Merge pull request #14477 from akx/spandrel-type-fix

Be more clear about Spandrel model nomenclature and types

5 files changed, 26 insertions, 21 deletions

diff --git a/extensions-builtin/SwinIR/scripts/swinir_model.py b/extensions-builtin/SwinIR/scripts/swinir_model.py
index aae159af..95c7ec64 100644
--- a/extensions-builtin/SwinIR/scripts/swinir_model.py
+++ b/extensions-builtin/SwinIR/scripts/swinir_model.py
@@ -71,7 +71,7 @@ class UpscalerSwinIR(Upscaler):
         else:
             filename = path
 
-        model = modelloader.load_spandrel_model(
+        model_descriptor = modelloader.load_spandrel_model(
             filename,
             device=self._get_device(),
             dtype=devices.dtype,
@@ -79,10 +79,10 @@ class UpscalerSwinIR(Upscaler):
         )
         if getattr(opts, 'SWIN_torch_compile', False):
             try:
-                model = torch.compile(model)
+                model_descriptor.model.compile()
             except Exception:
                 logger.warning("Failed to compile SwinIR model, fallback to JIT", exc_info=True)
-        return model
+        return model_descriptor
 
     def _get_device(self):
         return devices.get_device_for('swinir')
diff --git a/modules/gfpgan_model.py b/modules/gfpgan_model.py
index 48f8ad5e..445b0409 100644
--- a/modules/gfpgan_model.py
+++ b/modules/gfpgan_model.py
@@ -3,6 +3,8 @@ from __future__ import annotations
 import logging

 import os

 

+import torch

+

 from modules import (

     devices,

     errors,

@@ -25,7 +27,7 @@ class FaceRestorerGFPGAN(face_restoration_utils.CommonFaceRestoration):
     def get_device(self):

         return devices.device_gfpgan

 

-    def load_net(self) -> None:

+    def load_net(self) -> torch.Module:

         for model_path in modelloader.load_models(

             model_path=self.model_path,

             model_url=model_url,

@@ -34,13 +36,13 @@ class FaceRestorerGFPGAN(face_restoration_utils.CommonFaceRestoration):
             ext_filter=['.pth'],

         ):

             if 'GFPGAN' in os.path.basename(model_path):

-                net = modelloader.load_spandrel_model(

+                model = modelloader.load_spandrel_model(

                     model_path,

                     device=self.get_device(),

                     expected_architecture='GFPGAN',

                 ).model

-                net.different_w = True  # see https://github.com/chaiNNer-org/spandrel/pull/81

-                return net

+                model.different_w = True  # see https://github.com/chaiNNer-org/spandrel/pull/81

+                return model

         raise ValueError("No GFPGAN model found")

 

     def restore(self, np_image):

diff --git a/modules/modelloader.py b/modules/modelloader.py
index 0b89d682..a7194137 100644
--- a/modules/modelloader.py
+++ b/modules/modelloader.py
@@ -1,8 +1,9 @@
 from __future__ import annotations
 
+import importlib
 import logging
 import os
-import importlib
+from typing import TYPE_CHECKING
 from urllib.parse import urlparse
 
 import torch
@@ -10,6 +11,8 @@ import torch
 from modules import shared
 from modules.upscaler import Upscaler, UpscalerLanczos, UpscalerNearest, UpscalerNone
 
+if TYPE_CHECKING:
+    import spandrel
 
 logger = logging.getLogger(__name__)
 
@@ -140,19 +143,19 @@ def load_spandrel_model(
     *,
     device: str | torch.device | None,
     half: bool = False,
-    dtype: str | None = None,
+    dtype: str | torch.dtype | None = None,
     expected_architecture: str | None = None,
-):
+) -> spandrel.ModelDescriptor:
     import spandrel
-    model = spandrel.ModelLoader(device=device).load_from_file(path)
-    if expected_architecture and model.architecture != expected_architecture:
+    model_descriptor = spandrel.ModelLoader(device=device).load_from_file(path)
+    if expected_architecture and model_descriptor.architecture != expected_architecture:
         logger.warning(
-            f"Model {path!r} is not a {expected_architecture!r} model (got {model.architecture!r})",
+            f"Model {path!r} is not a {expected_architecture!r} model (got {model_descriptor.architecture!r})",
         )
     if half:
-        model = model.model.half()
+        model_descriptor.model.half()
     if dtype:
-        model = model.model.to(dtype=dtype)
-    model.eval()
-    logger.debug("Loaded %s from %s (device=%s, half=%s, dtype=%s)", model, path, device, half, dtype)
-    return model
+        model_descriptor.model.to(dtype=dtype)
+    model_descriptor.model.eval()
+    logger.debug("Loaded %s from %s (device=%s, half=%s, dtype=%s)", model_descriptor, path, device, half, dtype)
+    return model_descriptor
diff --git a/modules/realesrgan_model.py b/modules/realesrgan_model.py
index 65f2e880..4d35b695 100644
--- a/modules/realesrgan_model.py
+++ b/modules/realesrgan_model.py
@@ -36,14 +36,14 @@ class UpscalerRealESRGAN(Upscaler):
             errors.report(f"Unable to load RealESRGAN model {path}", exc_info=True)

             return img

 

-        mod = modelloader.load_spandrel_model(

+        model_descriptor = modelloader.load_spandrel_model(

             info.local_data_path,

             device=self.device,

             half=(not cmd_opts.no_half and not cmd_opts.upcast_sampling),

             expected_architecture="ESRGAN",  # "RealESRGAN" isn't a specific thing for Spandrel

         )

         return upscale_with_model(

-            mod,

+            model_descriptor,

             img,

             tile_size=opts.ESRGAN_tile,

             tile_overlap=opts.ESRGAN_tile_overlap,

diff --git a/modules/upscaler_utils.py b/modules/upscaler_utils.py
index dde5d7ad..174c9bc3 100644
--- a/modules/upscaler_utils.py
+++ b/modules/upscaler_utils.py
@@ -6,7 +6,7 @@ import torch
 import tqdm
 from PIL import Image
 
-from modules import devices, images
+from modules import images
 
 logger = logging.getLogger(__name__)