aboutsummaryrefslogtreecommitdiffstats
path: root/webui.py
Commit message (Collapse)AuthorAgeFilesLines
...
* fixed some bugs in gridAUTOMATIC2022-08-291-8/+39
| | | | | changed some default values to more reasonable added PNG info tab
* gfpgan is not kept in memoryAUTOMATIC2022-08-291-39/+40
| | | | font selection setting
* pushed the lost --precision switch fr anon to test iAUTOMATIC2022-08-291-4/+8
|
* forgot to remove debug messagesAUTOMATIC2022-08-281-4/+0
|
* support for generating images on video cards with 4GBAUTOMATIC2022-08-281-4/+86
|
* Option to not save grid for single images for #22AUTOMATIC2022-08-281-1/+3
|
* Merge pull request #21 from orionaskatu/patch-1AUTOMATIC11112022-08-281-2/+2
|\ | | | | Typo StableDiffuion
| * Typo StableDiffuionorionaskatu2022-08-281-2/+2
| | | | | | Small typo StableDiffuionModelHijack() => StableDiffusionModelHijack()
* | Queue concurrency 1 to prevent CUDA OOMorionaskatu2022-08-281-0/+1
|/ | | | | Mandatory for me as I have a RTX 2070 (8Gb) and I get CUDA OOM if two users launch jobs at the same time. I can also use multiple tabs and jobs will be queued. You may not want it to be the default though.
* support for running custom code (primarily to generate various labeled grids)AUTOMATIC2022-08-281-48/+97
| | | | export for 4chan option
* split draw_prompt_matrix into two: generalized grid annotation and actual ↵AUTOMATIC2022-08-281-82/+56
| | | | | | prompt matrix disabled saving samples for SD upscale
* add upscaler modes for #19AUTOMATIC2022-08-281-1/+68
|
* fixed all lines PyCharm was nagging me aboutAUTOMATIC2022-08-271-274/+287
| | | | | | fixed input verification not working properly with long textual inversion tokens in some cases (plus it will prevent incorrect outputs for forks that use the :::: prompt weighing method) changed process_images to object class with same fields as args it was previously accepting changed options system to make it possible to explicitly specify gradio objects with args
* Implementation for SD upscale.AUTOMATIC2022-08-271-24/+154
|
* implementation for attention using [] and ()AUTOMATIC2022-08-271-23/+56
|
* fix gfpgan oom on 6GBCraftyawesome2022-08-261-0/+1
| | | | force a gc if out of memory
* fix a bug with wrong row count in prompt matrixAUTOMATIC2022-08-261-5/+6
|
* added samples to img2imgAUTOMATIC2022-08-261-8/+10
| | | | fixed a bug with sampler selection (oops)
* Renamed GFPGAN to extrasAUTOMATIC2022-08-261-21/+76
| | | | Added Real-ESRGAN to extras tab
* Add Denoising Strength to output parameters in the output textAUTOMATIC2022-08-261-7/+19
|
* option to add prompt matrix variable text parts to start of the prompt ↵AUTOMATIC2022-08-261-5/+10
| | | | rather than the end
* extra samplers from K-diffusionAUTOMATIC2022-08-251-23/+32
|
* textual inversion embeddings supportAUTOMATIC2022-08-251-102/+329
| | | | settings tab
* Check for the embedding managerdogewanwan2022-08-241-1/+2
|
* Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webuidogewanwan2022-08-241-25/+79
|\
| * add execution timings to outputAUTOMATIC2022-08-241-8/+34
| | | | | | | | change the text output element to HTML
| * save image generation params into text chunks for png imagesAUTOMATIC2022-08-241-17/+23
| |
| * commandline options to control saved file type/quality/namesAUTOMATIC2022-08-241-6/+24
| |
| * Merge branch 'master' into masterAUTOMATIC11112022-08-241-26/+72
| |\
| * | torch_gc/empty cache after generationhlky2022-08-241-2/+5
| | | | | | | | | | | | | | | added torch_gc() which calls both cuda.empty_cache() and cuda.ipc_collect() called before and after generation
| * | jpg grid, named gridhlky2022-08-241-1/+2
| | | | | | | | | | | | Grid file named with seed and prompt, output as jpg
* | | Textual inversion supportdogewanwan2022-08-241-6/+19
| |/ |/|
* | loopback mode for img2imgAUTOMATIC2022-08-241-25/+71
|/ | | | commandline options for grid filetypes and max batch count
* gfpgan dir for the guide's directory namesAUTOMATIC2022-08-241-2/+2
| | | | fix a bug in image resizing
* added resizing modesAUTOMATIC2022-08-241-2/+39
| | | | added more info into readme
* remove remote image as sample for img2img (it will now use a local image if ↵AUTOMATIC2022-08-241-1/+4
| | | | you have one, none otherwise)
* hide gradio progressbar for about 10% speed increase on my GPU; a ↵AUTOMATIC2022-08-241-1/+12
| | | | commandline option to prevent hiding
* fixed a possible issue with older versions of PILAUTOMATIC2022-08-231-1/+2
|
* --no-half commandline option to disable .half()AUTOMATIC2022-08-231-1/+2
|
* added prompt verification: if it's too long, a warning is returned in the ↵AUTOMATIC2022-08-231-0/+34
| | | | text field along with the part of prompt that has been truncated
* Added prompt matrix to img2imgAUTOMATIC2022-08-231-128/+134
| | | | refactoring: separated duplicate code from img2img and txt2img into a single function
* Prompt matrix now draws text like in demo.AUTOMATIC2022-08-231-45/+84
|
* additional picture for prompt matrixAUTOMATIC2022-08-231-68/+69
| | | | | proper seeds for img2img a bit of refactoring
* silence the warning from transformersAUTOMATIC2022-08-231-12/+22
| | | | add feature demonstrations to readme
* added prompt matrix featureAUTOMATIC2022-08-221-41/+127
| | | | | | | all images in batches now have proper seeds, not just the first one added code to remove bad characters from filenames added code to flag output which writes it to csv and saves images renamed some fields in UI for clarity
* fixed bug with images not resizing for img2imgAUTOMATIC2022-08-221-91/+109
| | | | | | | added GFPGAN as an option for img2img added GFPGAN as a tab added autodetection for row counts for grids, enabled by default removed Fixed Code sampling because no one can figure out what it does; maybe someone will be upset by removal and will tell me
* firstAUTOMATIC2022-08-221-0/+404
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-01 10:12:15 +0000