diff options
author | Greg Fuller <gfuller23@gmail.com> | 2022-10-12 01:02:41 +0000 |
---|---|---|
committer | Greg Fuller <gfuller23@gmail.com> | 2022-10-12 01:02:41 +0000 |
commit | d717eb079cd6b7fa7a4f97c0a10d400bdec753fb (patch) | |
tree | 5e63e2a59b4f0de00bf3b7cb960e4f86c23b3be0 /modules/deepbooru.py | |
parent | 6be32b31d181e42c639dad3451229aa7b9cfd1cf (diff) | |
download | stable-diffusion-webui-gfx803-d717eb079cd6b7fa7a4f97c0a10d400bdec753fb.tar.gz stable-diffusion-webui-gfx803-d717eb079cd6b7fa7a4f97c0a10d400bdec753fb.tar.bz2 stable-diffusion-webui-gfx803-d717eb079cd6b7fa7a4f97c0a10d400bdec753fb.zip |
Interrogate: add option to include ranks in output
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)
Diffstat (limited to 'modules/deepbooru.py')
-rw-r--r-- | modules/deepbooru.py | 14 |
1 files changed, 9 insertions, 5 deletions
diff --git a/modules/deepbooru.py b/modules/deepbooru.py index 7e3c0618..32d741e2 100644 --- a/modules/deepbooru.py +++ b/modules/deepbooru.py @@ -3,7 +3,7 @@ from concurrent.futures import ProcessPoolExecutor from multiprocessing import get_context -def _load_tf_and_return_tags(pil_image, threshold): +def _load_tf_and_return_tags(pil_image, threshold, include_ranks): import deepdanbooru as dd import tensorflow as tf import numpy as np @@ -52,12 +52,16 @@ def _load_tf_and_return_tags(pil_image, threshold): if result_dict[tag] >= threshold: if tag.startswith("rating:"): continue - result_tags_out.append(tag) + tag_formatted = tag.replace('_', ' ').replace(':', ' ') + if include_ranks: + result_tags_out.append(f'({tag_formatted}:{result_dict[tag]})') + else: + result_tags_out.append(tag_formatted) result_tags_print.append(f'{result_dict[tag]} {tag}') print('\n'.join(sorted(result_tags_print, reverse=True))) - return ', '.join(result_tags_out).replace('_', ' ').replace(':', ' ') + return ', '.join(result_tags_out) def subprocess_init_no_cuda(): @@ -65,9 +69,9 @@ def subprocess_init_no_cuda(): os.environ["CUDA_VISIBLE_DEVICES"] = "-1" -def get_deepbooru_tags(pil_image, threshold=0.5): +def get_deepbooru_tags(pil_image, threshold=0.5, include_ranks=False): context = get_context('spawn') with ProcessPoolExecutor(initializer=subprocess_init_no_cuda, mp_context=context) as executor: - f = executor.submit(_load_tf_and_return_tags, pil_image, threshold, ) + f = executor.submit(_load_tf_and_return_tags, pil_image, threshold, include_ranks) ret = f.result() # will rethrow any exceptions return ret
\ No newline at end of file |