Commit Graph

2094 Commits

Author SHA1 Message Date
dan 18a09c7e00 Simplification and bugfix 2023-01-19 17:36:23 +08:00
dan 4688bfff55 Add auto-sized cropping UI 2023-01-17 17:16:43 +08:00
AUTOMATIC c361b89026 disable the new NaN check for the CI 2023-01-17 11:05:01 +03:00
fuggy eb2223340c
Fix typo 2023-01-16 21:50:30 -06:00
AUTOMATIC e0e8005009 make StableDiffusionProcessing class not hold a reference to shared.sd_model object 2023-01-16 23:09:08 +03:00
AUTOMATIC 9991967f40 Add a check and explanation for tensor with all NaNs. 2023-01-16 22:59:46 +03:00
AUTOMATIC 064983c0ad return an option to hide progressbar 2023-01-16 12:56:30 +03:00
AUTOMATIC ff6a5bcec1 bugfix for previous commit 2023-01-16 01:28:20 +03:00
AUTOMATIC 3f887f7f61 support old configs that say "auto" for ssd_vae
change sd_vae_as_default to True by default as it's a more sensible setting
2023-01-16 00:44:52 +03:00
AUTOMATIC 3db22e6ee4 rename masking to inpaint in UI
make inpaint go to the right place for users who don't have it in config string
2023-01-15 23:32:38 +03:00
AUTOMATIC1111 30cfe4ed9b
Merge pull request #6758 from Poktay/allow_reorder_masking_controls
allow reordering of inpaint masking controls (like the other sections can be reordered)
2023-01-15 23:24:09 +03:00
AUTOMATIC 89314e79da fix an error that happens when you send an empty image from txt2img to img2img 2023-01-15 23:23:24 +03:00
AUTOMATIC1111 f3167b10ce
Merge pull request #6780 from vladmandic/train-logging
add fields to settings file
2023-01-15 22:55:45 +03:00
AUTOMATIC1111 d6fa8e92ca
Merge pull request #6782 from aria1th/fix-hypernetwork-loss
Fix tensorboard-hypernetwork integration correctly
2023-01-15 22:55:06 +03:00
AUTOMATIC1111 4385449933
Merge pull request #6778 from pangbo13/master
Fix unexpected behavior when show_progress_every_n_steps is set to -1
2023-01-15 22:54:14 +03:00
AUTOMATIC 8e2aeee4a1 add BREAK keyword to end current text chunk and start the next 2023-01-15 22:29:53 +03:00
aria1th 13445738d9 Fix tensorboard related functions 2023-01-16 03:02:54 +09:00
aria1th 598f7fcd84 Fix loss_dict problem 2023-01-16 02:46:21 +09:00
Vladimir Mandic 110d1a2d59
add fields to settings file 2023-01-15 12:41:00 -05:00
AUTOMATIC 205991df78 Merge remote-tracking branch 'origin/fix-mean-loss' 2023-01-15 20:30:42 +03:00
AUTOMATIC b6ce041cdf put interrupt and skip buttons back where they were 2023-01-15 20:29:55 +03:00
AUTOMATIC a534bdfc80 add setting for progressbar update period 2023-01-15 20:29:55 +03:00
AngelBottomless 16f410893e
fix missing 'mean loss' for tensorboard integration 2023-01-16 02:08:47 +09:00
pangbo13 388708f7b1 fix when show_progress_every_n_steps == -1 2023-01-16 00:56:24 +08:00
AUTOMATIC1111 ce13ced5dc
Merge pull request #6772 from vladmandic/sha-calc-optimization
increase block size
2023-01-15 19:09:46 +03:00
AUTOMATIC1111 006997d180
Merge pull request #6770 from brkirch/approx-nn-fix
Fix Approx NN not working on torch devices other than CUDA
2023-01-15 19:09:06 +03:00
AUTOMATIC d8b90ac121 big rework of progressbar/preview system to allow multiple users to prompts at the same time and do not get previews of each other 2023-01-15 18:51:04 +03:00
Vladimir Mandic f0312565e5
increase block size 2023-01-15 09:42:34 -05:00
brkirch eef1990a5e Fix Approx NN on devices other than CUDA 2023-01-15 08:13:33 -05:00
Josh R 9ef41df6f9 add inpaint masking controls to orderable section that the settings can order 2023-01-14 15:26:45 -08:00
Vladimir Mandic ce9827a7c5
Merge pull request #6731 from vladmandic/state_server_start
Add server start time to state info
2023-01-14 16:03:29 -05:00
AUTOMATIC1111 beeec2b598
Merge pull request #6728 from bbc-mc/exclude_clip_index_from_merge_target
Exclude clip index from merge
2023-01-14 23:12:31 +03:00
AUTOMATIC 86359535d6 add buttons to copy images between img2img tabs 2023-01-14 22:43:01 +03:00
AUTOMATIC f8c5124785 typo? 2023-01-14 20:00:12 +03:00
AUTOMATIC 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
Vladimir Mandic fad850fc3d
add server_start to shared.state 2023-01-14 11:18:05 -05:00
AUTOMATIC f94a215abe add an option to choose what you want to see in live preview (Live preview subject) and moves live preview settings to its own tab 2023-01-14 16:29:23 +03:00
AUTOMATIC 08c6f009a5 load hashes from cache for checkpoints that have them
add checkpoint hash to footer
2023-01-14 15:55:40 +03:00
bbc_mc 5f8685237e Exclude clip index from merge 2023-01-14 20:09:32 +09:00
AUTOMATIC febd2b722e update key to use with checkpoints' sha256 in cache 2023-01-14 13:37:55 +03:00
AUTOMATIC f9ac3352cb change hypernets to use sha256 hashes 2023-01-14 10:25:37 +03:00
AUTOMATIC a95f135308 change hash to sha256 2023-01-14 09:56:59 +03:00
AUTOMATIC 82725f0ac4 fix a bug caused by merge 2023-01-13 15:04:37 +03:00
AUTOMATIC1111 9cd7716753
Merge branch 'master' into tensorboard 2023-01-13 14:57:38 +03:00
AUTOMATIC1111 544e7a233e
Merge pull request #6689 from Poktay/add_gradient_settings_to_logging_file
add gradient settings to training settings log files
2023-01-13 14:45:32 +03:00
AUTOMATIC1111 3ad1fdd99b
Merge pull request #6684 from space-nuko/save-extension-params-to-last-params
Fix extension parameters not being saved to last used parameters
2023-01-13 14:44:39 +03:00
AUTOMATIC1111 7bf3cfc427
Merge pull request #6685 from space-nuko/script-callback-fix-infotext
Add script callback for fixing infotext parameters
2023-01-13 14:43:42 +03:00
AUTOMATIC a176d89487 print bucket sizes for training without resizing images #6620
fix an error when generating a picture with embedding in it
2023-01-13 14:32:15 +03:00
AUTOMATIC1111 486bda9b33
Merge pull request #6620 from guaneec/varsize_batch
Enable batch_size>1 for mixed-sized training
2023-01-13 14:03:31 +03:00
Josh R 0b262802b8 add gradient settings to training settings log files 2023-01-12 17:31:05 -08:00