aa10faa591
fix checkpoint name jumping around in the list of checkpoints for no good reason
2023-08-09 14:47:44 +03:00
c8c48640e6
Merge pull request #12426 from AUTOMATIC1111/split_shared
...
Split shared.py into multiple files
2023-08-09 14:40:06 +03:00
386245a264
split shared.py into multiple files; should resolve all circular reference import errors related to shared.py
2023-08-09 10:25:35 +03:00
54c3e5c913
Merge branch 'dev' into refiner
2023-08-08 21:49:47 +03:00
8c200c2156
Fix mismatch between shared.sd_model & shared.opts
2023-08-08 10:48:03 +09:00
6e7828e1d2
apply unet overrides after switching model
2023-08-07 08:16:20 +03:00
c96e4750d8
SD VAE rework 2
...
- the setting for preferring opts.sd_vae has been inverted and reworded
- resolve_vae function made easier to read and now returns an object rather than a tuple
- if the checkbox for overriding per-model preferences is checked, opts.sd_vae overrides checkpoint user metadata
- changing VAE in user metadata for currently loaded model immediately applies the selection
2023-08-07 08:07:20 +03:00
f1975b0213
initial refiner support
2023-08-06 17:01:07 +03:00
22ecb78b51
Merge branch 'dev' into multiple_loaded_models
2023-08-05 07:52:29 +03:00
0ae2767ae6
Merge pull request #12181 from AUTOMATIC1111/hires_checkpoint
...
Hires fix change checkpoint
2023-08-05 07:47:34 +03:00
24f21583cd
fix: prevent cache model.state_dict() after model hijack
...
Signed-off-by: AnyISalIn <anyisalin@gmail.com>
2023-08-04 11:43:27 +08:00
20549a50cb
add style editor dialog
...
rework toprow for img2img and txt2img to use a class with fields
fix the console error when editing checkpoint user metadata
2023-08-03 23:31:13 +03:00
390bffa81b
repair merge error
2023-08-01 17:13:15 +03:00
0c9b1e7969
Merge branch 'dev' into multiple_loaded_models
2023-08-01 16:55:55 +03:00
07be13caa3
add metadata to checkpoint merger
2023-08-01 08:27:54 +03:00
4b43480fe8
show metadata for SD checkpoints in the extra networks UI
2023-08-01 07:08:11 +03:00
b235022c61
option to keep multiple models in memory
2023-08-01 00:24:48 +03:00
4d9b096663
additional memory improvements when switching between models of different types
2023-07-31 10:43:31 +03:00
3bca90b249
hires fix checkpoint selection
2023-07-30 13:48:27 +03:00
0a89cd1a58
Use less RAM when creating models
2023-07-24 22:08:08 +03:00
b270ded268
fix the issue with /sdapi/v1/options failing (this time for sure!)
...
fix automated tests downloading CLIP model
2023-07-18 18:10:04 +03:00
f0e2098f1a
Add support for `--upcast-sampling` with SD XL
2023-07-18 00:39:50 -04:00
699108bfbb
hide cards for networks of incompatible stable diffusion version in Lora extra networks interface
2023-07-17 18:56:22 +03:00
b7dbeda0d9
linter
2023-07-14 09:19:08 +03:00
6d8dcdefa0
initial SDXL refiner support
2023-07-14 09:16:01 +03:00
6c5f83b19b
add support for SDXL loras with te1/te2 modules
2023-07-13 21:17:50 +03:00
e16ebc917d
repair --no-half for SDXL
2023-07-13 17:32:35 +03:00
da464a3fb3
SDXL support
2023-07-12 23:52:43 +03:00
af081211ee
getting SD2.1 to run on SDXL repo
2023-07-11 21:16:43 +03:00
da468a585b
Fix typo: checkpoint_alisases
2023-07-08 17:28:42 +03:00
da8916f926
added torch.mps.empty_cache() to torch_gc()
...
changed a bunch of places that use torch.cuda.empty_cache() to use torch_gc() instead
2023-07-08 17:13:18 +03:00
24129368f1
send tensors to the correct device when loading from safetensors file with memmap disabled for #11260
2023-06-27 09:19:04 +03:00
14196548c5
Merge pull request #11260 from dhwz/dev
...
fix very slow loading speed of .safetensors files
2023-06-27 09:11:08 +03:00
41363e0d27
fix very slow loading speed of .safetensors files
2023-06-16 18:10:15 +02:00
165ab44f03
Use os.makedirs(..., exist_ok=True)
2023-06-13 12:35:43 +03:00
f1533de982
assign devices.dtype early because it's needed before the model is loaded
2023-06-01 07:28:20 +03:00
d92a6acf0e
Merge pull request #10739 from linkoid/fix-ui-debug-mode-exit
...
