| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2022-10-16 | Added Refresh Button to embedding and hypernetwork names in Train Tab | Junpeng Qiu | |
| Problem everytime I modified pt files in embedding_dir or hypernetwork_dir, I need to restart webui to have the new files shown in the dropdown of Train Tab Solution refactored create_refresh_button out of create_setting_component so we can use this method to create button next to gr.Dropdowns of embedding name and hypernetworks Extra Modification hypernetwork pt are now sorted in alphabetic order | |||
| 2022-10-16 | Warn when user uses bad ui setting | CookieHCl | |
| 2022-10-16 | Use default value when dropdown ui setting is bad | CookieHCl | |
| Default value is the first value of selectables. Particually, None in styles. | |||
| 2022-10-16 | Make style configurable in ui-config.json | CookieHCl | |
| 2022-10-16 | Allow specifying the region of ngrok. | ddPn08 | |
| 2022-10-16 | honor --hide-ui-dir-config option for #2807 | AUTOMATIC | |
| 2022-10-16 | added extras batch work from directory | winterspringsummer | |
| 2022-10-16 | do not reload embeddings from disk when doing textual inversion | AUTOMATIC | |
| 2022-10-15 | Update sd_hijack.py | C43H66N12O12S2 | |
| 2022-10-15 | fix saving images compatibility with gradio update | AUTOMATIC | |
| 2022-10-15 | Change vector size footer label | DepFA | |
| 2022-10-15 | generalise to popular lossless formats | DepFA | |
| 2022-10-15 | add webp for embed load | DepFA | |
| 2022-10-15 | only save 1 image per embedding | DepFA | |
| 2022-10-15 | add vector size to embed text | DepFA | |
| 2022-10-15 | check NaN for hypernetwork tuning | AngelBottomless | |
| 2022-10-15 | fix download section layout | ruocaled | |
| 2022-10-15 | typo | NO_ob | |
| 2022-10-15 | add First pass size always regardless of whether it was auto chosen or specified | AUTOMATIC | |
| 2022-10-15 | fix gadio issue with sending files between tabs | AUTOMATIC | |
| 2022-10-15 | change styling for top right corner UI | AUTOMATIC | |
| made save style button not die when you cancel | |||
| 2022-10-15 | bring back scale latent option in settings | AUTOMATIC | |
| 2022-10-15 | fix new gradio failing to preserve image params | AUTOMATIC | |
| 2022-10-15 | re-apply height hacks to work with new gradio | AUTOMATIC | |
| 2022-10-15 | Merge branch 'master' into ckpt-cache | AUTOMATIC1111 | |
| 2022-10-15 | Disable compiling deepbooru model | CookieHCl | |
| This is only necessary when you have to train, and compiling model produces warning. | |||
| 2022-10-15 | Merge branch 'master' into master | AUTOMATIC1111 | |
| 2022-10-15 | Set to -1 when seed input is none | githublsx | |
| 2022-10-15 | use "outdir_samples" if specified | ddPn08 | |
| 2022-10-15 | do not force relative paths in image history | ddPn08 | |
| 2022-10-15 | Add hint for `ctrl/alt enter` | aoirusann | |
| And duplicate implementations are removed | |||
| 2022-10-15 | add option to use batch size for training | AUTOMATIC | |
| 2022-10-15 | bring history tab back, make it behave; it's still slow but won't fuck ↵ | AUTOMATIC | |
| anything up until you use it | |||
| 2022-10-15 | reformat lines in images_history.py | AUTOMATIC | |
| 2022-10-15 | rename firstpass w/h to discard old user settings | AUTOMATIC | |
| 2022-10-14 | Raise an assertion error if no training images have been found. | Melan | |
| 2022-10-14 | set firstpass w/h to 0 by default and rever to old behavior when any are 0 | AUTOMATIC | |
| 2022-10-14 | disabling history - i knew it was slow as fuck but i didn't realize it would ↵ | AUTOMATIC | |
| also show galleries on launch | |||
| 2022-10-14 | add checkpoint cache option to UI for faster model switching | Rae Fu | |
| switching time reduced from ~1500ms to ~280ms | |||
| 2022-10-14 | remove duplicate code for log loss, add step, make it read from options ↵ | AUTOMATIC | |
| rather than gradio input | |||
| 2022-10-14 | Merge remote-tracking branch 'Melanpan/master' | AUTOMATIC | |
| 2022-10-14 | change checkpoint merger to work in a more obvious way | AUTOMATIC | |
| remove sigmoid and inverse sigmoid because they just did the same thing as weighed sum only with changed multiplier | |||
| 2022-10-14 | should fix the issue with missing layers in chechpoint merger | AUTOMATIC | |
| 2022-10-14 | add option to read generation params for learning previews from txt2img | AUTOMATIC | |
| 2022-10-14 | rework the code for lowram a bit | AUTOMATIC | |
| 2022-10-14 | load models to VRAM when using `--lowram` param | Ljzd-PRO | |
| load models to VRM instead of RAM (for machines which have bigger VRM than RAM such as free Google Colab server) | |||
| 2022-10-14 | add `--lowram` parameter | Ljzd-PRO | |
| load models to VRM instead of RAM (for machines which have bigger VRM than RAM such as free Google Colab server) | |||
| 2022-10-14 | Add option to prevent empty spots in grid (2/2) | Gugubo | |
| 2022-10-14 | Add option to prevent empty spots in grid (1/2) | Gugubo | |
| 2022-10-14 | Change grid row count autodetect to prevent empty spots | Gugubo | |
| Instead of just rounding (sometimes resulting in grids with "empty" spots), find a divisor. For example: 8 images will now result in a 4x2 grid instead of a 3x3 with one empty spot. | |||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiff |