multiple fixes in response to preflight testing bug reports

- updated environment-mac.yml #932
- use the upstream GFPGAN library now that issues with color-changing fixed
  and facial recognition improved #905
- preload_models fixed to download additional models needed by gfpgan

.gitignore

@@ -196,3 +196,6 @@ checkpoints
 .vscode/
 gfpgan/
 models/ldm/stable-diffusion-v1/model.sha256
+
+# GFPGAN model files
+gfpgan/

environment-mac.yml

@@ -3,12 +3,12 @@ channels:
   - pytorch
   - conda-forge
 dependencies:
-  - python==3.10.5
+  - python==3.9.13
   - pip==22.2.2
 
   # pytorch left unpinned
-  - pytorch
+  - pytorch==1.12.1
-  - torchvision
+  - torchvision==0.13.1
 
   # I suggest to keep the other deps sorted for convenience.
   # To determine what the latest versions should be, run:
@@ -27,13 +27,12 @@ dependencies:
   - imgaug==0.4.0
   - kornia==0.6.7
   - mpmath==1.2.1
-  - nomkl
+  - nomkl=1.0
   - numpy==1.23.2
   - omegaconf==2.1.1
   - openh264==2.3.0
   - onnx==1.12.0
   - onnxruntime==1.12.1
-  - protobuf==3.19.4
   - pudb==2022.1
   - pytorch-lightning==1.7.5
   - scipy==1.9.1
@@ -42,22 +41,22 @@ dependencies:
   - tensorboard==2.10.0
   - torchmetrics==0.9.3
   - pip:
-    - flask==2.1.3
+      - flask==2.1.3
-    - flask_socketio==5.3.0
+      - flask_socketio==5.3.0
-    - flask_cors==3.0.10
+      - flask_cors==3.0.10
-    - dependency_injector==4.40.0
+      - dependency_injector==4.40.0
-    - eventlet
+      - eventlet==0.33.1
-    - opencv-python==4.6.0
+      - opencv-python==4.6.0
-    - protobuf==3.20.1
+      - protobuf==3.19.5
-    - realesrgan==0.2.5.0
+      - realesrgan==0.2.5.0
-    - send2trash==1.8.0
+      - send2trash==1.8.0
-    - test-tube==0.7.5
+      - test-tube==0.7.5
-    - transformers==4.21.2
+      - transformers==4.21.2
-    - torch-fidelity==0.3.0
+      - torch-fidelity==0.3.0
-    - -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
+      - -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
-    - -e git+https://github.com/openai/CLIP.git@main#egg=clip
+      - -e git+https://github.com/openai/CLIP.git@main#egg=clip
-    - -e git+https://github.com/Birch-san/k-diffusion.git@mps#egg=k_diffusion
+      - -e git+https://github.com/Birch-san/k-diffusion.git@mps#egg=k_diffusion
-    - -e git+https://github.com/lstein/GFPGAN@fix-dark-cast-images#egg=gfpgan
+      - -e git+https://github.com/TencentARC/GFPGAN.git#egg=gfpgan
-    - -e .
+      - -e .
 variables:
   PYTORCH_ENABLE_MPS_FALLBACK: 1

environment.yml

@@ -36,5 +36,5 @@ dependencies:
     - -e git+https://github.com/openai/CLIP.git@main#egg=clip
     - -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
     - -e git+https://github.com/Birch-san/k-diffusion.git@mps#egg=k_diffusion
-    - -e git+https://github.com/lstein/GFPGAN@fix-dark-cast-images#egg=gfpgan
+    - -e git+https://github.com/TencentARC/GFPGAN.git#egg=gfpgan
     - -e .

requirements-linux-arm64.txt

@@ -20,6 +20,6 @@ torchmetrics==0.6.0
 transformers==4.19.2
 -e git+https://github.com/openai/CLIP.git@main#egg=clip
 -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
-git+https://github.com/lstein/k-diffusion.git@master#egg=k-diffusion
+-e git+https://github.com/lstein/k-diffusion.git@master#egg=k-diffusion
--e git+https://github.com/lstein/GFPGAN@fix-dark-cast-images#egg=gfpgan
+-e git+https://github.com/TencentARC/GFPGAN.git#egg=gfpgan
 -e .

