aboutsummaryrefslogtreecommitdiffstats
path: root/modules/ui.py
Commit message (Collapse)AuthorAgeFilesLines
* Split history ui.py to ui_progress.pyAUTOMATIC2023-01-101-91/+3
|
* Split history ui.py to ui_progress.pyAndrey2023-01-101-0/+1928
|
* Split history ui.py to ui_progress.pyAndrey2023-01-101-1928/+0
|
* Variable dropout ratearia1th2023-01-101-1/+3
| | | | | | | | | | Implements variable dropout rate from #4549 Fixes hypernetwork multiplier being able to modified during training, also fixes user-errors by setting multiplier value to lower values for training. Changes function name to match torch.nn.module standard Fixes RNG reset issue when generating previews by restoring RNG state
* make a dropdown for prompt template selectionAUTOMATIC2023-01-091-2/+9
|
* remove/simplify some changes from #6481AUTOMATIC2023-01-091-1/+1
|
* Merge branch 'master' into varsizeAUTOMATIC11112023-01-091-9/+14
|\
| * add an option to use old hiresfix width/height behaviorAUTOMATIC2023-01-091-9/+14
| | | | | | | | add a visual effect to inactive hires fix elements
* | Add checkbox for variable training dimsdan2023-01-071-0/+3
|/
* add "from" resolution for hires fix to be less confusing.AUTOMATIC2023-01-071-1/+1
|
* rework hires fix preview for #6437: movie it to where it takes less place, ↵AUTOMATIC2023-01-071-13/+27
| | | | make it actually account for all relevant sliders and calculate dimensions correctly
* this breaks on default config because width, height, hr_scale are None at ↵AUTOMATIC2023-01-071-8/+6
| | | | that point.
* Merge pull request #6437 from Mitchell1711/show-target-resolutionAUTOMATIC11112023-01-071-0/+15
|\ | | | | Show upscaled resolution on hires fix
| * Changed HTML to textbox insteadMitchell Boot2023-01-071-2/+5
| | | | | | | | Using HTML caused an issue where the row would expand for a frame when changing the sliders because of the loading animation. This solution also doesn't use any additional HTML padding
| * remove camelcaseMitchell Boot2023-01-061-1/+1
| |
| * Added UI elementsMitchell Boot2023-01-061-0/+12
| | | | | | | | Added a new row to hires fix that shows the new resolution after scaling
* | CLIP hijack reworkAUTOMATIC2023-01-061-1/+1
|/
* remove restriction for saving dropdowns to ui-config.jsonAUTOMATIC2023-01-061-8/+2
|
* Add files via uploadacncagua2023-01-061-0/+2
|
* add footer with versionsAUTOMATIC2023-01-051-1/+30
|
* Add element ids for script components and a few more in ui.pyme2023-01-041-8/+8
|
* added the option to specify target resolution with possibility of truncating ↵AUTOMATIC2023-01-041-6/+18
| | | | for hires fix; also sampling steps
* train tab visual updatesAUTOMATIC2023-01-041-14/+21
| | | | allow setting train tab values from ui-config.json
* Merge branch 'master' into gradient-clippingAUTOMATIC11112023-01-041-385/+434
|\
| * rename weirdly named variables from #3176AUTOMATIC2023-01-041-7/+5
| |
| * Merge branch 'master' into masterAUTOMATIC11112023-01-041-665/+641
| |\
| | * ui: save dropdown sampling method to the ui-configMax Weber2023-01-041-0/+1
| | |
| | * added licenses screen to settingsAUTOMATIC2023-01-031-2/+13
| | | | | | | | | | | | | | | added footer removed unused inpainting code
| | * add option to reorder items in main UIAUTOMATIC2023-01-031-46/+84
| | |
| | * add a button to show all setting pagesAUTOMATIC2023-01-031-0/+2
| | |
| | * make quicksettings UI elements appear in same order as they are listed in ↵AUTOMATIC2023-01-031-2/+2
| | | | | | | | | | | | the setting
| | * styling rework to make things more compactAUTOMATIC2023-01-031-60/+61
| | |
| | * change settings UI to use vertical tabsAUTOMATIC2023-01-031-28/+17
| | |
| | * fix possible error with accessing nonexistent settingAUTOMATIC2023-01-021-1/+1
| | |
| | * error out with a readable message in chwewckpoint merger for incompatible ↵AUTOMATIC2023-01-021-1/+1
| | | | | | | | | | | | tensor shapes (ie when trying to merge SD1.5 with SD2.0)
| | * Hires fix reworkAUTOMATIC2023-01-021-8/+7
| | |
| | * Add a lot more elem_id/HTML id, modified some that were duplicates for seed ↵me2023-01-011-127/+127
| | | | | | | | | | | | section
| | * moved roll artist to built-in extensionsAUTOMATIC2023-01-011-34/+3
| | |
| | * make refresh buttons look more niceAUTOMATIC2023-01-011-3/+3
| | |
| | * add refresh buttons to checkpoint mergerAUTOMATIC2023-01-011-0/+6
| | |
| | * show sampler selection in dropdown, add option selection to revert to old ↵AUTOMATIC2022-12-311-7/+15
| | | | | | | | | | | | radio group
| | * HAPPY NEW YEARAUTOMATIC2022-12-311-8/+22
| | | | | | | | | | | | make save to zip into its own button instead of a checkbox
| | * make it so that memory/embeddings info is displayed in a separate UI element ↵AUTOMATIC2022-12-311-14/+17
| | | | | | | | | | | | from generation parameters, and is preserved when you change the displayed infotext by clicking on gallery images
| | * validate textual inversion embeddingsVladimir Mandic2022-12-311-2/+0
| | |
| | * Merge pull request #6003 from eaglgenes101/settings-css-classesAUTOMATIC11112022-12-251-2/+2
| | |\ | | | | | | | | Add CSS classes for the settings panels
| | | * Add CSS classes for the settings panelseaglgenes1012022-12-251-2/+2
| | | |
| | * | Fix clip interrogate from the webuiAllen Benz2022-12-251-1/+1
| | |/ | | | | | | | | | A recent change made the image RGBA, which makes the clip interrogator unhappy. deepbooru and calling the interrogator from the api already do the conversion so this is the only place that needed it.
| | * rename the option for img2img latent upscaleAUTOMATIC2022-12-241-1/+1
| | |
| | * Merge pull request #5521 from AndrewRyanChama/ryan/img2imglatentscaleAUTOMATIC11112022-12-241-1/+1
| | |\ | | | | | | | | Add latent upscale option to img2img
| | | * Add latent upscale option to img2imgAndrew Ryan2022-12-081-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Recently, the option to do latent upscale was added to txt2img highres fix. This feature runs by scaling the latent sample of the image, and then running a second pass of img2img. But, in this edition of highres fix, the image and parameters cannot be changed between the first pass and second pass. We might want to do a fixup in img2img before doing the second pass, or might want to run the second pass at a different resolution. This change adds the option for img2img to perform its upscale in latent space, rather than image space, giving very similar results to highres fix with latent upscale. The result is not exactly the same because there is an additional latent -> decoder -> image -> encoder -> latent that won't happen in highres fix, but this conversion has relatively small losses
generated by cgit v1.2.3 (git 2.25.1) at 2025-04-29 21:12:43 +0000