Uminosachi
042e1d5d0b
Fix SD VAE switch error after model reuse
2023-08-20 15:00:14 +09:00
w-e-w
8ce613bb3a
switch to PNG when images too large
2023-08-19 16:50:43 +09:00
AUTOMATIC1111
9d2299ed0b
implement undo hijack for SDXL
2023-08-19 10:16:27 +03:00
AUTOMATIC1111
35db3665b3
possible fix for dictionary changed size during iteration
2023-08-19 08:39:48 +03:00
AUTOMATIC1111
5a5913828c
Merge pull request #12616 from catboxanon/extra-noise-callback
...
Add extra noise callback
2023-08-19 08:36:44 +03:00
AUTOMATIC1111
448d6bef37
Merge pull request #12599 from AUTOMATIC1111/ram_optim
...
RAM optimization round 2
2023-08-19 08:36:20 +03:00
AUTOMATIC1111
7056fdf2be
Merge pull request #12630 from catboxanon/fix/nans-mk2
...
Attempt to resolve NaN issue with unstable VAEs in fp32 mk2
2023-08-19 08:34:46 +03:00
AUTOMATIC1111
3d81fd714b
Merge pull request #12633 from catboxanon/fix/img2img-bg-color
...
Fix img2img background color for transparent images option not being used
2023-08-19 08:33:22 +03:00
AUTOMATIC1111
99a64edea8
do not assign to vae_dict
2023-08-19 08:31:06 +03:00
AUTOMATIC1111
d75b521af8
Merge pull request #12638 from Cschlaefli/fix-api-vae-model-refresh
...
fix issues with api model-refresh and vae-refresh
2023-08-19 08:28:47 +03:00
AUTOMATIC1111
296c8f6a4a
Merge pull request #12639 from AUTOMATIC1111/more-hash
...
More hash filename patterns
2023-08-19 08:28:00 +03:00
AUTOMATIC1111
5590be7a8c
Merge pull request #12644 from AUTOMATIC1111/fix-model-override-logic
...
fix model override logic
2023-08-19 08:26:39 +03:00
AUTOMATIC1111
f084e6bbd0
revert xformers back to 0.0.20
2023-08-19 08:22:12 +03:00
AUTOMATIC1111
cd719b08bd
Merge pull request #12663 from SpenserCai/get_image_from_url
...
api support get image from url
2023-08-19 08:08:19 +03:00
AUTOMATIC1111
90e560bb75
Merge pull request #12648 from catboxanon/feat/gallery-tweaks
...
Gallery: Set preview to `True`, allow custom height
2023-08-19 08:06:13 +03:00
AUTOMATIC1111
9182dd7e5d
Merge pull request #12634 from catboxanon/feat/live-preview-fast-interrupt
...
Improve interrupt speed
2023-08-19 08:05:36 +03:00
AUTOMATIC1111
f739e3e05d
second appearance
2023-08-19 08:04:48 +03:00
AUTOMATIC1111
e7a044a2d1
Merge pull request #12653 from S-Del/fix/typo
...
fix typo `txt2txt` -> `txt2img`
2023-08-19 08:03:40 +03:00
SpenserCai
4760c3c0b5
api support get image from url
2023-08-19 12:19:21 +08:00
XDOneDude
61c1261e4e
more grammar fixes
2023-08-18 21:56:15 -04:00
XDOneDude
956e1d8d90
xformers update
2023-08-18 21:25:59 -04:00
S-Del
64d5fa1efd
fix typo txt2txt -> txt2img
2023-08-18 22:32:20 +09:00
catboxanon
9d1d63afca
Exit out of hires fix if interrupted earlier
2023-08-18 05:55:10 -04:00
catboxanon
44d4e7c500
Gallery: Set preview to True, allow custom height
2023-08-18 05:15:30 -04:00
w-e-w
640cb1bb8d
fix model override logic
...
do not need extra logic to unload refine model
2023-08-18 17:14:02 +09:00
w-e-w
a81dc43fcd
negative_prompt full_prompt hash
2023-08-18 15:13:12 +09:00
w-e-w
8a1f32b6a5
image hash
2023-08-18 14:04:46 +09:00
Cade Schlaefli
f9c2216ffa
remove unused import
2023-08-17 21:14:14 -05:00
Cade Schlaefli
959f8b32d5
fix issues with model refresh
2023-08-17 20:48:17 -05:00
catboxanon
3ce5fb8e5c
Add option for faster live interrupt
2023-08-17 20:03:26 -04:00
catboxanon
46e8898f65
Fix img2img background color not being used
2023-08-17 19:35:34 -04:00
catboxanon
3003b10e0a
Attempt to resolve NaN issue with unstable VAEs in fp32 mk2
2023-08-17 18:10:55 -04:00
AUTOMATIC1111
0dc74545c0
resolve the issue with loading fp16 checkpoints while using --no-half
2023-08-17 07:54:07 +03:00
catboxanon
254be4eeb2
Add extra noise callback
2023-08-16 21:45:19 -04:00
w-e-w
e1a29266b2
return empty list if extensions_dir not exist
2023-08-17 00:24:24 +09:00
w-e-w
0cf85b24df
auto add data-dir to gradio-allowed-path
2023-08-16 20:18:46 +09:00
AUTOMATIC1111
eaba3d7349
send weights to target device instead of CPU memory
2023-08-16 12:11:01 +03:00
AUTOMATIC1111
57e59c14c8
Revert "send weights to target device instead of CPU memory"
...
This reverts commit 0815c45bcd
2023-08-16 11:28:00 +03:00
AUTOMATIC1111
0815c45bcd
send weights to target device instead of CPU memory
2023-08-16 10:44:17 +03:00
AUTOMATIC1111
023a3a98a1
Merge pull request #12596 from AUTOMATIC1111/fix-taesd-scale
...
Remove wrong TAESD Latent scale
2023-08-16 09:56:12 +03:00
AUTOMATIC1111
86221269f9
RAM optimization round 2
2023-08-16 09:55:35 +03:00
Kohaku-Blueleaf
d9ddc5d4cd
Remove wrong scale
2023-08-16 11:21:12 +08:00
AUTOMATIC1111
fd563e3274
Merge pull request #12586 from catboxanon/fix/rng-shape
...
RNG: Make all elements of shape `int`s
2023-08-15 21:47:02 +03:00
catboxanon
0f77139253
Fix inpaint upload for alpha masks, create reusable function
2023-08-15 14:24:55 -04:00
catboxanon
5b28b7dbc7
RNG: Make all elements of shape ints
2023-08-15 13:38:37 -04:00
AUTOMATIC1111
f01682ee01
store patches for Lora in a specialized module
2023-08-15 19:23:40 +03:00
AUTOMATIC1111
7327be97aa
Merge pull request #12570 from NoCrypt/add-miku-theme
...
Add NoCrypt/miku gradio theme
2023-08-15 16:31:12 +03:00
brkirch
54209c1639
Use the new SD VAE override setting
2023-08-15 06:29:39 -04:00
AUTOMATIC1111
bc61ad9ec8
Merge pull request #12564 from catboxanon/feat/img2img-noise
...
Add extra noise param for img2img operations
2023-08-15 09:50:20 +03:00
NoCrypt
b0a6d61d73
Add NoCrypt/miku gradio theme
2023-08-15 13:22:44 +07:00
catboxanon
371b24b17c
Add extra img2img noise
2023-08-15 02:19:19 -04:00
AUTOMATIC1111
79d4e81984
fix processing error that happens if batch_size is not a multiple of how many prompts/negative prompts there are #12509
2023-08-15 08:46:17 +03:00
AUTOMATIC1111
7e77a38cbc
get XYZ plot to work with recent changes to refined specified in fields of p rather than in settings
2023-08-15 08:27:50 +03:00
AUTOMATIC1111
6f86573247
Merge pull request #12552 from brkirch/update-sdxl-commit-hash
...
Update SD XL commit hash
2023-08-15 08:12:21 +03:00
AUTOMATIC1111
45be87afc6
correctly add Eta DDIM to infotext when it's 1.0 and do not add it when it's 0.0.
2023-08-14 21:48:05 +03:00
AUTOMATIC1111
f23e5ce2da
revert changed inpainting mask conditioning calculation after #12311
2023-08-14 17:59:03 +03:00
AUTOMATIC1111
e56b7c8419
Merge pull request #12547 from whitebell/fix-typo
...
Fix typo in shared_options.py
2023-08-14 13:36:10 +03:00
brkirch
bc63339df3
Update hash for SD XL Repo
2023-08-14 06:26:36 -04:00
AUTOMATIC1111
6bfd4dfecf
add second_order to samplers that mistakenly didn't have it
2023-08-14 12:07:38 +03:00
Robert Barron
99ab3d43a7
hires prompt timeline: merge to latests, slightly simplify diff
2023-08-14 00:43:27 -07:00
AUTOMATIC1111
353c876172
fix API always using -1 as seed
2023-08-14 10:43:18 +03:00
Robert Barron
d61e31bae6
Merge remote-tracking branch 'auto1111/dev' into shared-hires-prompt-test
2023-08-14 00:35:17 -07:00
AUTOMATIC1111
f3b96d4998
return seed controls UI to how it was before
2023-08-14 10:22:52 +03:00
AUTOMATIC1111
abbecb3e73
further repair the /docs page to not break styles with the attempted fix
2023-08-14 10:15:10 +03:00
whitebell
b39d9364d8
Fix typo in shared_options.py
...
unperdictable -> unpredictable
2023-08-14 15:58:38 +09:00
AUTOMATIC1111
c7c16f805c
repair /docs page
2023-08-14 09:49:51 +03:00
AUTOMATIC1111
f37cc5f5e1
Merge pull request #12542 from AUTOMATIC1111/res-sampler
...
Add RES sampler and reorder the sampler list
2023-08-14 09:02:10 +03:00
AUTOMATIC1111
c1a31ec9f7
revert to applying mask before denoising for k-diffusion, like it was before
2023-08-14 08:59:15 +03:00
Kohaku-Blueleaf
aa26f8eb40
Put frequently used sampler back
2023-08-14 13:50:53 +08:00
AUTOMATIC1111
cda2f0a162
make on_before_component/on_after_component possible earlier
2023-08-14 08:49:39 +03:00
AUTOMATIC1111
aeb76ef174
repair DDIM/PLMS/UniPC batches
2023-08-14 08:49:02 +03:00
Kohaku-Blueleaf
0ea61a74be
add res(dpmdd 2m sde heun) and reorder the sampler list
2023-08-14 11:46:36 +08:00
AUTOMATIC1111
007ecfbb29
also use setup callback for the refiner instead of before_process
2023-08-13 21:01:13 +03:00
AUTOMATIC1111
9cd0475c08
Merge pull request #12526 from brkirch/mps-adjust-sub-quad
...
Fixes for `git checkout`, MPS/macOS fixes and optimizations
2023-08-13 20:28:49 +03:00
AUTOMATIC1111
8452708560
Merge pull request #12530 from eltociear/eltociear-patch-1
...
Fix typo in launch_utils.py
2023-08-13 20:27:17 +03:00
AUTOMATIC1111
16781ba09a
fix 2 for git code botched by previous PRs
2023-08-13 20:15:20 +03:00
Ikko Eltociear Ashimine
09ff5b5416
Fix typo in launch_utils.py
...
existance -> existence
2023-08-14 01:03:49 +09:00
AUTOMATIC1111
f093c9d39d
fix broken XYZ plot seeds
...
add new callback for scripts to be used before processing
2023-08-13 17:31:10 +03:00
brkirch
2035cbbd5d
Fix DDIM and PLMS samplers on MPS
2023-08-13 10:07:52 -04:00
brkirch
5df535b7c2
Remove duplicate code for torchsde randn
2023-08-13 10:07:52 -04:00
brkirch
f4dbb0c820
Change the repositories origin URLs when necessary
2023-08-13 10:07:52 -04:00
brkirch
9058620cec
git checkout with commit hash
2023-08-13 10:07:14 -04:00
brkirch
2489252099
torch.empty can create issues; use torch.zeros
...
For MPS, using a tensor created with `torch.empty()` can cause `torch.baddbmm()` to include NaNs in the tensor it returns, even though `beta=0`. However, with a tensor of shape [1,1,1], there should be a negligible performance difference between `torch.empty()` and `torch.zeros()` anyway, so it's better to just use `torch.zeros()` for this and avoid unnecessarily creating issues.
2023-08-13 10:06:25 -04:00
brkirch
87dd685224
Make sub-quadratic the default for MPS
2023-08-13 10:06:25 -04:00
brkirch
abfa4ad8bc
Use fixed size for sub-quadratic chunking on MPS
...
Even if this causes chunks to be much smaller, performance isn't significantly impacted. This will usually reduce memory usage but should also help with poor performance when free memory is low.
2023-08-13 10:06:25 -04:00
AUTOMATIC1111
3163d1269a
fix for the broken run_git calls
2023-08-13 16:51:21 +03:00
AUTOMATIC1111
1c6ca09992
Merge pull request #12510 from catboxanon/feat/extnet/hashes
...
Support search and display of hashes for all extra network items
2023-08-13 16:46:32 +03:00
AUTOMATIC1111
d73db17ee3
Merge pull request #12515 from catboxanon/fix/gc1
...
Clear sampler and garbage collect before decoding images to reduce VRAM
2023-08-13 16:45:38 +03:00
AUTOMATIC1111
127ab9114f
Merge pull request #12514 from catboxanon/feat/batch-encode
...
Encode batch items individually to significantly reduce VRAM
2023-08-13 16:41:07 +03:00
AUTOMATIC1111
d53f3b5596
Merge pull request #12520 from catboxanon/eta
...
Update description of eta setting
2023-08-13 16:40:17 +03:00
AUTOMATIC1111
d41a5bb97d
Merge pull request #12521 from catboxanon/feat/more-s-noise
...
Add `s_noise` param to more samplers
2023-08-13 16:39:25 +03:00
catboxanon
525b55b1e9
Restore extra_params that was lost in merge
2023-08-13 09:08:34 -04:00
catboxanon
ce0829d711
Merge branch 'feat/dpmpp3msde' into feat/more-s-noise
2023-08-13 08:46:58 -04:00
catboxanon
ac790fc49b
Discard penultimate sigma for DPM-Solver++(3M) SDE
2023-08-13 08:46:07 -04:00
catboxanon
f4757032e7
Fix s_noise description
2023-08-13 08:24:28 -04:00
catboxanon
d1a70c3f05
Add s_noise param to more samplers
2023-08-13 08:22:24 -04:00
AUTOMATIC1111
d8419762c1
Lora: output warnings in UI rather than fail for unfitting loras; switch to logging for error output in console
2023-08-13 15:07:37 +03:00
catboxanon
60a7405165
Update description of eta setting
2023-08-13 08:06:40 -04:00
catboxanon
1ae9dacb4b
Add DPM-Solver++(3M) SDE
2023-08-13 07:57:29 -04:00
catboxanon
69f49c8d39
Clear sampler before decoding images
...
More significant VRAM reduction.
2023-08-13 04:40:34 -04:00
