Lincoln Stein
5e433728b5
upped max_steps in v1-finetune.yaml and fixed TI docs to address #493
2022-09-11 16:20:14 -04:00
Lincoln Stein
7708f4fb98
slight efficiency gain by using += in attention.py
2022-09-11 16:03:54 -04:00
blessedcoolant
b86a1deb00
Remove print statement styling ( #504 )
...
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
2022-09-11 15:47:12 -04:00
chromaticist
4951e66103
Adding support for .bin files from huggingface concepts ( #498 )
...
* Adding support for .bin files from huggingface concepts
* Updating documentation to include huggingface .bin info
2022-09-11 15:44:26 -04:00
Lincoln Stein
79b445b0ca
Merge branch 'development' of github.com:lstein/stable-diffusion into development
2022-09-11 15:39:38 -04:00
Lincoln Stein
a323070a4d
update requirements for new location of gfpgan
2022-09-11 15:28:57 -04:00
Lincoln Stein
f7662c1808
update requirements for changed location of gfpgan
2022-09-11 15:00:24 -04:00
Lincoln Stein
93c242c9fb
make gfpgan_model_exists flag available to web interface
2022-09-11 14:47:58 -04:00
Lincoln Stein
c7c6cd7735
Update UPSCALE.md
...
New instructions needed to accommodate fact that the ESRGAN and GFPGAN packages are now installed by environment.yaml.
2022-09-11 14:43:07 -04:00
Lincoln Stein
77ca83e103
Update CLI.md
...
Final documentation tweak.
2022-09-11 14:31:56 -04:00
Lincoln Stein
0ea145d188
Update CLI.md
...
More doc fixes.
2022-09-11 14:29:26 -04:00
Lincoln Stein
162285ae86
Update CLI.md
...
Minor documentation fix
2022-09-11 14:28:45 -04:00
Lincoln Stein
37c921dfe2
documentation enhancements
2022-09-11 14:26:41 -04:00
Lincoln Stein
4f72cb44ad
moved the notebook files into their own directory
2022-09-11 13:05:38 -04:00
Lincoln Stein
878ef2e9e0
documentation tweaks
2022-09-11 12:58:06 -04:00
Lincoln Stein
4923118610
Merge branch 'development' of github.com:lstein/stable-diffusion into development
2022-09-11 12:51:25 -04:00
Dominic Letz
defafc0e8e
Enable upscaling on m1 ( #474 )
2022-09-11 12:51:01 -04:00
Lincoln Stein
16f6a6731d
install GFPGAN inside SD repository in order to fix 'dark cast' issue #169
2022-09-11 12:47:26 -04:00
Armando C. Santisbon
19fb66f3d5
Add comments on next steps
2022-09-11 11:03:33 -05:00
blessedcoolant
0881d429f2
Docs Update ( #466 )
...
Authored-by: @blessedcoolant
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
2022-09-11 11:52:43 -04:00
Gérald LONLAS
9a29d442b4
Revert "Add 3x Upscale option on the Web UI ( #442 )" ( #488 )
...
This reverts commit f8a540881c
2022-09-11 11:23:18 -04:00
Lincoln Stein
d301836fbd
can select prior output for init_img using -1, -2, etc
2022-09-11 10:52:19 -04:00
Armando C. Santisbon
da95729d90
Refactor docker build and move docker assets to their own folder
2022-09-11 09:47:54 -05:00
Lincoln Stein
70aa674e9e
merge PR #495 - keep using float16 in ldm.modules.attention
2022-09-11 10:34:06 -04:00
Peter Baylies
737a97c898
Merge branch 'development' into development
2022-09-11 10:30:23 -04:00
Lincoln Stein
8748370f44
negative -S indexing recovers correct previous seed; closes issue #476
2022-09-11 10:22:32 -04:00
Lincoln Stein
839e30e4b8
improve CUDA VRAM monitoring
...
extra check that device==cuda before getting VRAM stats
2022-09-11 10:10:24 -04:00
Armando C. Santisbon
e21938c12d
Remove unnecesary chmod from Dockerfile to avoid bloating
2022-09-11 02:04:11 -05:00
Armando C. Santisbon
eeff8e9033
[Documentation] Add +x permissions to miniconda installer
2022-09-10 22:45:08 -05:00
Armando C. Santisbon
336e16ef85
[Documentation] Fix typo
2022-09-10 19:31:39 -05:00
Armando C. Santisbon
eceb7d2b54
[Documentation] Clarify path to use
2022-09-10 18:52:12 -05:00
Armando C. Santisbon
9775a3502c
Fix documentation link
2022-09-10 15:29:44 -05:00
Armando C. Santisbon
f240e878e5
Merge branch 'docker-apple-silicon'
2022-09-10 14:41:11 -05:00
Mihai
529fc57f2b
~7% speedup (1.57 to 1.69it/s) from switch to += in ldm.modules.attention. ( #482 )
...
Tested on 8GB eGPU nvidia setup so YMMV.
512x512 output, max VRAM stays same.
2022-09-10 14:07:12 -05:00
Armando C. Santisbon
0ca9d1f228
Merge branch 'lstein:main' into main
2022-09-10 14:05:25 -05:00
Armando C. Santisbon
b656d333de
Add entrypoint and update documentation
2022-09-10 13:58:07 -05:00
Armando C. Santisbon
7136603604
Ignore Anaconda/Miniconda installer used during Docker build
2022-09-10 13:58:07 -05:00
Armando C. Santisbon
5cbea51f31
Initial version of Dockerfile and entreypoint
2022-09-10 13:58:07 -05:00
Armando C. Santisbon
2cf8de9234
Add entrypoint and update documentation
2022-09-10 13:56:18 -05:00
Armando C. Santisbon
f9239af7dc
Ignore Anaconda/Miniconda installer used during Docker build
2022-09-10 12:42:05 -05:00
Armando C. Santisbon
97c0c4bfe8
Initial version of Dockerfile and entreypoint
2022-09-10 12:38:31 -05:00
Peter Baylies
c6be8f320d
Merge branch 'development' into development
2022-09-10 10:31:32 -04:00
tildebyte
bfb2781279
fix(readme): add note about updating env via conda ( #475 )
2022-09-10 10:15:56 -04:00
Lincoln Stein
5c43988862
reduce VRAM memory usage by half during model loading
...
* This moves the call to half() before model.to(device) to avoid GPU
copy of full model. Improves speed and reduces memory usage dramatically
* This fix contributed by @mh-dm (Mihai)
2022-09-10 10:02:43 -04:00
Mihai
62863ac586
~7% speedup (1.57 to 1.69it/s) from switch to += in ldm.modules.attention. ( #482 )
...
Tested on 8GB eGPU nvidia setup so YMMV.
512x512 output, max VRAM stays same.
2022-09-10 09:58:07 -04:00
Lincoln Stein
99122708ca
Merge branch 'development' of github.com:lstein/stable-diffusion into development
2022-09-10 09:54:34 -04:00
Lincoln Stein
817c4a26de
remove -F option from normalized prompt; closes #483
2022-09-10 09:54:26 -04:00
Lincoln Stein
ecc6b75a3e
remove -F option from normalized prompt
2022-09-10 09:53:27 -04:00
Peter Baylies
bf707d9e75
* Use the right graphic.
2022-09-10 08:11:14 -04:00
Peter Baylies
db52991b9d
Update README.md
...
Add descriptions for truncation and perlin noise, and link to a graphic.
2022-09-10 08:10:58 -04:00
