[Bug]: 컨트롤넷 모델 선택해도 사용 안하고 넘어갑니다.

[4w97euiosha]

Describe the bug

webui 업데이트, extensions 업데이트 후, adetailer 에서 컨트롤넷 모델, 모듈을 선택해도 preprocessing 하지 않고 넘어갑니다. extensions 언인스톨, 다시 인스톨해도 같은 증상입니다. 예전에는 preprocessing 한 메시지가 나왔는데, 로그에 안 나오고 그림도 이상하게 나옵니다.

Inpaint denoising strength 0.4 로 하면 잘 나옵니다.

3번째 스크린샷은, 컨트롤넷 사용해서 다른 그림을 run preprocessor 했을 때는, 정상적으로 작동 했습니다.

Steps to reproduce

Inpaint denoising strength 1 Use separate checkpoint ControlNet model

Screenshots

Console logs, from start to end.

venv "D:\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.11 (tags/v3.10.11:7d4cc5a, Apr  5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]
Version: v1.10.1
Commit hash: 82a973c04367123ae98bd9abdf80d9eda9b910e2
Launching Web UI with arguments: --theme dark
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
[-] ADetailer initialized. version: 24.8.0, num models: 24
ControlNet preprocessor location: D:\stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\downloads
2024-08-26 11:27:40,499 - ControlNet - INFO - ControlNet v1.1.455
Loading weights [76d618d143] from D:\stable-diffusion-webui\models\Stable-diffusion\240128a.safetensors
Creating model from config: D:\stable-diffusion-webui\configs\v1-inference.yaml
Loading VAE weights specified in settings: D:\stable-diffusion-webui\models\VAE\vae-ft-mse-840000-ema-pruned.vae.pt
Applying attention optimization: Doggettx... done.
Model loaded in 4.5s (load weights from disk: 0.2s, create model: 0.4s, apply weights to model: 3.2s, load VAE: 0.2s, calculate empty prompt: 0.2s).
2024-08-26 11:27:46,449 - ControlNet - INFO - ControlNet UI callback registered.
*Deforum ControlNet support: enabled*
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 22.6s (prepare environment: 3.6s, import torch: 5.4s, import gradio: 1.1s, setup paths: 0.8s, initialize shared: 0.3s, other imports: 0.8s, load scripts: 3.2s, create ui: 6.0s, gradio launch: 0.5s, app_started_callback: 0.7s).
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:05<00:00,  3.66it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:04<00:00,  4.06it/s]
0: 640x480 2 faces, 95.8ms
Speed: 3.0ms preprocess, 95.8ms inference, 19.0ms postprocess per image at shape (1, 3, 640, 480)
Reusing loaded model 240128a.safetensors [76d618d143] to load analogMadness_v70.safetensors [71652f47a2]
Loading weights [71652f47a2] from D:\stable-diffusion-webui\models\Stable-diffusion\analogMadness_v70.safetensors
Creating model from config: D:\stable-diffusion-webui\configs\v1-inference.yaml
Loading VAE weights specified in settings: D:\stable-diffusion-webui\models\VAE\vae-ft-mse-840000-ema-pruned.vae.pt
Applying attention optimization: Doggettx... done.
Model loaded in 3.3s (create model: 0.4s, apply weights to model: 2.5s, load VAE: 0.2s).
tiled upscale: 100%|█████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00,  3.03it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00,  8.48it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:04<00:00,  4.05it/s]
tiled upscale: 100%|█████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00,  8.64it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00,  8.80it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:04<00:00,  4.05it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:30<00:00,  1.53s/it]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:30<00:00,  4.06it/s]

List of installed extensions

screenshot

[dosubot[bot]]

안녕하세요, @4w97euiosha!

저는 Dosu 봇이에요. 버그를 해결하고 질문에 답해주며 기여자가 되는 데 도움을 드릴 수 있어요. 어떤 도움이 필요하신가요?

The issue you're experiencing with ControlNet not performing preprocessing in ADetailer after updating the web UI and extensions is likely due to the ControlNet option not being available in WEBUI versions lower than 1.6.0. Ensure that you are using WEBUI version 1.6.0 or higher. Additionally, verify that the ControlNet extension is properly initialized and available, and that the selected model and module are correctly configured in ADetailer ^[1].

If you are already using WEBUI version 1.6.0 or higher and the issue persists, make sure that the ControlNet extension is correctly installed and initialized. You can check the initialization in the logs for any errors related to ControlNet. If the initialization fails, ControlNet will not perform preprocessing ^[1].

Lastly, ensure that the selected ControlNet model and module are supported and correctly configured. The default values for ControlNet-related settings in ADetailer are:

• ad_controlnet_model: "None"
• ad_controlnet_module: "None"
• ad_controlnet_weight: 1.0
• ad_controlnet_guidance_start: 0.0
• ad_controlnet_guidance_end: 1.0

These settings can be overridden by providing different values when initializing the ADetailerArgs class ^[2][3].

To continue talking to Dosu, mention @dosu.

[Bing-su]

어제 이 문제를 발견하고 dev 브랜치에 이미 고쳐놨습니다. 컨트롤넷에 변경사항이 있었는데 반영이 안되어 있었습니다.

[4w97euiosha]

답변들 감사합니다.

[Bing-su]

@4w97euiosha 혹시 댓글 링크 다운로드 받진 않으셨죠? 지금 이렇게 바이러스 유포하는 공격이 있다고 하네요.

[4w97euiosha]

@4w97euiosha 혹시 댓글 링크 다운로드 받진 않으셨죠? 지금 이렇게 바이러스 유포하는 공격이 있다고 하네요.

그냥 업데이트 나오면 받을려고 해당 링크는 안 받았습니다. 신경 써 주셔서 감사합니다.