Age | Commit message (Collapse) | Author | |
---|---|---|---|
2023-08-04 | resolve some of circular import issues for kohaku | AUTOMATIC1111 | |
2023-07-29 | textual inversion support for SDXL | AUTOMATIC1111 | |
2023-07-15 | suppress printing TI embedding into console by default | AUTOMATIC1111 | |
2023-07-15 | add textual inversion hashes to infotext | AUTOMATIC1111 | |
2023-07-10 | Use closing() with processing classes everywhere | Aarni Koskela | |
Follows up on #11569 | |||
2023-06-02 | Simplify a bunch of `len(x) > 0`/`len(x) == 0` style expressions | Aarni Koskela | |
2023-05-31 | rename print_error to report, use it with together with package name | AUTOMATIC | |
2023-05-31 | Merge pull request #10803 from klimaleksus/refactoring-for-embedding-merge | AUTOMATIC1111 | |
Refactor EmbeddingDatabase.register_embedding() to allow unregistering | |||
2023-05-29 | Add & use modules.errors.print_error where currently printing exception info ↵ | Aarni Koskela | |
by hand | |||
2023-05-29 | Refactor EmbeddingDatabase.register_embedding() to allow unregistering | klimaleksus | |
2023-05-11 | Autofix Ruff W (not W605) (mostly whitespace) | Aarni Koskela | |
2023-05-10 | suggestions and fixes from the PR | AUTOMATIC | |
2023-05-10 | fixes for B007 | AUTOMATIC | |
2023-05-10 | ruff auto fixes | AUTOMATIC | |
2023-05-10 | imports cleanup for ruff | AUTOMATIC | |
2023-05-10 | autofixes from ruff | AUTOMATIC | |
2023-05-09 | Fix up string formatting/concatenation to f-strings where feasible | Aarni Koskela | |
2023-04-13 | sort self.word_embeddings without instantiating it a new dict | Brad Smith | |
2023-04-08 | sort embeddings by name (case insensitive) | Brad Smith | |
2023-03-25 | Fix None type error for TI module | butaixianran | |
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. | |||
2023-02-15 | Add ability to choose using weighted loss or not | Shondoit | |
2023-02-15 | Call weighted_forward during training | Shondoit | |
2023-01-29 | do not display the message for TI unless the list of loaded embeddings changed | AUTOMATIC | |
2023-01-25 | allow symlinks in the textual inversion embeddings folder | Alex "mcmonkey" Goodwin | |
2023-01-21 | extra networks UI | AUTOMATIC | |
rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight> | |||
2023-01-18 | add option to show/hide warnings | AUTOMATIC | |
removed hiding warnings from LDSR fixed/reworked few places that produced warnings | |||
2023-01-15 | big rework of progressbar/preview system to allow multiple users to prompts ↵ | AUTOMATIC | |
at the same time and do not get previews of each other | |||
2023-01-14 | change hash to sha256 | AUTOMATIC | |
2023-01-13 | fix a bug caused by merge | AUTOMATIC | |
2023-01-13 | Merge branch 'master' into tensorboard | AUTOMATIC1111 | |
2023-01-13 | print bucket sizes for training without resizing images #6620 | AUTOMATIC | |
fix an error when generating a picture with embedding in it | |||
2023-01-12 | Allow creation of zero vectors for TI | Shondoit | |
2023-01-11 | set descriptions | Vladimir Mandic | |
2023-01-10 | Support loading textual inversion embeddings from safetensors files | Lee Bousfield | |
2023-01-09 | make a dropdown for prompt template selection | AUTOMATIC | |
2023-01-09 | remove/simplify some changes from #6481 | AUTOMATIC | |
2023-01-09 | Merge branch 'master' into varsize | AUTOMATIC1111 | |
2023-01-08 | make it possible for extensions/scripts to add their own embedding directories | AUTOMATIC | |
2023-01-08 | skip images in embeddings dir if they have a second .preview extension | AUTOMATIC | |
2023-01-08 | Add checkbox for variable training dims | dan | |
2023-01-08 | Allow variable img size | dan | |
2023-01-07 | CLIP hijack rework | AUTOMATIC | |
2023-01-06 | rework saving training params to file #6372 | AUTOMATIC | |
2023-01-06 | Merge pull request #6372 from ↵ | AUTOMATIC1111 | |
timntorres/save-ti-hypernet-settings-to-txt-revised Save hypernet and textual inversion settings to text file, revised. | |||
2023-01-06 | allow loading embeddings from subdirectories | Faber | |
2023-01-05 | typo in TI | Kuma | |
2023-01-05 | Include model in log file. Exclude directory. | timntorres | |
2023-01-05 | Clean up ti, add same behavior to hypernetwork. | timntorres | |
2023-01-05 | Add option to save ti settings to file. | timntorres | |
2023-01-04 | Merge branch 'master' into gradient-clipping | AUTOMATIC1111 | |