| Commit message (Collapse) | Author | Age | Files | Lines | ||
|---|---|---|---|---|---|---|
| ... | ||||||
| | * | | rework the code for lowram a bit | AUTOMATIC | 2022-10-14 | 1 | -1/+2 | |
| | | | | ||||||
| | * | | add `--lowram` parameter | Ljzd-PRO | 2022-10-14 | 1 | -0/+1 | |
| | | | | | | | | | | load models to VRM instead of RAM (for machines which have bigger VRM than RAM such as free Google Colab server) | |||||
| | * | | Add option to prevent empty spots in grid (1/2) | Gugubo | 2022-10-14 | 1 | -0/+1 | |
| | | | | ||||||
| | * | | Add 'interrogate' and 'all' choices to --use-cpu | brkirch | 2022-10-14 | 1 | -3/+3 | |
| | |/ | | | | | | | | | * Add 'interrogate' and 'all' choices to --use-cpu * Change type for --use-cpu argument to str.lower, so that choices are case insensitive | |||||
| * / | add checkpoint cache option to UI for faster model switching | Rae Fu | 2022-10-14 | 1 | -0/+1 | |
| |/ | | | | switching time reduced from ~1500ms to ~280ms | |||||
| * | add hypernetwork multipliers | AUTOMATIC | 2022-10-13 | 1 | -1/+4 | |
| | | ||||||
| * | options to refresh list of models and hypernetworks | AUTOMATIC | 2022-10-13 | 1 | -4/+5 | |
| | | ||||||
| * | add option to change what's shown in quicksettings bar | AUTOMATIC | 2022-10-13 | 1 | -2/+2 | |
| | | ||||||
| * | Merge pull request #2324 from HunterVacui/interrogate_include_ranks_in_output | AUTOMATIC1111 | 2022-10-13 | 1 | -0/+1 | |
| |\ | | | | | Interrogate: add option to include ranks in output | |||||
| | * | Merge remote-tracking branch 'upstream/master' into ↵ | Greg Fuller | 2022-10-12 | 1 | -2/+8 | |
| | |\ | | | | | | | | | | interrogate_include_ranks_in_output | |||||
| | * | | Interrogate: add option to include ranks in output | Greg Fuller | 2022-10-12 | 1 | -0/+1 | |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Since the UI also allows users to specify ranks, it can be useful to show people what ranks are being returned by interrogate This can also give much better results when feeding the interrogate results back into either img2img or txt2img, especially when trying to generate a specific character or scene for which you have a similar concept image Testing Steps: Launch Webui with command line arg: --deepdanbooru Navigate to img2img tab, use interrogate DeepBooru, verify tags appears as before. Use "Interrogate CLIP", verify prompt appears as before Navigate to Settings tab, enable new option, click "apply settings" Navigate to img2img, Interrogate DeepBooru again, verify that weights appear and are properly formatted. Note that "Interrogate CLIP" prompt is still unchanged In my testing, this change has no effect to "Interrogate CLIP", as it seems to generate a sentence-structured caption, and not a set of tags. (reproduce changes from https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/2149/commits/6ed4faac46c45ca7353f228aca9b436bbaba7bc7) | |||||
| * | | | remove interrogate option I accidentally deleted | AUTOMATIC | 2022-10-13 | 1 | -0/+1 | |
| | |/ |/| | ||||||
| * | | deepbooru: added option to use spaces or underscores | AUTOMATIC | 2022-10-12 | 1 | -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 | |||||
| * | | train: change filename processing to be more simple and configurable | AUTOMATIC | 2022-10-12 | 1 | -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 | |||||
| * | | just add the deepdanbooru settings unconditionally | AUTOMATIC | 2022-10-12 | 1 | -9/+4 | |
| | | | ||||||
| * | | Merge remote-tracking branch 'origin/steve3d' | AUTOMATIC | 2022-10-12 | 1 | -1/+1 | |
| |\ \ | ||||||
| | * | | Update shared.py | supersteve3d | 2022-10-12 | 1 | -1/+1 | |
| | |/ | | | | | Correct typo to "Unload VAE and CLIP from VRAM when training" in settings tab. | |||||
| * | | Merge pull request #2143 from JC-Array/deepdanbooru_pre_process | AUTOMATIC1111 | 2022-10-12 | 1 | -4/+9 | |
| |\ \ | | | | | | | deepbooru tags for textual inversion preproccessing | |||||
| | * | | resolved conflicts, moved settings under interrogate section, settings only ↵ | JC_Array | 2022-10-11 | 1 | -10/+9 | |
| | | | | | | | | | | | | | show if deepbooru flag is enabled | |||||