Fix --ui-debug-mode exit
2023-05-27 20:02:07 +03:00
339b531570
custom unet support
2023-05-27 15:47:33 +03:00
1f0fdede17
Show full traceback in get_sd_model()
...
to reveal if an error is caused by an extension
2023-05-26 15:25:31 -04:00
3829afec36
Remove exit() from select_checkpoint()
...
Raising a FileNotFoundError instead.
2023-05-26 15:08:53 -04:00
3366e494a1
option to pad prompt/neg prompt to be same length
2023-05-22 00:13:53 +03:00
71f4a4afdf
Deduplicate webui.py initial-load/reload code
2023-05-19 17:38:42 +03:00
cd8a510ca9
if sd_model is None, do not always try to load it
2023-05-18 15:47:43 +03:00
9fd6c1e343
move some settings to the new Optimization page
...
add slider for token merging for img2img
rework StableDiffusionProcessing to have the token_merging_ratio field
fix a bug with applying png optimizations for live previews when they shouldn't be applied
2023-05-17 20:22:54 +03:00
4071fa4a12
Merge pull request #10451 from dennissheng/master
...
not clear checkpoints cache when config changes
2023-05-17 08:24:56 +03:00
54f657ffbc
not clear checkpoints cache when config changes
2023-05-17 10:47:02 +08:00
1a43524018
fix model loading twice in some situations
2023-05-14 13:27:50 +03:00
ac83627a31
heavily simplify
2023-05-13 10:23:42 -05:00
75b3692920
Merge branch 'dev' of https://github.com/AUTOMATIC1111/stable-diffusion-webui into tomesd
2023-05-11 22:40:17 -05:00
49a55b410b
Autofix Ruff W (not W605) (mostly whitespace)
2023-05-11 20:29:11 +03:00
4b854806d9
F401 fixes for ruff
2023-05-10 09:02:23 +03:00
f741a98bac
imports cleanup for ruff
2023-05-10 08:43:42 +03:00
762265eab5
autofixes from ruff
2023-05-10 07:52:45 +03:00
3ba6c3c83c
Fix up string formatting/concatenation to f-strings where feasible
2023-05-09 22:25:39 +03:00
f08ae96115
resolve merge conflicts and swap to dev branch for now
2023-05-03 02:21:50 -05:00
b1717c0a48
do not load wait for shared.sd_model to load at startup
2023-05-02 09:08:00 +03:00
dff60e2e74
Update sd_models.py
2023-04-10 04:10:50 -05:00
5c8e53d5e9
Allow different merge ratios to be used for each pass. Make toggle cmd flag work again. Remove ratio flag. Remove warning about controlnet being incompatible
2023-04-04 02:26:44 -05:00
d132481058
Embed model merge metadata in .safetensors file
2023-04-02 17:41:55 -05:00
a609bd56b4
Transition to using settings through UI instead of cmd line args. Added feature to only apply to hr-fix. Install package using requirements_versions.txt
2023-04-01 22:18:35 -05:00
26ab018253
delay import
2023-04-01 03:31:22 -05:00
56680cd84a
first
2023-04-01 02:07:08 -05:00
1b63afbedc
sort hypernetworks and checkpoints by name
2023-03-28 20:03:57 +03:00
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
1f08600345
overwrite xformers in the unclip model config if not available
2023-03-26 16:55:29 -04:00
8a34671fe9
Add support for the Variations models (unclip-h and unclip-l)
2023-03-25 21:03:07 -04:00
956ed9a737
Merge pull request #8780 from Brawlence/master
...
Unload and re-load checkpoint to VRAM on request (API & Manual)
2023-03-25 12:03:26 +03:00
92e173d414
fix variable typo
2023-03-23 14:28:08 +09:00
4cbbb881ee
Unload checkpoints on Request
...
