[Bug]: hand_yolov8n.pt [ADetailer] is stuck before finishing the generated image

Hunter9886 commented 2 months ago

Checklist

[ ] The issue exists after disabling all extensions
[X] The issue exists on a clean installation of webui
[X] The issue is caused by an extension, but I believe it is caused by a bug in the webui
[X] The issue exists in the current version of the webui
[X] The issue has not been reported before recently
[ ] The issue has been reported before but has not been fixed yet

What happened?

txt2img is working perfectly but when using (hand_yolov8n.pt) in Adetailer after 1.9.0 it doesn't finish the generated image and stays stuck.

Steps to reproduce the problem

1-Generate txt2img 2-use Adetailer extension 3-enable face_yolov8n.pt and hand_yolov8n.pt as a 2nd

What should have happened?

generated image succesfully without bugs or staying stuck

What browsers do you use to access the UI ?

Microsoft Edge

Sysinfo

sysinfo-2024-04-17-10-33.json

Console logs

C:\User\Desktop\stable-diffusion-webui-directml>git pull
Already up to date.
venv "C:\User\Desktop\stable-diffusion-webui-directml\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: v1.9.0-1-ge51a8494
Commit hash: e51a8494691acfbfa18d1989fa4b810a15bf10b1
Skipping onnxruntime installation.
Pulled changes for repository in 'C:\User\Desktop\stable-diffusion-webui-directml\extensions\adetailer':
Already up to date.

Pulled changes for repository in 'C:\User\stable-diffusion-webui-directml\extensions\sd-webui-3d-open-pose-editor':
Already up to date.

Pulled changes for repository in 'C:\User\Desktop\stable-diffusion-webui-directml\extensions\sd-webui-controlnet':
Already up to date.

Pulled changes for repository in 'C:\User\Desktop\stable-diffusion-webui-directml\extensions\sd-webui-reactor':
Already up to date.

Pulled changes for repository in 'C:\User\Desktop\stable-diffusion-webui-directml\extensions\Stable-Diffusion-Webui-Civitai-Helper':
Already up to date.

Pulled changes for repository in 'C:\User\Desktop\stable-diffusion-webui-directml\extensions\Stylez':
Already up to date.

Pulled changes for repository in 'C:\User\Desktop\stable-diffusion-webui-directml\extensions\ultimate-upscale-for-automatic1111':
Already up to date.

no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
C:\User\Desktop\stable-diffusion-webui-directml\venv\lib\site-packages\pytorch_lightning\utilities\distributed.py:258: LightningDeprecationWarning: `pytorch_lightning.utilities.distributed.rank_zero_only` has been deprecated in v1.8.1 and will be removed in v2.0.0. You can import it from `pytorch_lightning.utilities` instead.
  rank_zero_deprecation(
Launching Web UI with arguments: --skip-ort --use-directml --medvram --use-cpu-torch --no-half --precision full --no-half-vae --opt-split-attention-v1 --disable-nan-check --skip-version-check --update-all-extensions --theme dark --autolaunch
CHv1.8.4: Get Custom Model Folder
[-] ADetailer initialized. version: 24.4.1, num models: 10
ControlNet preprocessor location: C:\User\stable-diffusion-webui-directml\extensions\sd-webui-controlnet\annotator\downloads
2024-04-17 12:46:56,774 - ControlNet - INFO - ControlNet v1.1.443
2024-04-17 12:46:57,027 - ControlNet - INFO - ControlNet v1.1.443
12:46:57 - ReActor - STATUS - Running v0.7.0-b7 on Device: CPU
12:46:57 - ReActor - STATUS - Running v0.7.0-b7 on Device: CPU
Loading weights [62bb78983a] from C:\User\Desktop\stable-diffusion-webui-directml\models\Stable-diffusion\epicphotogasm_lastUnicorn.safetensors
CHv1.8.4: Set Proxy:
2024-04-17 12:46:58,933 - ControlNet - INFO - ControlNet UI callback registered.
Creating model from config: C:\User\Desktop\stable-diffusion-webui-directml\configs\v1-inference.yaml
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 40.7s (prepare environment: 40.3s, initialize shared: 2.2s, other imports: 0.5s, load scripts: 6.4s, create ui: 3.0s, gradio launch: 0.9s).
Loading VAE weights specified in settings: C:\User\\Desktop\stable-diffusion-webui-directml\models\VAE\vae-ft-mse-840000-ema-pruned.safetensors
Applying attention optimization: V1... done.
Model loaded in 29.3s (load weights from disk: 1.4s, create model: 0.9s, apply weights to model: 21.3s, apply float(): 1.0s, load VAE: 4.1s, calculate empty prompt: 0.5s).
100%|██████████████████████████████████████████████████████████████████████████████████| 30/30 [00:54<00:00,  1.81s/it]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 30/30 [00:42<00:00,  1.45s/it]
0: 640x640 1 face, 426.2ms
Speed: 26.3ms preprocess, 426.2ms inference, 17.4ms postprocess per image at shape (1, 3, 640, 640)
100%|██████████████████████████████████████████████████████████████████████████████████| 13/13 [00:18<00:00,  1.42s/it]

0: 640x640 2 hands, 195.2ms
Speed: 6.0ms preprocess, 195.2ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640)
100%|██████████████████████████████████████████████████████████████████████████████████| 13/13 [00:18<00:00,  1.39s/it]

(!!generated image stays stuck here at 13/13!!)

Additional information

is it because of 1.9.0 update of the webui? this has never happend with me when using ADetailer.

lshqqytiger commented 2 months ago

I think the reason is same as issue #443. Could you try again with the latest commits?

Hunter9886 commented 2 months ago

I think the reason is same as issue #443. Could you try again with the latest commits?

yes lastest commits fixed it, now txt2img finishes generating the Image and Adetailer is working again.

i will close this issue

@lshqqytiger thanks!

lshqqytiger / stable-diffusion-webui-amdgpu