Bing-su / adetailer

Auto detecting, masking and inpainting with detection model.
GNU Affero General Public License v3.0
4.2k stars 329 forks source link

[Bug]: a1111 forge not showing soft inpainting on adetailer #700

Closed BenDes21 closed 2 months ago

BenDes21 commented 2 months ago

Describe the bug

Hi there, I added soft_inpainting in the Script names to apply to ADetailer in the setting option of adetailer. After restart I still see the normal inpainting tab only inside the Adetailer Extension.

Steps to reproduce

added soft_inpainting in the Script names to apply to ADetailer settings restart

Screenshots

Untitled

Console logs, from start to end.

[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 10685.84 MB ... Done.
Skipping unconditional conditioning when CFG = 1. Negative Prompts are ignored.
[Unload] Trying to free 16779.36 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10686.19 MB ... Unload model IntegratedAutoencoderKL Done.
[Memory Management] Target: KModel, Free GPU: 10848.57 MB, Model Require: 12119.51 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: -2294.94 MB, CPU Swap Loaded (blocked method): 3576.38 MB, GPU Loaded: 8543.13 MB
Moving model(s) has taken 2.68 seconds
100%|████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00,  1.60it/s]
[Unload] Trying to free 1231.84 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2284.73 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 2284.73 MB, Model Require: 159.87 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1100.85 MB, All loaded to GPU.
Moving model(s) has taken 0.13 seconds

0: 640x480 1 face_yolo, 8.1ms
Speed: 3.0ms preprocess, 8.1ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 480)
[Unload] Trying to free 3534.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 2054.15 MB ... Unload model KModel Current free memory is 10618.07 MB ... Done.
Memory cleanup has taken 3.17 seconds
[LORA] Loaded C:\Users\Admin\Documents\stable-diffusion-webui\models\Lora\JRRhandwriting.safetensors for KModel-UNet with 494 keys at weight 0.3 (skipped 0 keys) with on_the_fly = True
[Unload] Trying to free 13746.75 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10683.51 MB ... Unload model IntegratedAutoencoderKL Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 10846.89 MB, Model Require: 9786.73 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 36.16 MB, All loaded to GPU.
Moving model(s) has taken 2.63 seconds
Distilled CFG Scale: 3.5
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 1052.97 MB ... Done.
Distilled CFG Scale: 3.5
[Unload] Trying to free 17229.96 MB for cuda:0 with 0 models keep loaded ... Current free memory is 1047.96 MB ... Unload model JointTextEncoder Done.
[Memory Management] Target: KModel, Free GPU: 10837.88 MB, Model Require: 12119.51 MB, Previously Loaded: 0.00 MB, Inference Require: 1187.88 MB, Remaining: -2469.50 MB, CPU Swap Loaded (blocked method): 3805.88 MB, GPU Loaded: 8313.63 MB
Moving model(s) has taken 7.36 seconds
100%|██████████████████████████████████████████████████████████████████████████████████| 18/18 [01:18<00:00,  4.38s/it]

List of installed extensions

No response

dosubot[bot] commented 2 months ago

Hello there, @BenDes21! I'm here to help you with any bugs, questions, or contributions you may have. Let's tackle this issue together!

To address the issue of the soft_inpainting script not showing up in the ADetailer extension, ensure that you have correctly added the script name in the settings and that the script is compatible with ADetailer. Here are the steps to verify and troubleshoot:

  1. Verify Script Name Configuration: Ensure that you have added soft_inpainting to the ad_script_names setting as a comma-separated list. The configuration should look something like this:

    shared.opts.add_option(
       "ad_script_names",
       shared.OptionInfo(
           default="soft_inpainting",
           label="Script names to apply to ADetailer (separated by comma)",
           component=gr.Textbox,
           component_args={"placeholder": "comma-separated list of script names", "interactive": True},
           section=section,
       ),
    )
  2. Restart the WebUI: After making changes to the settings, ensure that you restart the stable diffusion webui to apply the new configuration.

  3. Check for Compatibility: Ensure that the soft_inpainting script is compatible with ADetailer. There might be specific dependencies or compatibility requirements that need to be met. Unfortunately, I couldn't find specific information on the dependencies for soft_inpainting within the repository [1].

  4. Console Logs: Review the console logs for any errors or warnings related to loading the soft_inpainting script. This can provide clues if there are issues with the script itself or its integration.

If the issue persists, you might need to check if the soft_inpainting script is correctly implemented and compatible with the current version of ADetailer.

To continue talking to Dosu, mention @dosu.