bb75174f4a
Merge branch 'development' into development
2022-09-20 08:43:25 -04:00
27b238999f
Use model_url instead of model_path for gfpgan and CodeFormer. Fixes lstein/stable-diffusion#678
2022-09-20 07:15:54 -04:00
8c72da3643
Merge remote-tracking branch 'upstream/development' into development
2022-09-19 15:48:22 -04:00
50d607ffea
Merge branch 'development' of github.com:lstein/stable-diffusion into development
2022-09-19 12:35:03 -04:00
57577401bd
Fixes metadata_loads() #686
2022-09-19 12:33:45 -04:00
58c63fe339
Merge branch 'development' of github.com:psychedelicious/stable-diffusion into psychedelicious-development
2022-09-19 12:27:42 -04:00
37c44ced1d
Merge branch 'development' into development
2022-09-19 07:22:03 -04:00
682d74754c
Fixes metadata_loads() #686
2022-09-18 22:41:39 -04:00
dc024845cf
Merge branch 'development' into development
2022-09-18 22:34:00 -04:00
1f29cb1dc1
Merge remote-tracking branch 'upstream/development' into development
2022-09-19 12:28:09 +10:00
6bf19cd897
Updating with evergreen Discord invite ( #635 )
...
* Update to add Adobe Photoshop Guide for inpainting (#617 )
* updating with Adobe instructions & assets
* Assets for Adobe guide
* correcting paths
* update Readme with evergreen discord invite link
* discord image asset uploaded
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com >
2022-09-18 21:30:21 -04:00
2743e17588
Fix token display when using -t
...
Add true weight used for subprompt
2022-09-18 21:25:27 -04:00
f0b500fba8
Fixes metadata implementation #686
2022-09-18 21:24:29 -04:00
aaec6baeca
Add .gitkeep to the weights folder
2022-09-18 20:35:05 -04:00
61611d7d0d
Fixes metadata implementation #686
2022-09-19 10:07:31 +10:00
73154a25d4
Merge remote-tracking branch 'upstream/development' into development
2022-09-19 10:06:43 +10:00
f4a275d1b5
* Tweaked frontend options; rebuilt frontend.
2022-09-18 19:21:59 -04:00
3692f223e1
Merge branch 'development' into development
2022-09-18 18:58:04 -04:00
1e8e5245eb
CLI writes prompt string metadata in same format as web server
2022-09-18 15:08:56 -04:00
4f926fc470
Merge branch 'development' into development
2022-09-18 15:04:01 -04:00
a0a9b12daf
fix(scripts): dream.py typo ( #675 )
...
Signed-off-by: Ben Alkov <ben.alkov@gmail.com >
Signed-off-by: Ben Alkov <ben.alkov@gmail.com >
2022-09-18 15:03:11 -04:00
f3292a6953
Implement CodeFormer Face Restoration ( #669 )
...
* Implement CodeFormer Face Restoration
* fix codeformer model destination path
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com >
2022-09-18 15:01:05 -04:00
062f3e8f31
Gfpgan download fix ( #655 )
...
* restore ability to save files to directories named after prompt
* don't download gfpgan model file if it exists
- Fixes #647
2022-09-18 14:42:43 -04:00
c98ade9b25
Merge branch 'development' into development
2022-09-18 12:35:28 -04:00
3c4c4d71c9
VARIATIONS.md - fix typo in formatting ( #664 )
...
A beginning line for a code section was left out.
2022-09-18 09:50:54 -04:00
ea2b0828d8
Documentation for negative prompts ( #668 )
...
Documentation for pull lstein#661, and splits prompt docs into a separate file.
2022-09-18 09:50:19 -04:00
045aa7a9a3
Support color correction for img2img and inpainting ( #613 )
...
* Support color correction for img2img and inpainting, avoiding the shift to magenta seen when running images through img2img repeatedly.
* Fix docs for color correction
* add --init_color to prompt reconstruction
* For best results, the --init_color option should point to the *very first* image used in the sequence of img2img operations. Otherwise color correction will skew towards cyan.
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com >
2022-09-18 09:47:57 -04:00
d478a241a8
Merge branch 'development' into development
2022-09-18 09:20:13 -04:00
0a4397094e
Negative / Unconditioned Prompts ( #661 )
...
