Merge pull request #1616 from brkirch/cpu-cmdline-opt

Add --use-cpu command line option

modules/bsrgan_model.py

@@ -8,7 +8,7 @@ import torch
 from basicsr.utils.download_util import load_file_from_url
 
 import modules.upscaler
-from modules import shared, modelloader
+from modules import devices, modelloader
 from modules.bsrgan_model_arch import RRDBNet
 from modules.paths import models_path
 
@@ -44,13 +44,13 @@ class UpscalerBSRGAN(modules.upscaler.Upscaler):
         model = self.load_model(selected_file)
         if model is None:
             return img
-        model.to(shared.device)
+        model.to(devices.device_bsrgan)
         torch.cuda.empty_cache()
         img = np.array(img)
         img = img[:, :, ::-1]
         img = np.moveaxis(img, 2, 0) / 255
         img = torch.from_numpy(img).float()
-        img = img.unsqueeze(0).to(shared.device)
+        img = img.unsqueeze(0).to(devices.device_bsrgan)
         with torch.no_grad():
             output = model(img)
         output = output.squeeze().float().cpu().clamp_(0, 1).numpy()

modules/devices.py

@@ -2,9 +2,9 @@ import contextlib
 
 import torch
 
-# has_mps is only available in nightly pytorch (for now), `getattr` for compatibility
 from modules import errors
 
+# has_mps is only available in nightly pytorch (for now), `getattr` for compatibility
 has_mps = getattr(torch, 'has_mps', False)
 
 cpu = torch.device("cpu")
@@ -34,8 +34,7 @@ def enable_tf32():
 
 errors.run(enable_tf32, "Enabling TF32")
 
-device = get_optimal_device()
+device = device_gfpgan = device_bsrgan = device_esrgan = device_scunet = device_codeformer = get_optimal_device()
-device_codeformer = cpu if has_mps else device
 dtype = torch.float16
 
 def randn(seed, shape):

modules/esrgan_model.py

@@ -6,8 +6,7 @@ from PIL import Image
 from basicsr.utils.download_util import load_file_from_url
 
 import modules.esrgam_model_arch as arch
-from modules import shared, modelloader, images
+from modules import shared, modelloader, images, devices
-from modules.devices import has_mps
 from modules.paths import models_path
 from modules.upscaler import Upscaler, UpscalerData
 from modules.shared import opts
@@ -97,7 +96,7 @@ class UpscalerESRGAN(Upscaler):
         model = self.load_model(selected_model)
         if model is None:
             return img
-        model.to(shared.device)
+        model.to(devices.device_esrgan)
         img = esrgan_upscale(model, img)
         return img
 
@@ -112,7 +111,7 @@ class UpscalerESRGAN(Upscaler):
             print("Unable to load %s from %s" % (self.model_path, filename))
             return None
 
-        pretrained_net = torch.load(filename, map_location='cpu' if has_mps else None)
+        pretrained_net = torch.load(filename, map_location='cpu' if shared.device.type == 'mps' else None)
         crt_model = arch.RRDBNet(3, 3, 64, 23, gc=32)
 
         pretrained_net = fix_model_layers(crt_model, pretrained_net)
@@ -127,7 +126,7 @@ def upscale_without_tiling(model, img):
     img = img[:, :, ::-1]
     img = np.moveaxis(img, 2, 0) / 255
     img = torch.from_numpy(img).float()
-    img = img.unsqueeze(0).to(shared.device)
+    img = img.unsqueeze(0).to(devices.device_esrgan)
     with torch.no_grad():
         output = model(img)
     output = output.squeeze().float().cpu().clamp_(0, 1).numpy()

modules/gfpgan_model.py

@@ -21,7 +21,7 @@ def gfpgann():
     global loaded_gfpgan_model
     global model_path
     if loaded_gfpgan_model is not None:
-        loaded_gfpgan_model.gfpgan.to(shared.device)
+        loaded_gfpgan_model.gfpgan.to(devices.device_gfpgan)
         return loaded_gfpgan_model
 
     if gfpgan_constructor is None:
@@ -53,7 +53,7 @@ def gfpgan_fix_faces(np_image):
     if model is None:
         return np_image
 
-    send_model_to(model, devices.device)
+    send_model_to(model, devices.device_gfpgan)
 
     np_image_bgr = np_image[:, :, ::-1]
     cropped_faces, restored_faces, gfpgan_output_bgr = model.enhance(np_image_bgr, has_aligned=False, only_center_face=False, paste_back=True)

modules/scunet_model.py

@@ -8,7 +8,7 @@ import torch
 from basicsr.utils.download_util import load_file_from_url
 
 import modules.upscaler
-from modules import shared, modelloader
+from modules import devices, modelloader
 from modules.paths import models_path
 from modules.scunet_model_arch import SCUNet as net
 
@@ -51,12 +51,12 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
         if model is None:
             return img
 
-        device = shared.device
+        device = devices.device_scunet
         img = np.array(img)
         img = img[:, :, ::-1]
         img = np.moveaxis(img, 2, 0) / 255
         img = torch.from_numpy(img).float()
-        img = img.unsqueeze(0).to(shared.device)
+        img = img.unsqueeze(0).to(device)
 
         img = img.to(device)
         with torch.no_grad():
@@ -69,7 +69,7 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
         return PIL.Image.fromarray(output, 'RGB')
 
     def load_model(self, path: str):
-        device = shared.device
+        device = devices.device_scunet
         if "http" in path:
             filename = load_file_from_url(url=self.model_url, model_dir=self.model_path, file_name="%s.pth" % self.name,
                                           progress=True)

modules/shared.py

@@ -12,7 +12,7 @@ import modules.interrogate
 import modules.memmon
 import modules.sd_models
 import modules.styles
-from modules.devices import get_optimal_device
+import modules.devices as devices
 from modules.paths import script_path, sd_path
 
 sd_model_file = os.path.join(script_path, 'model.ckpt')
@@ -46,6 +46,7 @@ parser.add_argument("--ldsr-models-path", type=str, help="Path to directory with
 parser.add_argument("--opt-split-attention", action='store_true', help="force-enables cross-attention layer optimization. By default, it's on for torch.cuda and off for other torch devices.")
 parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
 parser.add_argument("--opt-split-attention-v1", action='store_true', help="enable older version of split attention optimization that does not consume all the VRAM it can find")
+parser.add_argument("--use-cpu", nargs='+',choices=['SD', 'GFPGAN', 'BSRGAN', 'ESRGAN', 'SCUNet', 'CodeFormer'], help="use CPU as torch device for specified modules", default=[])
 parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
 parser.add_argument("--port", type=int, help="launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available", default=None)
 parser.add_argument("--show-negative-prompt", action='store_true', help="does not do anything", default=False)
@@ -63,7 +64,11 @@ parser.add_argument("--enable-console-prompts", action='store_true', help="print
 
 
 cmd_opts = parser.parse_args()
-device = get_optimal_device()
+
+devices.device, devices.device_gfpgan, devices.device_bsrgan, devices.device_esrgan, devices.device_scunet, devices.device_codeformer = \
+(devices.cpu if x in cmd_opts.use_cpu else devices.get_optimal_device() for x in ['SD', 'GFPGAN', 'BSRGAN', 'ESRGAN', 'SCUNet', 'CodeFormer'])
+
+device = devices.device
 
 batch_cond_uncond = cmd_opts.always_batch_cond_uncond or not (cmd_opts.lowvram or cmd_opts.medvram)
 parallel_processing_allowed = not cmd_opts.lowvram and not cmd_opts.medvram