With the new update to Auto1111, this plugin no longer works. about ddetailer HOT 9 CLOSED

see #54

from ddetailer.

Try this fork. https://github.com/mlhub-action/ddetailer
for torch: 2.0.0+cu118
mmcv_full-1.7.1
mmdet 2.28.2

from ddetailer.

Try this fork. https://github.com/mlhub-action/ddetailer for torch: 2.0.0+cu118 mmcv_full-1.7.1 mmdet 2.28.2

Also didn't work, but thanks to you I found an even better fork than that extension: https://github.com/Bing-su/adetailer it has more options and even interaction with controlnet inpaint

from ddetailer.

same here, I got this error today. any idea?

Launching Web UI with arguments: --xformers --deepdanbooru --autolaunch --no-half-vae
Error loading script: ddetailer.py
Traceback (most recent call last):
File "J:\AI\stable-diffusion-webui\modules\scripts.py", line 256, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "J:\AI\stable-diffusion-webui\modules\script_loading.py", line 11, in load_module
module_spec.loader.exec_module(module)
File "", line 883, in exec_module
File "", line 241, in call_with_frames_removed
File "J:\AI\stable-diffusion-webui\extensions\ddetailer\scripts\ddetailer.py", line 458, in
from mmdet.core import get_classes
File "J:\AI\stable-diffusion-webui\venv\lib\site-packages\mmdet\core_init.py", line 3, in
from .bbox import * # noqa: F401, F403
File "J:\AI\stable-diffusion-webui\venv\lib\site-packages\mmdet\core\bbox_init_.py", line 8, in
from .samplers import (BaseSampler, CombinedSampler,
File "J:\AI\stable-diffusion-webui\venv\lib\site-packages\mmdet\core\bbox\samplers_init_.py", line 12, in
from .score_hlr_sampler import ScoreHLRSampler
File "J:\AI\stable-diffusion-webui\venv\lib\site-packages\mmdet\core\bbox\samplers\score_hlr_sampler.py", line 3, in
from mmcv.ops import nms_match
File "J:\AI\stable-diffusion-webui\venv\lib\site-packages\mmcv\ops_init_.py", line 3, in
from .active_rotated_filter import active_rotated_filter
File "J:\AI\stable-diffusion-webui\venv\lib\site-packages\mmcv\ops\active_rotated_filter.py", line 10, in
ext_module = ext_loader.load_ext(
File "J:\AI\stable-diffusion-webui\venv\lib\site-packages\mmcv\utils\ext_loader.py", line 13, in load_ext
ext = importlib.import_module('mmcv.' + name)
File "C:\Users\taegi\AppData\Local\Programs\Python\Python310\lib\importlib_init_.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
ImportError: DLL load failed while importing _ext: The specified procedure could not be found.

from ddetailer.

It's because of the update to Torch 2.x, I believe. Sadly, it's likely it won't work again unless the author decides to come by, or someone forks it.

from ddetailer.

you can downgrade torch 1.13.x like as following

• force uninstall pytorch and install pytorch 1.13.x

  • Please see https://mmcv.readthedocs.io/en/latest/get_started/installation.html

• venv/scripts/activate

• install mmdet / mmcv_full

pip install mmdet==2.28.2
mim install mmcv-full

• run webui and check any error log msgs.

from ddetailer.

It's because of the update to Torch 2.x, I believe. Sadly, it's likely it won't work again unless the author decides to come by, or someone forks it.

The only mmcv version that supports Torch 2.x is mmcv 2.x (use mim install mmcv>=2 since they changed the package name from mmcv-full to mmcv ), which forces you to update mmdet to 3.x (pip install mmdet>=3), which forces you to port outdated config files to mmdet 3.x (see https://mmdetection.readthedocs.io/en/v3.0.0/migration/config_migration.html#migration-of-other-configurations) and also refactor inference_mmdet_bbox and inference_mmdet_segm. I've actually successfully refactored inference_mmdet_bbox and the config file for mmdet_anime-face_yolov3. For the from mmdet.core import get_classes line replace it with from mmdet.evaluation import get_classes

from ddetailer.

Could someone please create a fork of this extension?

from ddetailer.

Is this plugin works on AMD guys?

from ddetailer.