| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2022-10-13 | remove interrogate option I accidentally deleted | AUTOMATIC | -0/+1 | |
| 2022-10-12 | deepbooru: added option to use spaces or underscores | AUTOMATIC | -0/+2 | |
| deepbooru: added option to quote (\) in tags deepbooru/BLIP: write caption to file instead of image filename deepbooru/BLIP: now possible to use both for captions deepbooru: process is stopped even if an exception occurs | ||||
| 2022-10-12 | train: change filename processing to be more simple and configurable | AUTOMATIC | -0/+3 | |
| train: make it possible to make text files with prompts train: rework scheduler so that there's less repeating code in textual inversion and hypernets train: move epochs setting to options | ||||
| 2022-10-12 | just add the deepdanbooru settings unconditionally | AUTOMATIC | -9/+4 | |
| 2022-10-12 | Merge remote-tracking branch 'origin/steve3d' | AUTOMATIC | -1/+1 | |
| 2022-10-12 | Merge pull request #2143 from JC-Array/deepdanbooru_pre_process | AUTOMATIC1111 | -4/+9 | |
| deepbooru tags for textual inversion preproccessing | ||||
| 2022-10-12 | create dir for hypernetworks | AUTOMATIC | -0/+1 | |
| 2022-10-12 | Update shared.py | supersteve3d | -1/+1 | |
| Correct typo to "Unload VAE and CLIP from VRAM when training" in settings tab. | ||||
| 2022-10-11 | resolved conflicts, moved settings under interrogate section, settings only ↵ | JC_Array | -10/+9 | |
| show if deepbooru flag is enabled | ||||
| 2022-10-11 | Merge branch 'AUTOMATIC1111:master' into deepdanbooru_pre_process | JC-Array | -4/+21 | |
| 2022-10-11 | add an option to unload models during hypernetwork training to save VRAM | AUTOMATIC | -0/+4 | |
| 2022-10-11 | Add cross-attention optimization from InvokeAI | brkirch | -2/+3 | |
| * Add cross-attention optimization from InvokeAI (~30% speed improvement on MPS) * Add command line option for it * Make it default when CUDA is unavailable | ||||
| 2022-10-11 | rename hypernetwork dir to hypernetworks to prevent clash with an old ↵ | AUTOMATIC | -1/+1 | |
| filename that people who use zip instead of git clone will have | ||||
| 2022-10-11 | Cleaned ngrok integration | JamnedZ | -0/+1 | |
| 2022-10-11 | fixes related to merge | AUTOMATIC | -2/+11 | |
| 2022-10-11 | Comma backtrack padding (#2192) | hentailord85ez | -0/+1 | |
| Comma backtrack padding | ||||
| 2022-10-11 | Added slider for deepbooru score threshold in settings | Kenneth | -0/+1 | |
| 2022-10-10 | Merge branch 'deepdanbooru_pre_process' into master | JC-Array | -0/+6 | |
| 2022-10-10 | added deepbooru settings (threshold and sort by alpha or likelyhood) | JC_Array | -0/+6 | |
| 2022-10-10 | add an option to not add watermark to created images | AUTOMATIC | -0/+1 | |
| 2022-10-10 | Merge pull request #2131 from ssysm/upstream-master | AUTOMATIC1111 | -0/+1 | |
| Add VAE Path Arguments | ||||
| 2022-10-10 | add eta noise seed delta option | AUTOMATIC | -0/+1 | |
| 2022-10-10 | --no-half-vae | AUTOMATIC | -0/+1 | |
| 2022-10-09 | Merge branch 'master' of ↵ | ssysm | -9/+11 | |
| https://github.com/AUTOMATIC1111/stable-diffusion-webui into upstream-master | ||||
| 2022-10-09 | add vae path args | ssysm | -1/+1 | |
| 2022-10-09 | Corrected CLIP Layer Ignore description and updated its range to the max ↵ | Fampai | -1/+1 | |
| possible | ||||
| 2022-10-09 | show model selection setting on top of page | AUTOMATIC | -2/+3 | |
| 2022-10-09 | added guard for torch.load to prevent loading pickles with unknown content | AUTOMATIC | -0/+1 | |
| 2022-10-09 | change up #2056 to make it work how i want it to plus make xy plot write ↵ | AUTOMATIC | -1/+1 | |
| correct values to images | ||||
| 2022-10-09 | Added extended model details to infotext | William Moorehouse | -0/+1 | |
| 2022-10-09 | Fix typo | Nicolas Noullet | -1/+1 | |
| 2022-10-09 | Fix VRAM Issue by only loading in hypernetwork when selected in settings | Fampai | -5/+2 | |
| 2022-10-09 | Merge pull request #1752 from Greendayle/dev/deepdanbooru | AUTOMATIC1111 | -0/+1 | |
| Added DeepDanbooru interrogator | ||||
| 2022-10-08 | chore: Fix typos | Aidan Holland | -3/+3 | |
| 2022-10-08 | Added ability to ignore last n layers in FrozenCLIPEmbedder | Fampai | -0/+1 | |
| 2022-10-08 | Merge branch 'master' into dev/deepdanbooru | Greendayle | -0/+1 | |
| 2022-10-08 | add --force-enable-xformers option and also add messages to console ↵ | AUTOMATIC | -0/+1 | |
| regarding cross attention optimizations | ||||
| 2022-10-08 | made deepdanbooru optional, added to readme, automatic download of deepbooru ↵ | Greendayle | -0/+1 | |
| model | ||||
| 2022-10-08 | simplify xfrmers options: --xformers to enable and that's it | AUTOMATIC | -1/+1 | |
| 2022-10-08 | Merge pull request #1851 from C43H66N12O12S2/flash | AUTOMATIC1111 | -1/+2 | |
| xformers attention | ||||
| 2022-10-08 | add xformers_available shared variable | C43H66N12O12S2 | -1/+1 | |
| 2022-10-08 | do not let user choose his own prompt token count limit | AUTOMATIC | -3/+0 | |
| 2022-10-08 | check specifically for skipped | Trung Ngo | -1/+0 | |
| 2022-10-08 | Add button to skip the current iteration | Trung Ngo | -0/+5 | |
| 2022-10-08 | let user choose his own prompt token count limit | AUTOMATIC | -2/+3 | |
| 2022-10-07 | added support for hypernetworks (???) | AUTOMATIC | -1/+8 | |
| 2022-10-07 | Update shared.py | C43H66N12O12S2 | -0/+1 | |
| 2022-10-06 | Removed duplicate defined models_path | Milly | -10/+9 | |
| Use `modules.paths.models_path` instead `modules.shared.model_path`. | ||||
| 2022-10-06 | Default window title progress updates on | DepFA | -1/+1 | |
| 2022-10-06 | Update shared.py | DepFA | -0/+1 | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |