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
ac38ad7e60
Merge remote-tracking branch 'origin/master' into unipc
2023-03-10 19:42:46 -05:00
a2d635ad13
Add before_process_batch script callback
2023-02-22 01:52:53 -08:00
15f4b217b1
fix the a merge conflict resolve i did that entirely breaks image generation
2023-02-19 09:50:14 +03:00
6911deb242
Merge branch 'master' into fix-save-params-2
2023-02-19 09:15:45 +03:00
b20737815a
Fix params.txt saving for infotexts modified by process_batch
2023-02-16 21:44:46 -08:00
0a4917ac40
Apply extra networks per-batch instead of per-session (fixes wildcards)
2023-02-13 03:33:28 -08:00
fb274229b2
bug fix
2023-02-10 14:30:35 -08:00
c88dcc20d4
UniPC does not support img2img (for now)
2023-02-10 05:00:54 -08:00
1253199889
Working UniPC (for batch size 1)
2023-02-10 03:30:20 -08:00
c27c0de0f7
txt2img Hires Fix
2023-02-03 19:15:32 -05:00
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
3b2ad20ac1
Processing only, no CFGDenoiser change
...
Allows instruct-pix2pix
2023-02-02 19:19:45 -05:00
cf0cfefe91
Revert "instruct-pix2pix support"
...
This reverts commit 269833067d
2023-02-02 19:15:38 -05:00
269833067d
instruct-pix2pix support
2023-02-02 09:37:01 -05:00
040ec7a80e
make the program read Eta and Eta DDIM from generation parameters
2023-01-30 10:47:09 +03:00
00dab8f10d
remove Batch size and Batch pos from textinfo (goodbye)
2023-01-29 11:53:24 +03:00
fecb990deb
Merge pull request #7309 from brkirch/fix-embeddings
...
Fix embeddings, upscalers, and refactor `--upcast-sampling`
2023-01-28 18:44:36 +03:00
ada17dbd7c
Refactor conditional casting, fix upscalers
2023-01-28 04:16:25 -05:00
5eee2ac398
add data-dir flag and set all user data directories based on it
2023-01-27 14:44:30 +01:00
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
10421f93c3
Fix full previews, --no-half-vae
2023-01-26 01:43:35 -05:00
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
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
57c1baa774
change to code for live preview fix on OSX to be bit more obvious
2023-01-25 18:56:23 +03:00
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
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
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
78f59a4e01
enable compact view for train tab
...
prevent previews from ruining hypernetwork training
2023-01-22 00:02:51 +03:00
3deea34135
extract extra network data from prompt earlier
2023-01-21 19:36:08 +03:00
92fb1096db
make it so that extra networks are not removed from infotext
2023-01-21 16:41:25 +03:00
40ff6db532
extra networks UI
...
rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight>
2023-01-21 08:36:07 +03:00
a8322ad75b
Merge pull request #6854 from EllangoK/master
...
Saves Extra Generation Parameters to params.txt
2023-01-18 23:25:56 +03:00
b186d44dcd
use DDIM in hires fix is the sampler is PLMS
2023-01-18 23:20:23 +03:00
5e15a0b422
Changed params.txt save to after manual init call
2023-01-17 11:42:44 -05:00
e0e8005009
make StableDiffusionProcessing class not hold a reference to shared.sd_model object
2023-01-16 23:09:08 +03:00
9991967f40
Add a check and explanation for tensor with all NaNs.
2023-01-16 22:59:46 +03:00
f9ac3352cb
change hypernets to use sha256 hashes
2023-01-14 10:25:37 +03:00
88416ab5ff
Fix extension parameters not being saved to last used parameters
2023-01-12 13:46:59 -08:00
d4fd2418ef
add an option to use old hiresfix width/height behavior
...
add a visual effect to inactive hires fix elements
2023-01-09 14:57:47 +03:00
50e2536279
Merge branch 'AUTOMATIC1111:master' into img2img-api-scripts
2023-01-07 14:18:09 +00:00
1a5b86ad65
rework hires fix preview for #6437 : movie it to where it takes less place, make it actually account for all relevant sliders and calculate dimensions correctly
2023-01-07 09:56:37 +03:00
b5253f0dab
allow img2img api to run scripts
2023-01-05 21:21:48 +00:00
847f869c67
experimental optimization
2023-01-05 21:00:52 +03:00
2e30997450
move sd_model assignment to the place where we change the sd_model
2023-01-05 10:21:17 +03:00
83ca8dd0c9
Merge branch 'AUTOMATIC1111:master' into fix-sd-arch-switch-in-override-settings
2023-01-05 05:00:58 +01:00
99b67cff0b
make hires fix not do anything if the user chooses the second pass resolution to be the same as first pass resolution
2023-01-05 01:25:52 +03:00
bc43293c64
fix incorrect display/calculation for number of steps for hires fix in progress bars
2023-01-04 23:56:43 +03:00
8149078094
added the option to specify target resolution with possibility of truncating for hires fix; also sampling steps
2023-01-04 22:04:40 +03:00
097a90b88b
add XY plot parameters to grid image and do not add them to individual images
2023-01-04 19:19:11 +03:00
AUTOMATIC1111