Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+generated.png filter=lfs diff=lfs merge=lfs -text
+test.png filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/test-checkpoint.ipynb

@@ -0,0 +1,95 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4f62bfd9-5396-48e2-aac7-bdf639cab345",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "The config attributes {'block_out_channels': [128, 256, 512, 768, 768], 'force_upcast': False} were passed to AsymmetricAutoencoderKL, but are not expected and will be ignored. Please verify your config.json configuration file.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ok\n"
+     ]
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "\n",
+    "from torchvision import transforms, utils\n",
+    "\n",
+    "import diffusers\n",
+    "from diffusers import AsymmetricAutoencoderKL\n",
+    "\n",
+    "from diffusers.utils import load_image\n",
+    "\n",
+    "def crop_image_to_nearest_divisible_by_8(img):\n",
+    "    # Check if the image height and width are divisible by 8\n",
+    "    if img.shape[1] % 8 == 0 and img.shape[2] % 8 == 0:\n",
+    "        return img\n",
+    "    else:\n",
+    "        # Calculate the closest lower resolution divisible by 8\n",
+    "        new_height = img.shape[1] - (img.shape[1] % 8)\n",
+    "        new_width = img.shape[2] - (img.shape[2] % 8)\n",
+    "        \n",
+    "        # Use CenterCrop to crop the image\n",
+    "        transform = transforms.CenterCrop((new_height, new_width), interpolation=transforms.InterpolationMode.BILINEAR)\n",
+    "        img = transform(img).to(torch.float32).clamp(-1, 1)\n",
+    "        \n",
+    "        return img\n",
+    "        \n",
+    "to_tensor = transforms.ToTensor()\n",
+    "\n",
+    "device = \"cuda\"\n",
+    "dtype=torch.float16\n",
+    "vae = AsymmetricAutoencoderKL.from_pretrained(\"vae\",torch_dtype=dtype).to(device).eval()\n",
+    "\n",
+    "image = load_image(\"generated.png\")\n",
+    "\n",
+    "image = crop_image_to_nearest_divisible_by_8(to_tensor(image)).unsqueeze(0).to(device,dtype=dtype)\n",
+    "\n",
+    "upscaled_image = vae(image).sample\n",
+    "# Save the reconstructed image\n",
+    "utils.save_image(upscaled_image, \"test.png\")\n",
+    "print('ok')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7e3ad326-c410-44b6-a738-15b7f7e15075",
+   "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": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

test.ipynb

@@ -0,0 +1,95 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4f62bfd9-5396-48e2-aac7-bdf639cab345",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "The config attributes {'block_out_channels': [128, 256, 512, 768, 768], 'force_upcast': False} were passed to AsymmetricAutoencoderKL, but are not expected and will be ignored. Please verify your config.json configuration file.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ok\n"
+     ]
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "\n",
+    "from torchvision import transforms, utils\n",
+    "\n",
+    "import diffusers\n",
+    "from diffusers import AsymmetricAutoencoderKL\n",
+    "\n",
+    "from diffusers.utils import load_image\n",
+    "\n",
+    "def crop_image_to_nearest_divisible_by_8(img):\n",
+    "    # Check if the image height and width are divisible by 8\n",
+    "    if img.shape[1] % 8 == 0 and img.shape[2] % 8 == 0:\n",
+    "        return img\n",
+    "    else:\n",
+    "        # Calculate the closest lower resolution divisible by 8\n",
+    "        new_height = img.shape[1] - (img.shape[1] % 8)\n",
+    "        new_width = img.shape[2] - (img.shape[2] % 8)\n",
+    "        \n",
+    "        # Use CenterCrop to crop the image\n",
+    "        transform = transforms.CenterCrop((new_height, new_width), interpolation=transforms.InterpolationMode.BILINEAR)\n",
+    "        img = transform(img).to(torch.float32).clamp(-1, 1)\n",
+    "        \n",
+    "        return img\n",
+    "        \n",
+    "to_tensor = transforms.ToTensor()\n",
+    "\n",
+    "device = \"cuda\"\n",
+    "dtype=torch.float16\n",
+    "vae = AsymmetricAutoencoderKL.from_pretrained(\"vae\",torch_dtype=dtype).to(device).eval()\n",
+    "\n",
+    "image = load_image(\"generated.png\")\n",
+    "\n",
+    "image = crop_image_to_nearest_divisible_by_8(to_tensor(image)).unsqueeze(0).to(device,dtype=dtype)\n",
+    "\n",
+    "upscaled_image = vae(image).sample\n",
+    "# Save the reconstructed image\n",
+    "utils.save_image(upscaled_image, \"test.png\")\n",
+    "print('ok')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7e3ad326-c410-44b6-a738-15b7f7e15075",
+   "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": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

vae/config.json

@@ -0,0 +1,48 @@
+{
+  "_class_name": "AsymmetricAutoencoderKL",
+  "_diffusers_version": "0.33.1",
+  "_name_or_path": "simple_vae",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    768,
+    768
+  ],
+  "down_block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": false,
+  "in_channels": 3,
+  "latent_channels": 16,
+  "layers_per_down_block": 2,
+  "layers_per_up_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 1,
+  "up_block_out_channels": [
+    128,
+    256,
+    512,
+    768,
+    768
+  ],
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09af5fe391d8095fd1937160c5990f1da40d3f83b4836f25ca43699c3729de9
+size 349017470