aboutsummaryrefslogtreecommitdiffstats
path: root/modules/interrogate.py
AgeCommit message (Collapse)AuthorLines
2024-01-27fix CLIP Interrogator topN regexw-e-w-1/+1
Co-Authored-By: Martin Rizzo <60830236+martin-rizzo@users.noreply.github.com>
2023-12-31change import statements for #14478AUTOMATIC1111-3/+2
2023-12-31Add utility to inspect a model's parameters (to get dtype/device)Aarni Koskela-1/+2
2023-08-22add --medvram-sdxlAUTOMATIC1111-3/+2
2023-07-03Add job argument to State.begin()Aarni Koskela-2/+1
2023-05-31rename print_error to report, use it with together with package nameAUTOMATIC-2/+1
2023-05-29Add & use modules.errors.print_error where currently printing exception info ↵Aarni Koskela-3/+2
by hand
2023-05-10fixes for B007AUTOMATIC-2/+2
2023-05-10ruff auto fixesAUTOMATIC-1/+1
2023-05-10manual fixes for ruffAUTOMATIC-1/+0
2023-05-09Fix up string formatting/concatenation to f-strings where feasibleAarni Koskela-2/+2
2023-04-29use exist_ok=True instead of checking if directory existsAUTOMATIC-2/+1
2023-04-25Fix CLIP FileExistsErrordarnell8-2/+3
2023-01-27add data-dir flag and set all user data directories based on itMax Audron-1/+1
2023-01-24remove fairscale requirement, add fake fairscale to make BLIP not complain ↵AUTOMATIC-1/+1
about it mk2
2023-01-24remove fairscale requirement, add fake fairscale to make BLIP not complain ↵AUTOMATIC-2/+9
about it
2023-01-24fix BLIP failing to import depending on configurationAUTOMATIC-1/+2
2023-01-23add option to skip interrogate categoriesVladimir Mandic-14/+18
2023-01-23improve interrogateVladimir Mandic-12/+17
2023-01-21make CLIP interrogator download original text files if the directory does ↵AUTOMATIC-14/+41
not exist remove random artist built-in extension (to re-added as a normal extension on demand) remove artists.csv (but what does it mean????????????????????) make interrogate buttons show Loading... when you click them
2023-01-03add state to interrogateVladimir Mandic-1/+3
2022-12-31initialize result so not to cause exception on empty resultsVladimir Mandic-1/+1
2022-12-24fix F541 f-string without any placeholdersYuval Aboulafia-1/+1
2022-12-03use modelloader for #4956AUTOMATIC-14/+8
2022-12-03Merge pull request #4956 from TiagoSantos81/offline_BLIPAUTOMATIC1111-1/+12
[CLIP interrogator] use local file, if available
2022-11-30Use devices.autocast instead of torch.autocastbrkirch-2/+1
2022-11-24[interrogator] mkdir checkTiago F. Santos-6/+10
2022-11-22[CLIP interrogator] use local file, if availableTiago F. Santos-1/+8
2022-10-31Added "--clip-models-path" switch to avoid using default "~/.cache/clip" and ↵mawr-2/+2
enable to run under unprivileged user without homedir
2022-10-21interrogate: Fix CLIP-interrogation on CPUPatryk Wychowaniec-3/+9
Currently, trying to perform CLIP interrogation on a CPU fails, saying: ``` RuntimeError: "slow_conv2d_cpu" not implemented for 'Half' ``` This merge request fixes this issue by detecting whether the target device is CPU and, if so, force-enabling `--no-half` and passing `device="cpu"` to `clip.load()` (which then does some extra tricks to ensure it works correctly on CPU).
2022-10-17make CLIP interrogate ranks output sane valuesAUTOMATIC-3/+3
2022-10-17Fix CLIP Interrogator and disable ranks for itDenkingOfficial-2/+2
2022-10-14Add 'interrogate' and 'all' choices to --use-cpubrkirch-7/+7
* Add 'interrogate' and 'all' choices to --use-cpu * Change type for --use-cpu argument to str.lower, so that choices are case insensitive
2022-10-11Interrogate: add option to include ranks in outputGreg Fuller-2/+5
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)
2022-10-08chore: Fix typosAidan Holland-2/+2
2022-10-02preprocessing for textual inversion addedAUTOMATIC-0/+1
2022-09-15fix for Error Interrogating when user has garbage in text files #479AUTOMATIC-1/+1
2022-09-12remove mistaken error messageAUTOMATIC-1/+1
2022-09-12memory optimization for CLIP interrogatorAUTOMATIC-5/+23
changed default cfg_scale to a higher value
2022-09-11add half() supporrt for CLIP interrogationAUTOMATIC-17/+24
2022-09-11CLIP interrogatorAUTOMATIC-0/+142