| | * | | Merge branch 'AUTOMATIC1111:master' into deepdanbooru_pre_process | JC-Array | 2022-10-11 | 1 | -4/+21 | |
| | |\| | ||||||
| | * | | Merge branch 'deepdanbooru_pre_process' into master | JC-Array | 2022-10-10 | 1 | -0/+6 | |
| | |\ \ | ||||||
| | | * | | added deepbooru settings (threshold and sort by alpha or likelyhood) | JC_Array | 2022-10-10 | 1 | -0/+6 | |
| | | | | | ||||||
| * | | | | create dir for hypernetworks | AUTOMATIC | 2022-10-12 | 1 | -0/+1 | |
| | |_|/ |/| | | ||||||
| * | | | add an option to unload models during hypernetwork training to save VRAM | AUTOMATIC | 2022-10-11 | 1 | -0/+4 | |
| | | | | ||||||
| * | | | Add cross-attention optimization from InvokeAI | brkirch | 2022-10-11 | 1 | -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 | |||||
| * | | | rename hypernetwork dir to hypernetworks to prevent clash with an old ↵ | AUTOMATIC | 2022-10-11 | 1 | -1/+1 | |
| | | | | | | | | | | | | | filename that people who use zip instead of git clone will have | |||||
| * | | | Cleaned ngrok integration | JamnedZ | 2022-10-11 | 1 | -0/+1 | |
| | | | | ||||||
| * | | | fixes related to merge | AUTOMATIC | 2022-10-11 | 1 | -2/+11 | |
| | | | | ||||||
| * | | | Comma backtrack padding (#2192) | hentailord85ez | 2022-10-11 | 1 | -0/+1 | |
| | | | | | | | | | | Comma backtrack padding | |||||
| * | | | Added slider for deepbooru score threshold in settings | Kenneth | 2022-10-11 | 1 | -0/+1 | |
| |/ / | ||||||
| * | | add an option to not add watermark to created images | AUTOMATIC | 2022-10-10 | 1 | -0/+1 | |
| | | | ||||||
| * | | Merge pull request #2131 from ssysm/upstream-master | AUTOMATIC1111 | 2022-10-10 | 1 | -0/+1 | |
| |\ \ | | | | | | | Add VAE Path Arguments | |||||
| | * | | Merge branch 'master' of ↵ | ssysm | 2022-10-10 | 1 | -9/+11 | |
| | |\| | | | | | | | | | | https://github.com/AUTOMATIC1111/stable-diffusion-webui into upstream-master | |||||
| | * | | add vae path args | ssysm | 2022-10-10 | 1 | -1/+1 | |
| | | | | ||||||
| * | | | add eta noise seed delta option | AUTOMATIC | 2022-10-10 | 1 | -0/+1 | |
| | | | | ||||||
| * | | | --no-half-vae | AUTOMATIC | 2022-10-10 | 1 | -0/+1 | |
| | |/ |/| | ||||||
| * | | Corrected CLIP Layer Ignore description and updated its range to the max ↵ | Fampai | 2022-10-09 | 1 | -1/+1 | |
| | | | | | | | | | possible | |||||
| * | | show model selection setting on top of page | AUTOMATIC | 2022-10-09 | 1 | -2/+3 | |
| | | | ||||||
| * | | added guard for torch.load to prevent loading pickles with unknown content | AUTOMATIC | 2022-10-09 | 1 | -0/+1 | |
| | | | ||||||
| * | | change up #2056 to make it work how i want it to plus make xy plot write ↵ | AUTOMATIC | 2022-10-09 | 1 | -1/+1 | |
| | | | | | | | | | correct values to images | |||||
| * | | Added extended model details to infotext | William Moorehouse | 2022-10-09 | 1 | -0/+1 | |
| | | | ||||||
| * | | Fix typo | Nicolas Noullet | 2022-10-09 | 1 | -1/+1 | |
| | | | ||||||
| * | | Fix VRAM Issue by only loading in hypernetwork when selected in settings | Fampai | 2022-10-09 | 1 | -5/+2 | |
| | | | ||||||
| * | | Merge pull request #1752 from Greendayle/dev/deepdanbooru | AUTOMATIC1111 | 2022-10-09 | 1 | -0/+1 | |
| |\ \ | |/ |/| | Added DeepDanbooru interrogator | |||||
| | * | Merge branch 'master' into dev/deepdanbooru | Greendayle | 2022-10-08 | 1 | -0/+1 | |
| | |\ | ||||||
| | * | | made deepdanbooru optional, added to readme, automatic download of deepbooru ↵ | Greendayle | 2022-10-08 | 1 | -0/+1 | |
| | | | | | | | | | | | | | model | |||||
| * | | | chore: Fix typos | Aidan Holland | 2022-10-08 | 1 | -3/+3 | |
| | | | | ||||||
| * | | | Added ability to ignore last n layers in FrozenCLIPEmbedder | Fampai | 2022-10-08 | 1 | -0/+1 | |
| | |/ |/| | ||||||
| * | | add --force-enable-xformers option and also add messages to console ↵ | AUTOMATIC | 2022-10-08 | 1 | -0/+1 | |
| |/ | | | | regarding cross attention optimizations | |||||
| * | simplify xfrmers options: --xformers to enable and that's it | AUTOMATIC | 2022-10-08 | 1 | -1/+1 | |
| | | ||||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |