Commit Graph

156 Commits

Author SHA1 Message Date
Aarni Koskela 49a55b410b Autofix Ruff W (not W605) (mostly whitespace) 2023-05-11 20:29:11 +03:00
AUTOMATIC 3ec7b705c7 suggestions and fixes from the PR 2023-05-10 21:21:32 +03:00
AUTOMATIC a5121e7a06 fixes for B007 2023-05-10 11:37:18 +03:00
AUTOMATIC 028d3f6425 ruff auto fixes 2023-05-10 11:05:02 +03:00
AUTOMATIC f741a98bac imports cleanup for ruff 2023-05-10 08:43:42 +03:00
AUTOMATIC 762265eab5 autofixes from ruff 2023-05-10 07:52:45 +03:00
Aarni Koskela 3ba6c3c83c Fix up string formatting/concatenation to f-strings where feasible 2023-05-09 22:25:39 +03:00
Brad Smith dab5002c59
sort self.word_embeddings without instantiating it a new dict 2023-04-13 23:19:10 -04:00
Brad Smith 27b9ec60e4
sort embeddings by name (case insensitive) 2023-04-08 15:58:00 -04:00
butaixianran 803d44c474
Fix None type error for TI module
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.
2023-03-25 02:05:00 +08:00
Shondoit edb10092de Add ability to choose using weighted loss or not 2023-02-15 10:03:59 +01:00
Shondoit bc50936745 Call weighted_forward during training 2023-02-15 10:03:59 +01:00
AUTOMATIC aa6e55e001 do not display the message for TI unless the list of loaded embeddings changed 2023-01-29 11:53:05 +03:00
Alex "mcmonkey" Goodwin e179b6098a allow symlinks in the textual inversion embeddings folder 2023-01-25 08:48:40 -08:00
AUTOMATIC 40ff6db532 extra networks UI
rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight>
2023-01-21 08:36:07 +03:00
AUTOMATIC 924e222004 add option to show/hide warnings
removed hiding warnings from LDSR
fixed/reworked few places that produced warnings
2023-01-18 23:04:24 +03:00
AUTOMATIC d8b90ac121 big rework of progressbar/preview system to allow multiple users to prompts at the same time and do not get previews of each other 2023-01-15 18:51:04 +03:00
AUTOMATIC a95f135308 change hash to sha256 2023-01-14 09:56:59 +03:00
AUTOMATIC 82725f0ac4 fix a bug caused by merge 2023-01-13 15:04:37 +03:00
AUTOMATIC1111 9cd7716753
Merge branch 'master' into tensorboard 2023-01-13 14:57:38 +03:00
AUTOMATIC a176d89487 print bucket sizes for training without resizing images #6620
fix an error when generating a picture with embedding in it
2023-01-13 14:32:15 +03:00
Shondoit d52a80f7f7 Allow creation of zero vectors for TI 2023-01-12 09:22:29 +01:00
Vladimir Mandic 3f43d8a966
set descriptions 2023-01-11 10:28:55 -05:00
Lee Bousfield f9706acf43
Support loading textual inversion embeddings from safetensors files 2023-01-10 18:40:34 -07:00
AUTOMATIC 1fbb6f9ebe make a dropdown for prompt template selection 2023-01-09 23:35:40 +03:00
AUTOMATIC 43bb5190fc remove/simplify some changes from #6481 2023-01-09 22:52:23 +03:00
AUTOMATIC1111 18c001792a
Merge branch 'master' into varsize 2023-01-09 22:45:39 +03:00
AUTOMATIC 085427de0e make it possible for extensions/scripts to add their own embedding directories 2023-01-08 09:37:33 +03:00
AUTOMATIC a0c87f1fdf skip images in embeddings dir if they have a second .preview extension 2023-01-08 08:52:26 +03:00
dan 669fb18d52 Add checkbox for variable training dims 2023-01-08 02:31:40 +08:00
dan 448b9cedab Allow variable img size 2023-01-08 02:14:36 +08:00
AUTOMATIC 79e39fae61 CLIP hijack rework 2023-01-07 01:46:13 +03:00
AUTOMATIC 683287d87f rework saving training params to file #6372 2023-01-06 08:52:06 +03:00
AUTOMATIC1111 88e01b237e
Merge pull request #6372 from timntorres/save-ti-hypernet-settings-to-txt-revised
Save hypernet and textual inversion settings to text file, revised.
2023-01-06 07:59:44 +03:00
Faber 81133d4168
allow loading embeddings from subdirectories 2023-01-06 03:38:37 +07:00
Kuma fda04e620d
typo in TI 2023-01-05 18:44:19 +01:00
timntorres b6bab2f052 Include model in log file. Exclude directory. 2023-01-05 09:14:56 -08:00
timntorres b85c2b5cf4 Clean up ti, add same behavior to hypernetwork. 2023-01-05 08:14:38 -08:00
timntorres eea8fc40e1 Add option to save ti settings to file. 2023-01-05 07:24:22 -08:00
AUTOMATIC1111 eeb1de4388
Merge branch 'master' into gradient-clipping 2023-01-04 19:56:35 +03:00
AUTOMATIC 525cea9245 use shared function from processing for creating dummy mask when training inpainting model 2023-01-04 17:58:07 +03:00
AUTOMATIC 184e670126 fix the merge 2023-01-04 17:45:01 +03:00
AUTOMATIC1111 da5c1e8a73
Merge branch 'master' into inpaint_textual_inversion 2023-01-04 17:40:19 +03:00
AUTOMATIC1111 7bbd984dda
Merge pull request #6253 from Shondoit/ti-optim
Save Optimizer next to TI embedding
2023-01-04 14:09:13 +03:00
Vladimir Mandic 192ddc04d6
add job info to modules 2023-01-03 10:34:51 -05:00
Shondoit bddebe09ed Save Optimizer next to TI embedding
Also add check to load only .PT and .BIN files as embeddings. (since we add .optim files in the same directory)
2023-01-03 13:30:24 +01:00
Philpax c65909ad16 feat(api): return more data for embeddings 2023-01-02 12:21:48 +11:00
AUTOMATIC 311354c0bb fix the issue with training on SD2.0 2023-01-02 00:38:09 +03:00
AUTOMATIC bdbe09827b changed embedding accepted shape detection to use existing code and support the new alt-diffusion model, and reformatted messages a bit #6149 2022-12-31 22:49:09 +03:00
Vladimir Mandic f55ac33d44
validate textual inversion embeddings 2022-12-31 11:27:02 -05:00