Commit Graph

1097 Commits

Author SHA1 Message Date
Jason Toffaletti
fa98601bfb better error reporting for load_model 2022-08-31 22:03:50 -07:00
Jason Toffaletti
66fe110148 default full_prevision to True for mps device 2022-08-31 22:03:50 -07:00
Jason Toffaletti
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
James Reynolds
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
Lincoln Stein
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
James Reynolds
35d3f0ed90
Merge branch 'lstein:main' into main 2022-08-31 21:42:12 -06:00
blessedcoolant
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
Lincoln Stein
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
Lincoln Stein
9ad79207c2 Merge branch 'main' of github.com:lstein/stable-diffusion into main 2022-08-31 14:44:18 -04:00
Lincoln Stein
0be2351c97 Merge branch 'resolution-checker' of https://github.com/blessedcoolant/stable-diffusion into main 2022-08-31 14:43:17 -04:00
David Wager
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
_nderscore
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
Lincoln Stein
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
Kevin Gibbons
a14fd69a5a
fix progress bar in webui when using strength parameter (#254) 2022-08-31 11:28:11 -04:00
James Reynolds
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
David Ford
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
Mikhail Tishin
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
James Reynolds
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
Brent Ozar
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
Tom Elovi Spruce
4280788c18
Fix link to Mac instructions in README (#235) 2022-08-31 10:51:25 -04:00
Lincoln Stein
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
Lincoln Stein
8a2b849620 fix regression in WebGUI progress bar and WebGUI crashes, closes issue #236. Closes issue #249 2022-08-31 10:07:19 -04:00
Lincoln Stein
462a1961e4 fix infinite hang during GFPGAN duration inadvertently introduced during batch_size cleanup 2022-08-31 08:21:49 -04:00
James Reynolds
84c10346fb check if torch.backends has mps before calling it 2022-08-31 03:29:37 -06:00
Jason Toffaletti
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
Lincoln Stein
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
Lincoln Stein
5354122094
Merge branch 'main' into refactor-pngwriter-2 2022-08-31 01:24:17 -04:00
spezialspezial
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
Kevin Gibbons
d566ee092a move make_grid into image_utils 2022-08-30 22:03:53 -07:00
Kevin Gibbons
b983d61e93 tweak format of "result" event in web ui 2022-08-30 22:03:53 -07:00
Kevin Gibbons
153c93bdd4 refactor pngwriter 2022-08-30 22:03:51 -07:00
Lincoln Stein
3be1cee17c avoid crash due to dangling batch_size reference 2022-08-31 00:56:12 -04:00
Lincoln Stein
bdb0651eb2 add support for Apple hardware using MPS acceleration 2022-08-31 00:33:23 -04:00
blessedcoolant
1480ef84dc Add Resolution Checker 2022-08-31 14:54:16 +12:00
Kevin Gibbons
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
David Ford
b5565d2c82
Update .gitignore (#225)
Include log folders in git ignore.
2022-08-30 20:29:26 -04:00
David Ford
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
Lincoln Stein
d126db2413
Update README.md 2022-08-30 15:57:54 -04:00
blessedcoolant
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
Yosuke Shinya
d524e5797d
Add regression test (#136)
* Add regression test
* fix regression test with full_precision
2022-08-30 15:39:14 -04:00
Kevin Gibbons
8ca4d6542d
support progress for img2img (#215)
WebGUI shows progress bar when an initial image is provided.
2022-08-30 15:36:12 -04:00
Lincoln Stein
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
Lincoln Stein
8bf321f6ae
Merge pull request #182 from bakkot/webui-cancel
webui: support cancelation
2022-08-30 12:02:05 -04:00
Kevin Gibbons
5d13207aa6 webui: support cancelation 2022-08-30 08:55:40 -07:00
Lincoln Stein
dae2b26765 remove message about GFPGAN being required, since it is no longer displayed if GFPGAN missing 2022-08-30 09:50:39 -04:00
Lincoln Stein
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
Lincoln Stein
186d0f9d10 Merge branch 'sw-drop' of https://github.com/bakkot/stable-diffusion into bakkot-sw-drop 2022-08-30 09:17:07 -04:00
Lincoln Stein
55b448818e
Update README.md
Highlighted Colab notebook addition.
2022-08-29 23:49:42 -04:00
Lincoln Stein
b4babf7680 add a screenshot to description of command-line utility 2022-08-29 23:27:44 -04:00
Lincoln Stein
85f32752fe promote most headings by one level 2022-08-29 23:16:41 -04:00