Age | Commit message (Collapse) | Author | |
---|---|---|---|
2022-10-12 | xy_grid: Find hypernetwork by closest name | Milly | |
2022-10-12 | Merge branch 'master' into feature/scale_to | AUTOMATIC1111 | |
2022-10-12 | Ensure the directory exists before saving to it | brkirch | |
The directory for the images saved with the Save button may still not exist, so it needs to be created prior to opening the log.csv file. | |||
2022-10-12 | just add the deepdanbooru settings unconditionally | AUTOMATIC | |
2022-10-12 | Merge remote-tracking branch 'origin/steve3d' | AUTOMATIC | |
2022-10-12 | Merge pull request #2143 from JC-Array/deepdanbooru_pre_process | AUTOMATIC1111 | |
deepbooru tags for textual inversion preproccessing | |||
2022-10-12 | Truncate error text to fix service lockup / stall | Greg Fuller | |
What: * Update wrap_gradio_call to add a limit to the maximum amount of text output Why: * wrap_gradio_call currently prints out a list of the arguments provided to the failing function. * if that function is save_image, this causes the entire image to be printed to stderr * If the image is large, this can cause the service to lock up while attempting to print all the text * It is easy to generate large images using the x/y plot script * it is easy to encounter image save exceptions, including if the output directory does not exist / cannot be written to, or if the file is too big * The huge amount of log spam is confusing and not particularly helpful | |||
2022-10-12 | create dir for hypernetworks | AUTOMATIC | |
2022-10-11 | Interrogate: add option to include ranks in output | Greg Fuller | |
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) | |||
2022-10-12 | Update shared.py | supersteve3d | |
Correct typo to "Unload VAE and CLIP from VRAM when training" in settings tab. | |||
2022-10-11 | resolved conflicts, moved settings under interrogate section, settings only ↵ | JC_Array | |
show if deepbooru flag is enabled | |||
2022-10-11 | Merge branch 'AUTOMATIC1111:master' into deepdanbooru_pre_process | JC-Array | |
2022-10-11 | reports that training with medvram is possible. | AUTOMATIC | |
2022-10-11 | add file based test | DepFA | |
2022-10-11 | Add files via upload | DepFA | |
2022-10-11 | spacing | DepFA | |
2022-10-11 | update imports | DepFA | |
2022-10-11 | correct conflict resolution typo | DepFA | |
2022-10-11 | apply lr schedule to hypernets | AUTOMATIC | |
2022-10-11 | remove old caption method | DepFA | |
2022-10-11 | shift embedding logic out of textual_inversion | DepFA | |
2022-10-11 | Merge branch 'learning_rate-scheduling' into learnschedule | AUTOMATIC1111 | |
2022-10-11 | remove embedding related image functions from images | DepFA | |
2022-10-11 | move embedding logic to separate file | DepFA | |
2022-10-11 | prevent extra modules from being saved/loaded with hypernet | AUTOMATIC | |
2022-10-11 | add an option to unload models during hypernetwork training to save VRAM | AUTOMATIC | |
2022-10-11 | produce error when training with medvram/lowvram enabled | AUTOMATIC | |
2022-10-11 | removed unneeded print | JC_Array | |
2022-10-11 | add option to select hypernetwork modules when creating | AUTOMATIC | |
2022-10-11 | Merge pull request #2201 from alg-wiki/textual__inversion | AUTOMATIC1111 | |
Textual Inversion: Preprocess and Training will only pick-up image files instead | |||
2022-10-11 | Use apply_hypernetwork function | brkirch | |
2022-10-11 | Add InvokeAI and lstein to credits, add back CUDA support | brkirch | |
2022-10-11 | Add check for psutil | brkirch | |
2022-10-11 | Add cross-attention optimization from InvokeAI | brkirch | |
* Add cross-attention optimization from InvokeAI (~30% speed improvement on MPS) * Add command line option for it * Make it default when CUDA is unavailable | |||
2022-10-11 | Merge pull request #2227 from papuSpartan/master | AUTOMATIC1111 | |
Refresh list of models/ckpts upon hitting restart gradio in the setti… | |||
2022-10-11 | Merge branch 'master' into embed-embeddings-in-images | DepFA | |
2022-10-11 | become even stricter with pickles | AUTOMATIC | |
no pickle shall pass thank you again, RyotaK | |||
2022-10-11 | move list refresh to webui.py and add stdout indicating it's doing so | papuSpartan | |
2022-10-11 | Merge branch 'master' into master | 不会画画的中医不是好程序员 | |
2022-10-11 | more renames | AUTOMATIC | |
2022-10-11 | rename hypernetwork dir to hypernetworks to prevent clash with an old ↵ | AUTOMATIC | |
filename that people who use zip instead of git clone will have | |||
2022-10-11 | Added new line at the end of ngrok.py | JamnedZ | |
2022-10-11 | Cleaned ngrok integration | JamnedZ | |
2022-10-11 | add a space holder | Ben | |
2022-10-11 | Layout fix | Ben | |
2022-10-11 | images history improvement | yfszzx | |
2022-10-11 | Fix typo in comments | Martin Cairns | |
2022-10-11 | Remove debug code for checking that first sigma value is same after code cleanup | Martin Cairns | |
2022-10-11 | Handle different parameters for DPM fast & adaptive | Martin Cairns | |
2022-10-11 | images history improvement | yfszzx | |