1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
|
import logging
import sys
import numpy as np
import torch
from PIL import Image
from tqdm import tqdm
from modules import modelloader, devices, script_callbacks, shared
from modules.shared import opts, state
from modules.upscaler import Upscaler, UpscalerData
SWINIR_MODEL_URL = "https://github.com/JingyunLiang/SwinIR/releases/download/v0.0/003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR-L_x4_GAN.pth"
logger = logging.getLogger(__name__)
class UpscalerSwinIR(Upscaler):
def __init__(self, dirname):
self._cached_model = None # keep the model when SWIN_torch_compile is on to prevent re-compile every runs
self._cached_model_config = None # to clear '_cached_model' when changing model (v1/v2) or settings
self.name = "SwinIR"
self.model_url = SWINIR_MODEL_URL
self.model_name = "SwinIR 4x"
self.user_path = dirname
super().__init__()
scalers = []
model_files = self.find_models(ext_filter=[".pt", ".pth"])
for model in model_files:
if model.startswith("http"):
name = self.model_name
else:
name = modelloader.friendly_name(model)
model_data = UpscalerData(name, model, self)
scalers.append(model_data)
self.scalers = scalers
def do_upscale(self, img: Image.Image, model_file: str) -> Image.Image:
current_config = (model_file, opts.SWIN_tile)
device = self._get_device()
if self._cached_model_config == current_config:
model = self._cached_model
else:
try:
model = self.load_model(model_file)
except Exception as e:
print(f"Failed loading SwinIR model {model_file}: {e}", file=sys.stderr)
return img
self._cached_model = model
self._cached_model_config = current_config
img = upscale(
img,
model,
tile=opts.SWIN_tile,
tile_overlap=opts.SWIN_tile_overlap,
device=device,
)
devices.torch_gc()
return img
def load_model(self, path, scale=4):
if path.startswith("http"):
filename = modelloader.load_file_from_url(
url=path,
model_dir=self.model_download_path,
file_name=f"{self.model_name.replace(' ', '_')}.pth",
)
else:
filename = path
model = modelloader.load_spandrel_model(
filename,
device=self._get_device(),
dtype=devices.dtype,
)
if getattr(opts, 'SWIN_torch_compile', False):
try:
model = torch.compile(model)
except Exception:
logger.warning("Failed to compile SwinIR model, fallback to JIT", exc_info=True)
return model
def _get_device(self):
return devices.get_device_for('swinir')
def upscale(
img,
model,
*,
tile: int,
tile_overlap: int,
window_size=8,
scale=4,
device,
):
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(device, dtype=devices.dtype)
with torch.no_grad(), devices.autocast():
_, _, h_old, w_old = img.size()
h_pad = (h_old // window_size + 1) * window_size - h_old
w_pad = (w_old // window_size + 1) * window_size - w_old
img = torch.cat([img, torch.flip(img, [2])], 2)[:, :, : h_old + h_pad, :]
img = torch.cat([img, torch.flip(img, [3])], 3)[:, :, :, : w_old + w_pad]
output = inference(
img,
model,
tile=tile,
tile_overlap=tile_overlap,
window_size=window_size,
scale=scale,
device=device,
)
output = output[..., : h_old * scale, : w_old * scale]
output = output.data.squeeze().float().cpu().clamp_(0, 1).numpy()
if output.ndim == 3:
output = np.transpose(
output[[2, 1, 0], :, :], (1, 2, 0)
) # CHW-RGB to HCW-BGR
output = (output * 255.0).round().astype(np.uint8) # float32 to uint8
return Image.fromarray(output, "RGB")
def inference(
img,
model,
*,
tile: int,
tile_overlap: int,
window_size: int,
scale: int,
device,
):
# test the image tile by tile
b, c, h, w = img.size()
tile = min(tile, h, w)
assert tile % window_size == 0, "tile size should be a multiple of window_size"
sf = 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=devices.dtype, device=device).type_as(img)
W = torch.zeros_like(E, dtype=devices.dtype, device=device)
with tqdm(total=len(h_idx_list) * len(w_idx_list), desc="SwinIR tiles") as pbar:
for h_idx in h_idx_list:
if state.interrupted or state.skipped:
break
for w_idx in w_idx_list:
if state.interrupted or state.skipped:
break
in_patch = img[..., h_idx: h_idx + tile, w_idx: w_idx + tile]
out_patch = model(in_patch)
out_patch_mask = torch.ones_like(out_patch)
E[
..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
].add_(out_patch)
W[
..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
].add_(out_patch_mask)
pbar.update(1)
output = E.div_(W)
return output
def on_ui_settings():
import gradio as gr
shared.opts.add_option("SWIN_tile", shared.OptionInfo(192, "Tile size for all SwinIR.", gr.Slider, {"minimum": 16, "maximum": 512, "step": 16}, section=('upscaling', "Upscaling")))
shared.opts.add_option("SWIN_tile_overlap", shared.OptionInfo(8, "Tile overlap, in pixels for SwinIR. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}, section=('upscaling', "Upscaling")))
shared.opts.add_option("SWIN_torch_compile", shared.OptionInfo(False, "Use torch.compile to accelerate SwinIR.", gr.Checkbox, {"interactive": True}, section=('upscaling', "Upscaling")).info("Takes longer on first run"))
script_callbacks.on_ui_settings(on_ui_settings)
|