…to free VRAM.
New Action buttons in the settings to manually free and reload checkpoints, essentially
juggling models between RAM and VRAM.
2023-03-21 09:28:50 +03:00
6a04a7f20f
fix an error loading Lora with empty values in metadata
2023-03-14 11:22:29 +03:00
c19530f1a5
Add view metadata button for Lora cards.
2023-03-14 09:10:26 +03:00
014e7323f6
when exists
2023-02-19 20:49:07 +09:00
c77f01ff31
fix auto sd download issue
2023-02-19 20:37:40 +09:00
c4ea16a03f
Add ".vae.ckpt" to ext_blacklist
2023-02-15 19:47:30 -07:00
1615f786ee
Download model if none are found
2023-02-14 20:54:02 -07:00
668d7e9b9a
make it possible to load SD1 checkpoints without CLIP
2023-02-05 11:21:00 +03:00
3e0f9a7543
fix issue with switching back to checkpoint that had its checksum calculated during runtime mentioned in #7506
2023-02-04 15:23:16 +03:00
c0e0b5844d
Merge pull request #7470 from cbrownstein-lambda/update-error-message-no-checkpoint
...
Update error message WRT missing checkpoint file
2023-02-04 12:07:12 +03:00
81823407d9
add --no-hashing
2023-02-04 11:38:56 +03:00
fb97acef63
Update error message WRT missing checkpoint file
...
The Safetensors format is also supported.
2023-02-01 14:51:06 -08:00
f6b7768f84
support for searching subdirectory names for extra networks
2023-01-29 10:20:19 +03:00
5d14f282c2
fixed a bug where after switching to a checkpoint with unknown hash, you'd get empty space instead of checkpoint name in UI
...
fixed a bug where if you update a selected checkpoint on disk and then restart the program, a different checkpoint loads, but the name is shown for the the old one.
2023-01-28 16:23:49 +03:00
5eee2ac398
add data-dir flag and set all user data directories based on it
2023-01-27 14:44:30 +01:00
6f31d2210c
support detecting midas model
...
fix broken api for checkpoint list
2023-01-27 11:54:19 +03:00
d2ac95fa7b
remove the need to place configs near models
2023-01-27 11:28:12 +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
ee0a0da324
Add instruct-pix2pix hijack
...
Allows loading instruct-pix2pix models via same method as inpainting models in sd_models.py and sd_hijack_ip2p.py
Adds ddpm_edit.py necessary for instruct-pix2pix
2023-01-25 08:53:23 -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
c1928cdd61
bring back short hashes to sd checkpoint selection
2023-01-19 18:58:08 +03:00
a5bbcd2153
fix bug with "Ignore selected VAE for..." option completely disabling VAE election
...
rework VAE resolving code to be more simple
2023-01-14 19:56:09 +03:00
08c6f009a5
load hashes from cache for checkpoints that have them
...
add checkpoint hash to footer
2023-01-14 15:55:40 +03:00
febd2b722e
update key to use with checkpoints' sha256 in cache
2023-01-14 13:37:55 +03:00
f9ac3352cb
change hypernets to use sha256 hashes
2023-01-14 10:25:37 +03:00
a95f135308
change hash to sha256
2023-01-14 09:56:59 +03:00
4bd490727e
fix for an error caused by skipping initialization, for realsies this time: TypeError: expected str, bytes or os.PathLike object, not NoneType
2023-01-11 18:54:13 +03:00
1a23dc32ac
possible fix for fallback for fast model creation from config, attempt 2
2023-01-11 10:34:36 +03:00
4fdacd31e4
possible fix for fallback for fast model creation from config
2023-01-11 10:24:56 +03:00
0f8603a559
add support for transformers==4.25.1
...
add fallback for when quick model creation fails
2023-01-10 17:46:59 +03:00
ce3f639ec8
add more stuff to ignore when creating model from config
...
prevent .vae.safetensors files from being listed as stable diffusion models
2023-01-10 16:51:04 +03:00
0c3feb202c
disable torch weight initialization and CLIP downloading/reading checkpoint to speedup creating sd model from config
2023-01-10 14:08:29 +03:00
AUTOMATIC1111