aboutsummaryrefslogtreecommitdiffstats
path: root/modules/interrogate.py
Commit message (Collapse)AuthorAgeFilesLines
* add state to interrogateVladimir Mandic2023-01-031-1/+3
|
* initialize result so not to cause exception on empty resultsVladimir Mandic2022-12-311-1/+1
|
* fix F541 f-string without any placeholdersYuval Aboulafia2022-12-241-1/+1
|
* use modelloader for #4956AUTOMATIC2022-12-031-14/+8
|
* Merge pull request #4956 from TiagoSantos81/offline_BLIPAUTOMATIC11112022-12-031-1/+12
|\ | | | | [CLIP interrogator] use local file, if available
| * [interrogator] mkdir checkTiago F. Santos2022-11-241-6/+10
| |
| * [CLIP interrogator] use local file, if availableTiago F. Santos2022-11-221-1/+8
| |
* | Use devices.autocast instead of torch.autocastbrkirch2022-11-301-2/+1
|/
* Added "--clip-models-path" switch to avoid using default "~/.cache/clip" and ↵mawr2022-10-301-2/+2
| | | | enable to run under unprivileged user without homedir
* interrogate: Fix CLIP-interrogation on CPUPatryk Wychowaniec2022-10-211-3/+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).
* make CLIP interrogate ranks output sane valuesAUTOMATIC2022-10-171-3/+3
|
* Fix CLIP Interrogator and disable ranks for itDenkingOfficial2022-10-171-2/+2
|
* Add 'interrogate' and 'all' choices to --use-cpubrkirch2022-10-141-7/+7
| | | | | * Add 'interrogate' and 'all' choices to --use-cpu * Change type for --use-cpu argument to str.lower, so that choices are case insensitive
* Interrogate: add option to include ranks in outputGreg Fuller2022-10-121-2/+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)
* chore: Fix typosAidan Holland2022-10-081-2/+2
|
* preprocessing for textual inversion addedAUTOMATIC2022-10-021-0/+1
|
* fix for Error Interrogating when user has garbage in text files #479AUTOMATIC2022-09-151-1/+1
|
* remove mistaken error messageAUTOMATIC2022-09-121-1/+1
|
* memory optimization for CLIP interrogatorAUTOMATIC2022-09-121-5/+23
| | | | changed default cfg_scale to a higher value
* add half() supporrt for CLIP interrogationAUTOMATIC2022-09-111-17/+24
|
* CLIP interrogatorAUTOMATIC2022-09-111-0/+142
generated by cgit v1.2.3 (git 2.25.1) at 2025-04-29 23:12:38 +0000