black controlnet screen[Bug]:

[incubusspiral]

Is there an existing issue for this?

• [X] I have searched the existing issues and checked the recent builds/commits of both this extension and the webui

What happened?

black screen appears when performing a pose in controlnet, controlnet settings are correct, removed browser extensions, disabled nan chek from webui bat, image size 512x512, updated video card drivers, using latest models for controlnet, installed web ui from automatic 1111, also tried on webui portable, It worked a couple times and then it stopped, after uninstalling another error Unet got tensor with all NaNs, gpu 1650 super, cpu i3 10100f

Steps to reproduce the problem

decided to make an image of the pose, I chose openpose and inserted the image.

What should have happened?

was to make an image with the right pose

Commit where the problem happens

webui: controlnet:

What browsers do you use to access the UI ?

No response

Command Line Arguments

--lowvram --autolaunch --xformers --autolaunch --theme dark --no-half --disable-nan-check

List of enabled extensions

Console logs

From https://github.com/AUTOMATIC1111/stable-diffusion-webui
 * branch              master     -> FETCH_HEAD
Already up to date.
venv "C:\stablediffussion\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.5.2
Commit hash: c9c8485bc1e8720aba70f029d25cba1c4abf2b5c

Launching Web UI with arguments: --lowvram --autolaunch --xformers --autolaunch --theme dark --no-half --disable-nan-check
2023-08-31 05:07:26,687 - ControlNet - INFO - ControlNet v1.1.313
ControlNet preprocessor location: C:\stablediffussion\stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\downloads
2023-08-31 05:07:26,861 - ControlNet - INFO - ControlNet v1.1.313
Loading weights [9aba26abdf] from C:\stablediffussion\stable-diffusion-webui\models\Stable-diffusion\deliberate_v2.safetensors
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Creating model from config: C:\stablediffussion\stable-diffusion-webui\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Startup time: 16.6s (launcher: 5.1s, import torch: 4.5s, import gradio: 1.2s, setup paths: 1.4s, other imports: 1.3s, setup codeformer: 0.1s, load scripts: 1.7s, create ui: 0.5s, gradio launch: 0.7s).
Applying attention optimization: xformers... done.
Model loaded in 65.8s (load weights from disk: 0.8s, create model: 2.2s, apply weights to model: 59.6s, hijack: 0.1s, load textual inversion embeddings: 0.1s, calculate empty prompt: 2.8s).
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.5.2
Commit hash: c9c8485bc1e8720aba70f029d25cba1c4abf2b5c

Launching Web UI with arguments: --lowvram --autolaunch --xformers --autolaunch --theme dark --no-half --disable-nan-check
2023-08-31 05:14:09,553 - ControlNet - INFO - ControlNet v1.1.313
ControlNet preprocessor location: C:\stablediffussion\stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\downloads
2023-08-31 05:14:09,715 - ControlNet - INFO - ControlNet v1.1.313
Loading weights [9aba26abdf] from C:\stablediffussion\stable-diffusion-webui\models\Stable-diffusion\deliberate_v2.safetensors
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 15.6s (launcher: 4.8s, import torch: 4.5s, import gradio: 1.2s, setup paths: 1.2s, other imports: 1.2s, setup codeformer: 0.1s, load scripts: 1.8s, create ui: 0.5s, gradio launch: 0.3s).
Creating model from config: C:\stablediffussion\stable-diffusion-webui\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying attention optimization: xformers... done.
Model loaded in 48.7s (load weights from disk: 0.8s, create model: 0.6s, apply weights to model: 42.9s, move model to device: 1.2s, hijack: 1.8s, load textual inversion embeddings: 0.2s, calculate empty prompt: 1.1s).
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [03:17<00:00,  9.85s/it]
Total progress: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [01:54<00:00,  5.72s/it]
2023-08-31 05:18:53,390 - ControlNet - INFO - Loading model: control_v11p_sd15_openpose [cab727d4]██████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [01:54<00:00,  5.52s/it]
2023-08-31 05:19:05,408 - ControlNet - INFO - Loaded state_dict from [C:\stablediffussion\stable-diffusion-webui\models\ControlNet\control_v11p_sd15_openpose.pth]
2023-08-31 05:19:09,445 - ControlNet - INFO - Loading config: C:\stablediffussion\stable-diffusion-webui\extensions\sd-webui-controlnet\models\control_v11p_sd15_openpose.yaml
2023-08-31 05:19:22,413 - ControlNet - INFO - ControlNet model control_v11p_sd15_openpose [cab727d4] loaded.
2023-08-31 05:19:22,577 - ControlNet - INFO - Loading preprocessor: openpose_full
2023-08-31 05:19:22,579 - ControlNet - INFO - preprocessor resolution = 512
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [02:24<00:00,  7.25s/it]
Total progress: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [02:28<00:00,  7.44s/it]
Total progress: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [02:28<00:00,  6.43s/it]

Additional information

No response

[incubusspiral]

I tried the same thing with lowram without it.

[huchenlei]

It seems like openpose_full does not detect anything from the input image. You can try dw_openposes_full preprocessor which has better detection.

[incubusspiral]

God bless you, it's working.