Hugging Face's logo

AiArtLab
/
simplevae2x

Diffusers
Safetensors
Model card Files
xet
Community
simplevae2x
File size: 9,634 Bytes 
e3d03e3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
187
188
189
190
191
192
193
 
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "7efc5ac3-1568-4d92-8361-e3ef6a00e9fd",
   "metadata": {},
   "outputs": [
    {
     "ename": "ImportError",
     "evalue": "cannot import name 'SwinIRForImageSuperResolution' from 'transformers' (/usr/local/lib/python3.12/dist-packages/transformers/__init__.py)",
     "output_type": "error",
     "traceback": [
      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
      "\u001b[31mImportError\u001b[39m                               Traceback (most recent call last)",
      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[1]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mtransformers\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m SwinIRForImageSuperResolution\n\u001b[32m      2\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mtorch\u001b[39;00m\n\u001b[32m      3\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mPIL\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m Image\n",
      "\u001b[31mImportError\u001b[39m: cannot import name 'SwinIRForImageSuperResolution' from 'transformers' (/usr/local/lib/python3.12/dist-packages/transformers/__init__.py)"
     ]
    }
   ],
   "source": [
    "from transformers import SwinIRForImageSuperResolution\n",
    "import torch\n",
    "from PIL import Image\n",
    "\n",
    "model = SwinIRForImageSuperResolution.from_pretrained(\"caidas/swinir-large-2x\")\n",
    "image = Image.open(\"/workspace/simplevae2x/123456789.jpg\")\n",
    "inputs = model.pixel_values(image, return_tensors=\"pt\")\n",
    "outputs = model(inputs)\n",
    "output_image = outputs.pixel_values[0].permute(1, 2, 0).numpy()\n",
    "output_image = (output_image * 255).astype(\"uint8\")\n",
    "Image.fromarray(output_image).save(\"output.jpg\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "dd10133d-ecfb-4bd5-8647-539aab4b1124",
   "metadata": {},
   "outputs": [
    {
     "ename": "ImportError",
     "evalue": "cannot import name 'RealESRGANForImageSuperResolution' from 'transformers' (/usr/local/lib/python3.12/dist-packages/transformers/__init__.py)",
     "output_type": "error",
     "traceback": [
      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
      "\u001b[31mImportError\u001b[39m                               Traceback (most recent call last)",
      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[2]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mtransformers\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m RealESRGANForImageSuperResolution, RealESRGANImageProcessor\n\u001b[32m      2\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mPIL\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m Image\n\u001b[32m      3\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mrequests\u001b[39;00m\n",
      "\u001b[31mImportError\u001b[39m: cannot import name 'RealESRGANForImageSuperResolution' from 'transformers' (/usr/local/lib/python3.12/dist-packages/transformers/__init__.py)"
     ]
    }
   ],
   "source": [
    "from transformers import RealESRGANForImageSuperResolution, RealESRGANImageProcessor\n",
    "from PIL import Image\n",
    "import requests\n",
    "\n",
    "# Загрузка модели и процессора\n",
    "model = RealESRGANForImageSuperResolution.from_pretrained(\"nateraw/real-esrgan\")\n",
    "processor = RealESRGANImageProcessor()\n",
    "\n",
    "# Загрузка и подготовка изображения\n",
    "url = \"http://images.cocodataset.org/val2017/000000039769.jpg\"\n",
    "image = Image.open(requests.get(url, stream=True).raw)\n",
    "\n",
    "# Предобработка изображения\n",
    "inputs = processor(images=image, return_tensors=\"pt\")\n",
    "\n",
    "# Инференс\n",
    "outputs = model(**inputs)\n",
    "\n",
    "# Постобработка и сохранение результата\n",
    "output = outputs.pixel_values[0].permute(1, 2, 0).numpy()\n",
    "output = processor.postprocess(output, output_type=\"pil\")\n",
    "output.save(\"output.jpg\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "7cc6d952-a5cb-44a7-80a8-a2cf279d00d0",
   "metadata": {},
   "outputs": [
    {
     "ename": "ModuleNotFoundError",
     "evalue": "No module named 'realesrgan'",
     "output_type": "error",
     "traceback": [
      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
      "\u001b[31mModuleNotFoundError\u001b[39m                       Traceback (most recent call last)",
      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[3]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mrealesrgan\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m RealESRGAN\n\u001b[32m      2\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mPIL\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m Image\n\u001b[32m      3\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mtorch\u001b[39;00m\n",
      "\u001b[31mModuleNotFoundError\u001b[39m: No module named 'realesrgan'"
     ]
    }
   ],
   "source": [
    "from realesrgan import RealESRGAN\n",
    "from PIL import Image\n",
    "import torch\n",
    "\n",
    "# Загружаем модель\n",
    "device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n",
    "model = RealESRGAN(device, scale=2)\n",
    "model.load_weights('RealESRGAN_x2.pth')  # если нет — скачай заранее\n",
    "\n",
    "# Открываем изображение\n",
    "image = Image.open('/workspace/simplevae2x/123456789.jpg').convert('RGB')\n",
    "\n",
    "# Апскейл\n",
    "sr_image = model.predict(image)\n",
    "\n",
    "# Сохраняем\n",
    "sr_image.save('output.png')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "87fb3261-550d-4df1-9cba-879be405cd4b",
   "metadata": {},
   "outputs": [
    {
     "ename": "ModuleNotFoundError",
     "evalue": "No module named 'realesrgan'",
     "output_type": "error",
     "traceback": [
      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
      "\u001b[31mModuleNotFoundError\u001b[39m                       Traceback (most recent call last)",
      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[4]\u001b[39m\u001b[32m, line 2\u001b[39m\n\u001b[32m      1\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mtorch\u001b[39;00m\n\u001b[32m----> \u001b[39m\u001b[32m2\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mrealesrgan\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m RealESRGANer\n\u001b[32m      3\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mbasicsr\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01marchs\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mrrdbnet_arch\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m RRDBNet\n\u001b[32m      4\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mPIL\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m Image\n",
      "\u001b[31mModuleNotFoundError\u001b[39m: No module named 'realesrgan'"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "from realesrgan import RealESRGANer\n",
    "from basicsr.archs.rrdbnet_arch import RRDBNet\n",
    "from PIL import Image\n",
    "\n",
    "# Настраиваем модель\n",
    "model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=2)\n",
    "upsampler = RealESRGANer(\n",
    "    scale=2,\n",
    "    model_path='RealESRGAN_x2plus.pth',\n",
    "    model=model,\n",
    "    half=torch.cuda.is_available()\n",
    ")\n",
    "\n",
    "# Загружаем изображение\n",
    "img = Image.open('input.jpg').convert('RGB')\n",
    "img = np.array(img)[..., ::-1]  # PIL -> BGR\n",
    "\n",
    "# Апскейлим\n",
    "output, _ = upsampler.enhance(img, outscale=2)\n",
    "\n",
    "# Сохраняем\n",
    "cv2.imwrite('output.png', output)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fc380493-5e87-45af-9be1-7bf0ee80f512",
   "metadata": {},
   "outputs": [],
   "source": [
    "!"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}