requirements.txt

@@ -33,4 +33,4 @@ dependency_injector==4.40.0
 eventlet
 git+https://github.com/openai/CLIP.git@main#egg=clip
 git+https://github.com/Birch-san/k-diffusion.git@mps#egg=k-diffusion
-git+https://github.com/lstein/GFPGAN@fix-dark-cast-images#egg=gfpgan
+git+https://github.com/TencentARC/GFPGAN.git#egg=gfpgan

scripts/preload_models.py

@@ -15,13 +15,13 @@ import urllib.request
 transformers.logging.set_verbosity_error()
 
 # this will preload the Bert tokenizer fles
-print('preloading bert tokenizer...')
+print('preloading bert tokenizer...', end='')
 
 tokenizer = BertTokenizerFast.from_pretrained('bert-base-uncased')
 print('...success')
 
 # this will download requirements for Kornia
-print('preloading Kornia requirements (ignore the deprecation warnings)...')
+print('preloading Kornia requirements...', end='')
 with warnings.catch_warnings():
     warnings.filterwarnings('ignore', category=DeprecationWarning)
     import kornia
@@ -29,12 +29,12 @@ print('...success')
 
 version = 'openai/clip-vit-large-patch14'
 
-print('preloading CLIP model (Ignore the deprecation warnings)...')
+print('preloading CLIP model...',end='')
 sys.stdout.flush()
 
 tokenizer = CLIPTokenizer.from_pretrained(version)
 transformer = CLIPTextModel.from_pretrained(version)
-print('\n\n...success')
+print('...success')
 
 # In the event that the user has installed GFPGAN and also elected to use
 # RealESRGAN, this will attempt to download the model needed by RealESRGANer
@@ -47,7 +47,7 @@ except ModuleNotFoundError:
     pass
 
 if gfpgan:
-    print('Loading models from RealESRGAN and facexlib')
+    print('Loading models from RealESRGAN and facexlib...',end='')
     try:
         from realesrgan.archs.srvgg_arch import SRVGGNetCompact
         from facexlib.utils.face_restoration_helper import FaceRestoreHelper
@@ -65,28 +65,41 @@ if gfpgan:
         print('Error loading ESRGAN:')
         print(traceback.format_exc())
 
-    try:
+    print('Loading models from GFPGAN')
-        import urllib.request
+    import urllib.request
-        model_url  = 'https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth'
+    for model in (
-        model_dest = 'src/gfpgan/experiments/pretrained_models/GFPGANv1.4.pth'
+            [
+                'https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth',
+                'src/gfpgan/experiments/pretrained_models/GFPGANv1.4.pth'
+            ],
+            [
+                'https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_Resnet50_Final.pth',
+                './gfpgan/weights/detection_Resnet50_Final.pth'
+            ],
+            [
+                'https://github.com/xinntao/facexlib/releases/download/v0.2.2/parsing_parsenet.pth',
+                './gfpgan/weights/parsing_parsenet.pth'
+            ],
+    ):
+        model_url,model_dest  = model
+        try:
+            if not os.path.exists(model_dest):
+                print(f'Downloading gfpgan model file {model_url}...',end='')
+                os.makedirs(os.path.dirname(model_dest), exist_ok=True)
+                urllib.request.urlretrieve(model_url,model_dest)
+                print('...success')
+        except Exception:
+            import traceback
+            print('Error loading GFPGAN:')
+            print(traceback.format_exc())
 
-        if not os.path.exists(model_dest):
+print('preloading CodeFormer model file...',end='')
-            print('downloading gfpgan model file...')
-            os.makedirs(os.path.dirname(model_dest))
-            urllib.request.urlretrieve(model_url,model_dest)
-    except Exception:
-        import traceback
-        print('Error loading GFPGAN:')
-        print(traceback.format_exc())
-print('...success')
-
-print('preloading CodeFormer model file...')
 try:
         import urllib.request
         model_url  = 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth'
         model_dest = 'ldm/dream/restoration/codeformer/weights/codeformer.pth'
         if not os.path.exists(model_dest):
-            print('downloading codeformer model file...')
+            print('Downloading codeformer model file...')
             os.makedirs(os.path.dirname(model_dest), exist_ok=True)
             urllib.request.urlretrieve(model_url,model_dest)
 except Exception: