fa98601bfb
better error reporting for load_model
2022-08-31 22:03:50 -07:00
66fe110148
default full_prevision to True for mps device
2022-08-31 22:03:50 -07:00
bf50ab9dd6
changes to get dream.py working on M1
...
- move all device init logic to T2I.__init__
- handle m1 specific edge case with autocast device type
- check torch.cuda.is_available before using cuda
2022-08-31 22:03:42 -07:00
70119602a0
Issue 270 fix ( #274 )
...
* check if torch.backends has mps before calling it
* Fixes issue 270
Co-authored-by: James Reynolds <magnsuviri@me.com >
2022-09-01 00:59:20 -04:00
28fe84177e
optionally scale initial image to fit box defined by width x height
...
* This functionality is triggered by the --fit option in the CLI (default
false), and by the "fit" checkbox in the WebGUI (default True)
* In addition, this commit contains a number of whitespace changes to
make the code more readable, as well as an attempt to unify the visual
appearance of info and warning messages.
2022-09-01 00:52:43 -04:00
35d3f0ed90
Merge branch 'lstein:main' into main
2022-08-31 21:42:12 -06:00
0433b3d625
Add Warning When Image Is Too Large ( #271 )
...
* Add Warning When Image Is Too Large
* fix incomprehensible formatting introduced by "blue"
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com >
2022-08-31 23:13:21 -04:00
4b560b50c2
fix AttributeError crash when running on non-CUDA systems ( #256 )
...
* fix AttributeError crash when running on non-CUDA systems; closes issue #234 and issue #250
* although this prevents dream.py script from crashing immediately on MPS systems, MPS support still very much a work in progress.
2022-08-31 16:59:27 -04:00
9ad79207c2
Merge branch 'main' of github.com:lstein/stable-diffusion into main
2022-08-31 14:44:18 -04:00
0be2351c97
Merge branch 'resolution-checker' of https://github.com/blessedcoolant/stable-diffusion into main
2022-08-31 14:43:17 -04:00
ed513397b2
Allow configuration of which SD model to use ( #263 )
...
* Allow configuration of which SD model to use
Closes https://github.com/lstein/stable-diffusion/issues/49 The syntax isn't quite the same (opting for --weights over --model), although --weights is more in-line with the existing naming convention.
This method also locks us into models in the models/ldm/stable-diffusion-v1/ directory. Personally, I'm not averse to this, although a secondary solution may be necessary if we wish to supply weights from an external directory.
* Fix typo
* Allow either filename OR filepath input for arg
This approach allows both
--weights SD13
--weights C:/StableDiffusion/models/ldm/stable-diffusion-v1/SD13.ckpt
2022-08-31 14:20:28 -04:00
c52ba1b022
feat: simplify and enhance prompt weight splitting ( #258 )
...
* feat: simplify and enhance prompt weight splitting
* fix: don't shadow the prompt variable
* feat: enable backslash-escaped colons in prompts
2022-08-31 14:00:10 -04:00
d022d0dd11
continue to display in-progress image until the post-processing is done, for better esthetics ( #255 )
2022-08-31 12:32:56 -04:00
a14fd69a5a
fix progress bar in webui when using strength parameter ( #254 )
2022-08-31 11:28:11 -04:00
0d2e6f90c8
Readme update ( #253 )
...
* check if torch.backends has mps before calling it
* Updated Mac Readme with latest debugging info
Co-authored-by: James Reynolds <magnsuviri@me.com >
2022-08-31 11:27:13 -04:00
58e3562652
Fix merging embeddings ( #226 )
...
Fixed merging embeddings based on the changes made in textual inversion. Tested and working. Inverted their logic to prioritize Stable Diffusion implementation over alternatives, but left the option for alternatives to still be used.
2022-08-31 11:24:11 -04:00
b622819051
Expose img2img strength parameter in Web UI ( #239 )
...
* Expose img2img strength parameter in Web UI
* Fix strength label id
Co-authored-by: Mikhail Tishin <michail.tishin@fayrix.com >
Co-authored-by: Kevin Gibbons https://github.com/bakkot
2022-08-31 11:18:32 -04:00
a547c33327
check if torch.backends has mps before calling it ( #245 )
...
Co-authored-by: James Reynolds <magnsuviri@me.com >
2022-08-31 10:56:38 -04:00
31b77dbaf8
Readme.md - fix hyperlink to Mac docs ( #246 )
...
The square brackets & curly brackets were mixed up.
2022-08-31 10:53:21 -04:00
4280788c18
Fix link to Mac instructions in README ( #235 )
2022-08-31 10:51:25 -04:00
146e75a1de
Merge branch 'bakkot-refactor-pngwriter-2' into main
...
This fixes regressions in the WebGUI and makes maintenance of pngwriter
easier.
2022-08-31 10:07:57 -04:00
8a2b849620
fix regression in WebGUI progress bar and WebGUI crashes, closes issue #236 . Closes issue #249
2022-08-31 10:07:19 -04:00
462a1961e4
fix infinite hang during GFPGAN duration inadvertently introduced during batch_size cleanup
2022-08-31 08:21:49 -04:00
84c10346fb
check if torch.backends has mps before calling it
2022-08-31 03:29:37 -06:00
2aa8393272
set PYTORCH_ENABLE_MPS_FALLBACK in mac environment ( #232 )
...
- this enables cpu fallback for op not yet implemented for m1 gpu
2022-08-31 02:00:40 -04:00
c83d01b369
fix hang during GFPGAN processing due to bug introduced by recent removal of batch_size arg from pngwriter
2022-08-31 01:41:15 -04:00
5354122094
Merge branch 'main' into refactor-pngwriter-2
2022-08-31 01:24:17 -04:00
64444025a9
Update simplet2i.py ( #228 )
...
Typo causing bug when preinitializing the model. Unsupported Sampler: klms, Defaulting to plms
2022-08-31 01:08:46 -04:00
d566ee092a
move make_grid into image_utils
2022-08-30 22:03:53 -07:00
b983d61e93
tweak format of "result" event in web ui
2022-08-30 22:03:53 -07:00
153c93bdd4
refactor pngwriter
2022-08-30 22:03:51 -07:00
3be1cee17c
avoid crash due to dangling batch_size reference
2022-08-31 00:56:12 -04:00
bdb0651eb2
add support for Apple hardware using MPS acceleration
2022-08-31 00:33:23 -04:00
1480ef84dc
Add Resolution Checker
2022-08-31 14:54:16 +12:00
1714816fe2
remove support for batch_size from dream.py ( #227 )
...
* remove dream.py support for batch_size
* expect to get a single image
2022-08-30 22:30:12 -04:00
b5565d2c82
Update .gitignore ( #225 )
...
Include log folders in git ignore.
2022-08-30 20:29:26 -04:00
4fad71cd8c
Training optimizations ( #217 )
...
* Optimizations to the training model
Based on the changes made in
textual_inversion I carried over the relevant changes that improve model training. These changes reduce the amount of memory used, significantly improve the speed at which training runs, and improves the quality of the results.
It also fixes the problem where the model trainer wouldn't automatically stop when it hit the set number of steps.
* Update main.py
Cleaned up whitespace
2022-08-30 15:59:32 -04:00
d126db2413
Update README.md
2022-08-30 15:57:54 -04:00
7811d20f21
Add Badges to README.md and add CHANGELOG.md ( #205 )
...
* Update README.md - Add Badges
* Add CHANGELOG.md
2022-08-30 15:40:56 -04:00
d524e5797d
Add regression test ( #136 )
...
* Add regression test
* fix regression test with full_precision
2022-08-30 15:39:14 -04:00
8ca4d6542d
support progress for img2img ( #215 )
...
WebGUI shows progress bar when an initial image is provided.
2022-08-30 15:36:12 -04:00
a51e18ea98
resize initial image to match requested width and height, preserving aspect ratio. Closes #210 . Closes #207 ( #214 )
2022-08-30 15:26:02 -04:00
8bf321f6ae
Merge pull request #182 from bakkot/webui-cancel
...
webui: support cancelation
2022-08-30 12:02:05 -04:00
5d13207aa6
webui: support cancelation
2022-08-30 08:55:40 -07:00
dae2b26765
remove message about GFPGAN being required, since it is no longer displayed if GFPGAN missing
2022-08-30 09:50:39 -04:00
713b2a03dc
Merge branch 'bakkot-sw-drop' into main
...
This adds a checkbox that shows the intermediate images fpr,omg as txt2img()
goes through its denoising steps.
2022-08-30 09:31:19 -04:00
186d0f9d10
Merge branch 'sw-drop' of https://github.com/bakkot/stable-diffusion into bakkot-sw-drop
2022-08-30 09:17:07 -04:00
55b448818e
Update README.md
...
Highlighted Colab notebook addition.
2022-08-29 23:49:42 -04:00
b4babf7680
add a screenshot to description of command-line utility
2022-08-29 23:27:44 -04:00
85f32752fe
promote most headings by one level
2022-08-29 23:16:41 -04:00
