-09Merge branch 'master' into varsizeAUTOMATIC1111
2023-01-08make it possible for extensions/scripts to add their own embedding directoriesAUTOMATIC
2023-01-08skip images in embeddings dir if they have a second .preview extensionAUTOMATIC
2023-01-08Add checkbox for variable training dimsdan
2023-01-08Allow variable img sizedan
2023-01-07CLIP hijack reworkAUTOMATIC
2023-01-06rework saving training params to file #6372AUTOMATIC
2023-01-06Merge pull request #6372 from ↵AUTOMATIC1111
timntorres/save-ti-hypernet-settings-to-txt-revised Save hypernet and textual inversion settings to text file, revised.
2023-01-06allow loading embeddings from subdirectoriesFaber
2023-01-05typo in TIKuma
2023-01-05Include model in log file. Exclude directory.timntorres
2023-01-05Clean up ti, add same behavior to hypernetwork.timntorres
2023-01-05Add option to save ti settings to file.timntorres
2023-01-04Merge branch 'master' into gradient-clippingAUTOMATIC1111
2023-01-04use shared function from processing for creating dummy mask when training ↵AUTOMATIC
inpainting model
2023-01-04fix the mergeAUTOMATIC
2023-01-04Merge branch 'master' into inpaint_textual_inversionAUTOMATIC1111
2023-01-04Merge pull request #6253 from Shondoit/ti-optimAUTOMATIC1111
Save Optimizer next to TI embedding
2023-01-03add job info to modulesVladimir Mandic
2023-01-03Save Optimizer next to TI embeddingShondoit
Also add check to load only .PT and .BIN files as embeddings. (since we add .optim files in the same directory)
2023-01-02feat(api): return more data for embeddingsPhilpax
2023-01-02fix the issue with training on SD2.0AUTOMATIC
2022-12-31changed embedding accepted shape detection to use existing code and support ↵AUTOMATIC
the new alt-diffusion model, and reformatted messages a bit #6149
2022-12-31validate textual inversion embeddingsVladimir Mandic
2022-12-24fix F541 f-string without any placeholdersYuval Aboulafia
generated by cgit v1.2.1 (git 2.18.0) at 2025-05-29 12:17:30 +0000