Remove BSRGAN from --use-cpu, add SwinIR

Author: brkirch

modules/devices.py

@@ -45,7 +45,7 @@ def enable_tf32():
 
 errors.run(enable_tf32, "Enabling TF32")
 
-device = device_interrogate = device_gfpgan = device_bsrgan = device_esrgan = device_scunet = device_codeformer = None
+device = device_interrogate = device_gfpgan = device_swinir = device_esrgan = device_scunet = device_codeformer = None
 dtype = torch.float16
 dtype_vae = torch.float16
 

modules/shared.py

@@ -58,7 +58,7 @@
 parser.add_argument("--opt-split-attention-invokeai", action='store_true', help="force-enables InvokeAI's cross-attention layer optimization. By default, it's on when cuda is unavailable.")
 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("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
-parser.add_argument("--use-cpu", nargs='+',choices=['all', 'sd', 'interrogate', 'gfpgan', 'bsrgan', 'esrgan', 'scunet', 'codeformer'], help="use CPU as torch device for specified modules", default=[], type=str.lower)
+parser.add_argument("--use-cpu", nargs='+',choices=['all', 'sd', 'interrogate', 'gfpgan', 'swinir', 'esrgan', 'scunet', 'codeformer'], help="use CPU as torch device for specified modules", default=[], type=str.lower)
 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)
@@ -96,8 +96,8 @@
     "outdir_save",
 ]
 
-devices.device, devices.device_interrogate, devices.device_gfpgan, devices.device_bsrgan, devices.device_esrgan, devices.device_scunet, devices.device_codeformer = \
-(devices.cpu if any(y in cmd_opts.use_cpu for y in [x, 'all']) else devices.get_optimal_device() for x in ['sd', 'interrogate', 'gfpgan', 'bsrgan', 'esrgan', 'scunet', 'codeformer'])
+devices.device, devices.device_interrogate, devices.device_gfpgan, devices.device_swinir, devices.device_esrgan, devices.device_scunet, devices.device_codeformer = \
+(devices.cpu if any(y in cmd_opts.use_cpu for y in [x, 'all']) else devices.get_optimal_device() for x in ['sd', 'interrogate', 'gfpgan', 'swinir', 'esrgan', 'scunet', 'codeformer'])
 
 device = devices.device
 weight_load_location = None if cmd_opts.lowram else "cpu"

modules/swinir_model.py

@@ -7,8 +7,8 @@
 from basicsr.utils.download_util import load_file_from_url
 from tqdm import tqdm
 
-from modules import modelloader
-from modules.shared import cmd_opts, opts, device
+from modules import modelloader, devices
+from modules.shared import cmd_opts, opts
 from modules.swinir_model_arch import SwinIR as net
 from modules.swinir_model_arch_v2 import Swin2SR as net2
 from modules.upscaler import Upscaler, UpscalerData
@@ -42,7 +42,7 @@ def do_upscale(self, img, model_file):
         model = self.load_model(model_file)
         if model is None:
             return img
-        model = model.to(device)
+        model = model.to(devices.device_swinir)
         img = upscale(img, model)
         try:
             torch.cuda.empty_cache()
@@ -111,7 +111,7 @@ def upscale(
     img = img[:, :, ::-1]
     img = np.moveaxis(img, 2, 0) / 255
     img = torch.from_numpy(img).float()
-    img = img.unsqueeze(0).to(device)
+    img = img.unsqueeze(0).to(devices.device_swinir)
     with torch.no_grad(), precision_scope("cuda"):
         _, _, h_old, w_old = img.size()
         h_pad = (h_old // window_size + 1) * window_size - h_old
@@ -139,8 +139,8 @@ def inference(img, model, tile, tile_overlap, window_size, scale):
     stride = tile - tile_overlap
     h_idx_list = list(range(0, h - tile, stride)) + [h - tile]
     w_idx_list = list(range(0, w - tile, stride)) + [w - tile]
-    E = torch.zeros(b, c, h * sf, w * sf, dtype=torch.half, device=device).type_as(img)
-    W = torch.zeros_like(E, dtype=torch.half, device=device)
+    E = torch.zeros(b, c, h * sf, w * sf, dtype=torch.half, device=devices.device_swinir).type_as(img)
+    W = torch.zeros_like(E, dtype=torch.half, device=devices.device_swinir)
 
     with tqdm(total=len(h_idx_list) * len(w_idx_list), desc="SwinIR tiles") as pbar:
         for h_idx in h_idx_list: