AUTOMATIC1111/stable-diffusion-webui · error · FileNotFoundError

Model file {path} not found

Error message

Model file {path} not found

What it means

HatModel.load_model refuses to proceed when the requested HAT upscaler path is not a regular file on disk, raising FileNotFoundError with the offending path. This is a pre-load sanity check before handing the file to modelloader.load_spandrel with expected_architecture='HAT'.

Source

Thrown at modules/hat_model.py:38

            self.scalers.append(scaler_data)

    def do_upscale(self, img, selected_model):
        try:
            model = self.load_model(selected_model)
        except Exception as e:
            print(f"Unable to load HAT model {selected_model}: {e}", file=sys.stderr)
            return img
        model.to(devices.device_esrgan)  # TODO: should probably be device_hat
        return upscale_with_model(
            model,
            img,
            tile_size=opts.ESRGAN_tile,  # TODO: should probably be HAT_tile
            tile_overlap=opts.ESRGAN_tile_overlap,  # TODO: should probably be HAT_tile_overlap
        )

    def load_model(self, path: str):
        if not os.path.isfile(path):
            raise FileNotFoundError(f"Model file {path} not found")
        return modelloader.load_spandrel_model(
            path,
            device=devices.device_esrgan,  # TODO: should probably be device_hat
            expected_architecture='HAT',
        )

View on GitHub (pinned to 82a973c043)

Solutions

1. Restore the HAT .pth file at the exact path shown in the error message (typically under models/HAT).
2. Hit refresh on the upscaler list so stale entries pointing at missing files are dropped.
3. Re-download the HAT model from its source into models/HAT if you no longer have it.

Example fix

import os

# before
model = hat.load_model('/stable-diffusion-webui/models/HAT/HAT_SRx4.pth')  # FileNotFoundError if absent

# after
path = '/stable-diffusion-webui/models/HAT/HAT_SRx4.pth'
if not os.path.isfile(path):
    raise SystemExit(f'Please place the HAT model at {path}')
model = hat.load_model(path)

import os

def load_hat_safe(path):
    if not os.path.isfile(path):
        raise SystemExit(f'HAT model missing at {path}; download it first')
    from modules.hat_model import HatModel
    return HatModel().load_model(path)

try:
    model = hat.load_model(path)
except FileNotFoundError as e:
    # path is in the message; prompt user or re-download
    raise SystemExit(f'{e}; place the HAT weights under models/HAT and retry')

When it happens

Trigger: Selecting a HAT upscaler entry whose recorded path does not exist — e.g. the models/HAT directory entry points at a deleted/moved file, or a custom path string is passed to load_model that was never validated.

Common situations: User deleted or moved .pth files under models/HAT while the UI list still cached the old entry; file is on an unmounted drive; typo in a manually configured model path.

Related errors

• RealESRGAN data missing: {scaler.local_data_path}
• DAT data missing: {scaler.local_data_path}
• Unable to find model info: {path}
• No GFPGAN model found
• Could not find checkpoint with name {p.refiner_checkpoint}

AI-assisted analysis of AUTOMATIC1111/stable-diffusion-webui@82a973c043 (2026-08-14). Data as JSON: /api/errors/68cb3a12771db583. Report an issue: GitHub.