aboutsummaryrefslogtreecommitdiffstats
path: root/modules/ui.py
Commit message (Collapse)AuthorAgeFilesLines
* Interrogate: add option to include ranks in outputGreg Fuller2022-10-121-3/+2
| | | | | | | | | | | | | | | | 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)
* apply lr schedule to hypernetsAUTOMATIC2022-10-111-1/+1
|
* Merge branch 'learning_rate-scheduling' into learnscheduleAUTOMATIC11112022-10-111-28/+84
|\
| * add option to select hypernetwork modules when creatingAUTOMATIC2022-10-111-0/+2
| |
| * Merge pull request #2227 from papuSpartan/masterAUTOMATIC11112022-10-111-0/+1
| |\ | | | | | | Refresh list of models/ckpts upon hitting restart gradio in the setti…
| | * move list refresh to webui.py and add stdout indicating it's doing sopapuSpartan2022-10-111-3/+0
| | |
| | * Refresh list of models/ckpts upon hitting restart gradio in the settings panepapuSpartan2022-10-111-0/+4
| | |
| * | more renamesAUTOMATIC2022-10-111-2/+2
| | |
| * | rename hypernetwork dir to hypernetworks to prevent clash with an old ↵AUTOMATIC2022-10-111-1/+1
| | | | | | | | | | | | filename that people who use zip instead of git clone will have
| * | Cleaned ngrok integrationJamnedZ2022-10-111-0/+5
| | |
| * | add a space holderBen2022-10-111-1/+4
| | |
| * | Layout fixBen2022-10-111-14/+14
| | |
| * | fixes related to mergeAUTOMATIC2022-10-111-2/+3
| | |
| * | Merge branch 'master' into hypernetwork-trainingAUTOMATIC2022-10-111-31/+145
| |\ \
| | * | Added slider for deepbooru score threshold in settingsKenneth2022-10-111-1/+1
| | | |
| | * | Make the ctrl+enter shortcut use the generate button on the current tabJairo Correa2022-10-111-1/+1
| | |/
| | * Always show previous mask and fix extras_send destVladimir Repin2022-10-101-1/+1
| | |
| | * Remove max_batch_count from ui.pyRW212022-10-101-2/+2
| | |
| * | hypernetwork training mk1AUTOMATIC2022-10-071-7/+51
| | |
* | | Refactored learning rate codeFampai2022-10-101-1/+1
| |/ |/|
* | Custom Width and Heightalg-wiki2022-10-101-4/+8
| |
* | Textual Inversion: Added custom training image size and number of repeats ↵alg-wiki2022-10-101-1/+7
| | | | | | | | per input image in a single epoch
* | show model selection setting on top of pageAUTOMATIC2022-10-091-9/+45
| |
* | prevent a possible code execution error (thanks, RyotaK)AUTOMATIC2022-10-091-0/+9
| |
* | hide filenames for save button by defaultAUTOMATIC2022-10-091-3/+3
| |
* | Merge pull request #1752 from Greendayle/dev/deepdanbooruAUTOMATIC11112022-10-091-5/+24
|\ \ | | | | | | Added DeepDanbooru interrogator
| * | made deepdanbooru optional, added to readme, automatic download of deepbooru ↵Greendayle2022-10-081-7/+12
| | | | | | | | | | | | model
| * | fix conflictsGreendayle2022-10-081-1/+9
| |\ \
| * \ \ Merge branch 'master' into dev/deepdanbooruGreendayle2022-10-071-40/+22
| |\ \ \ | | | |/ | | |/|
| * | | deepdanbooru interrogatorGreendayle2022-10-051-5/+19
| | | |
* | | | Support `Download` for txt files.aoirusann2022-10-091-1/+4
| | | |
* | | | Add `Download` & `Download as zip`aoirusann2022-10-091-5/+34
| | | |
* | | | chore: Fix typosAidan Holland2022-10-081-2/+2
| | | |
* | | | Update ui.pyDepFA2022-10-081-1/+1
| | | |
* | | | TI preprocess wordingDepFA2022-10-081-3/+3
| |_|/ |/| | | | | I had to check the code to work out what splitting was 🤷🏿
* | | Fixed typoMilly2022-10-081-1/+1
| | |
* | | Add button to skip the current iterationTrung Ngo2022-10-081-0/+8
| |/ |/|
* | Removed duplicate image saving codesMilly2022-10-061-36/+10
| | | | | | | | Use `modules.images.save_image()` instead.
* | added support for AND from ↵AUTOMATIC2022-10-051-2/+4
| | | | | | | | https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/
* | shared.state.interrupt when restart is requestedDepFA2022-10-051-0/+1
| |
* | Display time taken in mins, secs when relevantxpscyho2022-10-041-1/+6
| | | | | | | | Fixes #1656
* | add editor to img2imgAUTOMATIC2022-10-041-1/+1
|/
* ignore errors in parse for purposes of token counting for #1564AUTOMATIC2022-10-041-2/+10
|
* batch processing for img2img with an empty output directory, by requestAUTOMATIC2022-10-031-1/+1
|
* Convert folder icon surrogate pair to valid utf8Hanusz Leszek2022-10-031-1/+1
|
* keep textual inversion dataset latents in CPU memory to save a bit of VRAMAUTOMATIC2022-10-021-2/+2
|
* preprocessing for textual inversion addedAUTOMATIC2022-10-021-0/+36
|
* make save to dirs optional for imgs saved from uiLopyter2022-10-021-1/+1
|
* Merge branch 'master' into 1404-script-reload-without-restartAUTOMATIC11112022-10-021-32/+176
|\
| * Merge pull request #1324 from liamkerr/token_updatesAUTOMATIC11112022-10-021-8/+18
| |\ | | | | | | Fixing Bugs with Token Counter
generated by cgit v1.2.3 (git 2.25.1) at 2025-06-15 08:58:22 +0000