StableDiffusion/WebUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
4,128 Commits 1 Branch 0 Tags 31 MiB
7428fb5176
Commit Graph

298 Commits

Author SHA1 Message Date
AUTOMATIC
7428fb5176 add is_hr_pass field for processing 2023-04-29 16:28:51 +03:00
AUTOMATIC
1d11e89698 rework Negative Guidance minimum sigma to work with AND, add infotext and copypaste parameters support 2023-04-29 15:57:09 +03:00
AUTOMATIC1111
3591eefedf
Merge pull request #9177 from devNegative-asm/master 
(Optimization) Option to remove negative conditioning at low sigma values
 2023-04-29 14:38:25 +03:00
AUTOMATIC1111
32c3b97669
Merge pull request #9628 from catboxanon/patch/9092 
Fix image mask/composite for weird resolutions
 2023-04-29 13:21:32 +03:00
AUTOMATIC1111
d6a3988b86
Merge pull request #9669 from catboxanon/patch/sampler-schedule-fix 
Fix prompt schedule for second order samplers
 2023-04-29 12:56:57 +03:00
AUTOMATIC
5fe0dd79be rename CPU RNG to RNG source in settings, add infotext and parameters copypaste support to RNG source 2023-04-29 11:29:37 +03:00
catboxanon
9de7298898
Update processing.py 2023-04-16 21:06:37 -04:00
catboxanon
4d0c816303
Modify step multiplier flow 2023-04-16 20:39:45 -04:00
catboxanon
56f8a6b081
Fix sampler schedules with step multiplier 2023-04-16 20:34:52 -04:00
catboxanon
fbab3fc6d1
Only handle image mask if any option enabled 2023-04-14 17:24:55 -04:00
catboxanon
3af152d488
Fix image mask composite for weird resolutions 2023-04-14 17:17:14 -04:00
For Sure
b3593d0997 Add support for saving init images in img2img 2023-04-06 19:42:26 +03:00
devdn
42082e8a32 performance increase 2023-03-28 20:56:01 -04:00
AUTOMATIC
433b3ab701 Revert "Merge pull request #7931 from space-nuko/img2img-enhance" 
This reverts commit 4268759370, reversing
changes made to 1b63afbedc.
 2023-03-28 20:36:57 +03:00
AUTOMATIC1111
4268759370
Merge pull request #7931 from space-nuko/img2img-enhance 
Add `Upscale by` and `Upscaler` options to img2img
 2023-03-28 20:21:25 +03:00
AUTOMATIC1111
f1db987e6a
Merge pull request #8958 from MrCheeze/variations-model 
Add support for the unclip (Variations) models, unclip-h and unclip-l
 2023-03-28 19:39:20 +03:00
MrCheeze
8a34671fe9 Add support for the Variations models (unclip-h and unclip-l) 2023-03-25 21:03:07 -04:00
space-nuko
7ea5d395c4 Add upscaler to img2img 2023-03-25 12:52:43 -04:00
space-nuko
68999d0b15 Add upscale slider to img2img 2023-03-25 12:52:35 -04:00
catboxanon
caf84e8233 Expose inpainting mask and composite 
For inpainting, this exposes the mask and masked composite and gives
the user the ability to display these in the web UI,
save to disk, or both.
 2023-03-22 17:51:40 +00:00
high_byte
4d26c7da57 initialize extra_network_data before use 2023-03-13 17:37:29 +02:00
AUTOMATIC1111
da3f942ab2
Merge pull request #8017 from space-nuko/before-process-batch 
Add `before_process_batch` script callback
 2023-03-11 14:33:38 +03:00
space-nuko
ac38ad7e60 Merge remote-tracking branch 'origin/master' into unipc 2023-03-10 19:42:46 -05:00
space-nuko
a2d635ad13 Add before_process_batch script callback 2023-02-22 01:52:53 -08:00
AUTOMATIC
15f4b217b1 fix the a merge conflict resolve i did that entirely breaks image generation 2023-02-19 09:50:14 +03:00
AUTOMATIC1111
6911deb242
Merge branch 'master' into fix-save-params-2 2023-02-19 09:15:45 +03:00
space-nuko
b20737815a Fix params.txt saving for infotexts modified by process_batch 2023-02-16 21:44:46 -08:00
space-nuko
0a4917ac40 Apply extra networks per-batch instead of per-session (fixes wildcards) 2023-02-13 03:33:28 -08:00
space-nuko
fb274229b2 bug fix 2023-02-10 14:30:35 -08:00
space-nuko
c88dcc20d4 UniPC does not support img2img (for now) 2023-02-10 05:00:54 -08:00
space-nuko
1253199889 Working UniPC (for batch size 1) 2023-02-10 03:30:20 -08:00
Kyle
c27c0de0f7 txt2img Hires Fix 2023-02-03 19:15:32 -05:00
Kyle
6c6c6636bb Image CFG Added (Full Implementation) 
Uses separate denoiser for edit (instruct-pix2pix) models

No impact to txt2img or regular img2img

"Image CFG Scale" will only apply to instruct-pix2pix models and metadata will only be added if using such model
 2023-02-03 18:19:56 -05:00
Kyle
3b2ad20ac1 Processing only, no CFGDenoiser change 
Allows instruct-pix2pix
 2023-02-02 19:19:45 -05:00
Kyle
cf0cfefe91 Revert "instruct-pix2pix support" 
This reverts commit 269833067d.
 2023-02-02 19:15:38 -05:00
Kyle
269833067d instruct-pix2pix support 2023-02-02 09:37:01 -05:00
AUTOMATIC
040ec7a80e make the program read Eta and Eta DDIM from generation parameters 2023-01-30 10:47:09 +03:00
AUTOMATIC
00dab8f10d remove Batch size and Batch pos from textinfo (goodbye) 2023-01-29 11:53:24 +03:00
AUTOMATIC1111
fecb990deb
Merge pull request #7309 from brkirch/fix-embeddings 
Fix embeddings, upscalers, and refactor `--upcast-sampling`
 2023-01-28 18:44:36 +03:00
brkirch
ada17dbd7c Refactor conditional casting, fix upscalers 2023-01-28 04:16:25 -05:00
Max Audron
5eee2ac398 add data-dir flag and set all user data directories based on it 2023-01-27 14:44:30 +01:00
AUTOMATIC
7a14c8ab45 add an option to enable sections from extras tab in txt2img/img2img 
fix some style inconsistenices
 2023-01-26 23:31:32 +03:00
brkirch
10421f93c3 Fix full previews, --no-half-vae 2023-01-26 01:43:35 -05:00
AUTOMATIC
d1d6ce2983 add edit_image_conditioning from my earlier edits in case there's an attempt to inegrate pix2pix properly 
this allows to use pix2pix model in img2img though it won't work well this way
 2023-01-25 23:25:25 +03:00
AUTOMATIC1111
1574e96729
Merge pull request #6510 from brkirch/unet16-upcast-precision 
Add upcast options, full precision sampling from float16 UNet and upcasting attention for inference using SD 2.1 models without --no-half
 2023-01-25 19:12:29 +03:00
AUTOMATIC
57c1baa774 change to code for live preview fix on OSX to be bit more obvious 2023-01-25 18:56:23 +03:00
brkirch
e3b53fd295 Add UI setting for upcasting attention to float32 
Adds "Upcast cross attention layer to float32" option in Stable Diffusion settings. This allows for generating images using SD 2.1 models without --no-half or xFormers.

In order to make upcasting cross attention layer optimizations possible it is necessary to indent several sections of code in sd_hijack_optimizations.py so that a context manager can be used to disable autocast. Also, even though Stable Diffusion (and Diffusers) only upcast q and k, unfortunately my findings were that most of the cross attention layer optimizations could not function unless v is upcast also.
 2023-01-25 01:13:04 -05:00
brkirch
84d9ce30cb Add option for float32 sampling with float16 UNet 
This also handles type casting so that ROCm and MPS torch devices work correctly without --no-half. One cast is required for deepbooru in deepbooru_model.py, some explicit casting is required for img2img and inpainting. depth_model can't be converted to float16 or it won't work correctly on some systems (it's known to have issues on MPS) so in sd_models.py model.depth_model is removed for model.half().
 2023-01-25 01:13:02 -05:00
brkirch
f64af77adc Fix different first gen with Approx NN previews 
The loading of the model for approx nn live previews can change the internal state of PyTorch, resulting in a different image. This can be avoided by preloading the approx nn model in advance.
 2023-01-23 22:49:20 -05:00
AUTOMATIC
78f59a4e01 enable compact view for train tab 
prevent  previews from ruining hypernetwork training
 2023-01-22 00:02:51 +03:00