Co-Authored-By: rabidcopy <8052832+rabidcopy@users.noreply.github.com >
Co-authored-by: rabidcopy <8052832+rabidcopy@users.noreply.github.com >
2022-09-18 09:08:30 -04:00
0b786f61cc
Merge branch 'development' into development
2022-09-18 08:54:22 -04:00
b68cb521ba
restore ability to save files to directories named after prompt ( #654 )
2022-09-18 08:37:08 -04:00
e1f0ee819d
Minor bug fix
2022-09-18 21:13:42 +10:00
09bf6dd7c1
Merge remote-tracking branch 'upstream/development' into development
2022-09-18 18:44:40 +10:00
6e927acd58
Improves state/API code structure, formatting, etc
2022-09-18 17:33:09 +10:00
ef6609abcb
Updates frontend/README
2022-09-18 10:45:06 +10:00
2f93418095
Merge branch 'development' into development
2022-09-17 20:35:48 -04:00
9bcb0dff96
feat(docs): readme - add discord server badge/link ( #644 )
...
Signed-off-by: Ben Alkov <ben.alkov@gmail.com >
Signed-off-by: Ben Alkov <ben.alkov@gmail.com >
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com >
2022-09-17 18:28:26 -04:00
f84372efd8
fix(doc): readme - more meaningful CI links from badges ( #645 )
...
Signed-off-by: Ben Alkov <ben.alkov@gmail.com >
Signed-off-by: Ben Alkov <ben.alkov@gmail.com >
2022-09-17 18:26:09 -04:00
071f65a892
Enable even larger images with one simple torch.nn.functional.silu import ( #653 )
...
Fixes:
File "stable-diffusion/ldm/modules/diffusionmodules/model.py", line 37, in nonlinearity
return x*torch.sigmoid(x)
RuntimeError: CUDA out of memory. Tried to allocate 1.56 GiB [..]
Now up to 1536x1280 is possible on 8GB VRAM.
Also remove unused SiLU class.
2022-09-17 18:03:52 -04:00
e30827e19b
Adds enter keydown > generate
2022-09-18 06:13:27 +10:00
ad292b095d
minor fix to ldm.dream.args
...
- If no list of seeds is provided to metadata_dumps(), then the contents
of the Args object's seed attribute are used.
2022-09-17 13:44:39 -04:00
d8685ad66b
Merge branch 'development' of github.com:lstein/stable-diffusion into development
2022-09-17 13:29:21 -04:00
239f41f3e0
add sd-metadata metadata_loads() and metadata_dumps() functions
2022-09-17 13:28:37 -04:00
e0951f28cf
Refactor attention.CrossAttention to remove duplicate code and apply optimizations
...
Apply ~6% speedup by moving * self.scale to earlier on a smaller tensor.
When we have enough VRAM don't make a useless zeros tensor.
Switch between cuda/mps/cpu based on q.device.type to allow cleaner per architecture future optimizations.
For cuda and cpu keep VRAM usage and faster slicing consistent.
For cpu use smaller slices. Tested ~20% faster on i7, 9.8 to 7.7 s/it.
Fix = typo to self.mem_total >= 8 in einsum_op_mps_v2 as per #582 discussion.
2022-09-17 20:19:21 +03:00
100f2e8f57
toil(docs): readme - remove remaining markdown warts, HTML
...
Signed-off-by: Ben Alkov <ben.alkov@gmail.com >
2022-09-17 13:00:37 -04:00
7ade11c4f3
Merge branch 'development' into development
2022-09-17 12:29:25 -04:00
2faa116238
tidy up generation of prompt when variations in use
2022-09-17 11:59:47 -04:00
c94b8cd959
small bug fixes in prompt generation
...
- fixes no closing quote in pretty-printed dream_prompt string
- removes unecessary -f switch when txt2img used
In addition, this commit does an experimental commenting-out of the
random.seed() call in the variation-generating part of ldm.dream.generator.base.
This fixes the problem of two calls that use the same seed and -v0.1
generating different images (#641 ). However, it does not fix the issue
of two images generated using the same seed and -VXXXXXX being
different.
2022-09-17 10:18:55 -04:00
0c1a2b68bf
* Added parameters to new more verbose React app and rebuilt the app.
2022-09-17 09:11:29 -04:00
c06dc5b85b
Merge branch 'development' into development
2022-09-17 08:43:15 -04:00
