[Bug]: Error interrogating CLIP from img2img

[c0nfess0r]

Is there an existing issue for this?

• [X] I have searched the existing issues and checked the recent builds/commits

What happened?

So I'm new to this tool and I've had success with most of the features, but I'm struggling to run CLIP Interrogation because of this error:

Error interrogating Traceback (most recent call last): File "D:\Automatic\stable-diffusion-webui\modules\interrogate.py", line 147, in interrogate self.load() File "D:\Automatic\stable-diffusion-webui\modules\interrogate.py", line 75, in load self.blip_model = self.load_blip_model() File "D:\Automatic\stable-diffusion-webui\modules\interrogate.py", line 55, in load_blip_model blip_model = models.blip.blip_decoder(pretrained=files[0], image_size=blip_image_eval_size, vit='base', med_config=os.path.join(paths.paths["BLIP"], "configs", "med_config.json")) File "D:\Automatic\stable-diffusion-webui\repositories\BLIP\models\blip.py", line 175, in blip_decoder model,msg = load_checkpoint(model,pretrained) File "D:\Automatic\stable-diffusion-webui\repositories\BLIP\models\blip.py", line 224, in load_checkpoint state_dict = checkpoint['model'] TypeError: 'NoneType' object is not subscriptable

I would appreciate some kind of suggestions on how to resolve this. Thank you

Steps to reproduce the problem

1. Run CLIP from img2img
2. Receive an error message

What should have happened?

Proper CLIP interrogation

Commit where the problem happens

ce9827a7c51a9f69bf62c634e35d34fa75ee1833

What platforms do you use to access UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

No response

Additional information, context and logs

No response

[Starlento]

Check whether you have model_base_caption_capfilt_large.pth in your models/BLIP dir. It should be 854 MB. I guess you lost internet connection when downloading this resource.

[c0nfess0r]

Thank you. I will try to redownload it.