Upload weights, notebooks, sample images

.gitattributes

@@ -74,3 +74,4 @@ sample_images/sampleimage_6.png filter=lfs diff=lfs merge=lfs -text
 sample_images/sampleimage_7.png filter=lfs diff=lfs merge=lfs -text
 sample_images/sampleimage_8.png filter=lfs diff=lfs merge=lfs -text
 sample_images/sampleimage_9.png filter=lfs diff=lfs merge=lfs -text
+notebooks/UnReflectAnything.ipynb filter=lfs diff=lfs merge=lfs -text

notebooks/UnReflectAnything.ipynb

@@ -1,485 +1,3 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# UnReflectAnything API & CLI Examples\n",
-        "---\n",
-        "\n",
-        "### 1. Installation and assets download\n",
-        "Ensure you have installed UnReflectAnything with \n",
-        "```bash\n",
-        "pip install unreflectanything\n",
-        "```\n",
-        "this will also install the CLI, which is also callable with aliases `unreflect` and `ura`. Verify installation and check the version with:\n",
-        "```bash\n",
-        "unreflectanything --help\n",
-        "```\n",
-        "```bash\n",
-        "unreflect --version\n",
-        "```\n",
-        "```bash\n",
-        "ura --version\n",
-        "```"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 31,
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "Using device: cuda\n"
-          ]
-        }
-      ],
-      "source": [
-        "import torch\n",
-        "from pathlib import Path\n",
-        "\n",
-        "# Import UnreflectAnything!\n",
-        "import unreflectanything\n",
-        "\n",
-        "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
-        "print(f\"Using device: {device}\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "`pip install`ing UnReflectAnything does not download the pretrained model weights. Download them with the cli command\n",
-        "```bash\n",
-        "unrefleactanything download --weights\n",
-        "```\n",
-        "or"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 32,
-      "metadata": {},
-      "outputs": [
-        {
-          "data": {
-            "application/vnd.jupyter.widget-view+json": {
-              "model_id": "e2614e279f5f40609b18ac82d696b01d",
-              "version_major": 2,
-              "version_minor": 0
-            },
-            "text/plain": [
-              "Fetching 4 files:   0%|          | 0/4 [00:00<?, ?it/s]"
-            ]
-          },
-          "metadata": {},
-          "output_type": "display_data"
-        },
-        {
-          "data": {
-            "application/vnd.jupyter.widget-view+json": {
-              "model_id": "7293fbadfcc74c438a3cb5a0e4df1ac2",
-              "version_major": 2,
-              "version_minor": 0
-            },
-            "text/plain": [
-              "weights/diffuse_decoder.pt:   0%|          | 0.00/418M [00:00<?, ?B/s]"
-            ]
-          },
-          "metadata": {},
-          "output_type": "display_data"
-        },
-        {
-          "data": {
-            "application/vnd.jupyter.widget-view+json": {
-              "model_id": "f1253cb4b21d48c2b0c3780f4c4060ef",
-              "version_major": 2,
-              "version_minor": 0
-            },
-            "text/plain": [
-              "weights/token_inpainter.pt:   0%|          | 0.00/307M [00:00<?, ?B/s]"
-            ]
-          },
-          "metadata": {},
-          "output_type": "display_data"
-        },
-        {
-          "data": {
-            "application/vnd.jupyter.widget-view+json": {
-              "model_id": "74ed792f61264beab4a890ea5ede8a58",
-              "version_major": 2,
-              "version_minor": 0
-            },
-            "text/plain": [
-              "weights/highlight_decoder.pt:   0%|          | 0.00/54.8M [00:00<?, ?B/s]"
-            ]
-          },
-          "metadata": {},
-          "output_type": "display_data"
-        },
-        {
-          "data": {
-            "application/vnd.jupyter.widget-view+json": {
-              "model_id": "1ea92cd82ad34af68f06be823dd12060",
-              "version_major": 2,
-              "version_minor": 0
-            },
-            "text/plain": [
-              "weights/full_model_weights.pt:   0%|          | 0.00/3.55G [00:00<?, ?B/s]"
-            ]
-          },
-          "metadata": {},
-          "output_type": "display_data"
-        },
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "Weights saved to /home/arota/.cache/unreflectanything/weights\n"
-          ]
-        }
-      ],
-      "source": [
-        "weights_dir = unreflectanything.download(\"weights\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "511c670a",
-      "metadata": {},
-      "source": [
-        "Download some sample images which will be used in this notebook with \n",
-        "```bash\n",
-        "unrefleactanything download --images\n",
-        "```\n",
-        "or"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "e0c60b28",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "images_dir = unreflectanything.download(\"images\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "36417577",
-      "metadata": {},
-      "source": [
-        "### 2. Running UnReflectAnything with pretrained weights"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "c318961c",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Instantating the pretrained default UnreflectAnything model. \n",
-        "unreflect = unreflectanything.model(device=device)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "448d5456",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from PIL import Image\n",
-        "import numpy as np\n",
-        "\n",
-        "# Building a simple dataloader on a simple dataset that loads from a dir of images\n",
-        "sample_dataset = unreflectanything.ImageDirDataset(images_dir)\n",
-        "sample_dataloader = torch.utils.data.DataLoader(\n",
-        "    sample_dataset, batch_size=1, shuffle=False\n",
-        ")\n",
-        "\n",
-        "# Threshold and Dilation in inpaint mask can be overridden; defaults 0.2 and 40\n",
-        "THRESHOLD = 0.2\n",
-        "DILATION = 40\n",
-        "\n",
-        "# Process and display only N images out of the full sample dataset\n",
-        "DISPLAY_N_IMAGES = 2\n",
-        "\n",
-        "outputs = []\n",
-        "for batch in sample_dataloader:\n",
-        "    # Forward pass\n",
-        "    batch_output = unreflect(\n",
-        "        batch.to(device), return_dict=True, threshold=THRESHOLD, dilation=DILATION\n",
-        "    )\n",
-        "    outputs.append(batch_output)\n",
-        "    if len(outputs) >= DISPLAY_N_IMAGES:\n",
-        "        break\n",
-        "\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "98c60bf4",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Helper: Convert tensor [H, W, C] in [0,1] float32 to uint8 to display them \n",
-        "def tensor_to_uint8_img(t):\n",
-        "    arr = t.permute(1, 2, 0).detach().numpy()\n",
-        "    arr = np.clip(arr, 0, 1)\n",
-        "    arr = (arr * 255).round().astype(np.uint8)\n",
-        "    return arr\n",
-        "\n",
-        "# Plotting a collage of the input, the diffuse output, and the highlight mask\n",
-        "for input_batch, output_batch in zip(sample_dataloader, outputs):\n",
-        "    concat_images = torch.cat(\n",
-        "        [\n",
-        "            input_batch.cpu(),\n",
-        "            output_batch[\"diffuse\"].cpu(),\n",
-        "            output_batch[\"highlight\"].repeat(1, 3, 1, 1).cpu(), # \n",
-        "        ],\n",
-        "        dim=3,\n",
-        "    )\n",
-        "    for sample in concat_images:\n",
-        "        img_uint8 = tensor_to_uint8_img(sample)\n",
-        "        display(Image.fromarray(img_uint8))\n",
-        "    # break\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "cf0e6ac6",
-      "metadata": {},
-      "source": [
-        "### 3. Inference API and CLI endpoint\n",
-        "The `inference` wrapper instantiates the UnReflectAnything model and calls its forward function is a single API call. It either:\n",
-        "- Inputs a batched image tensor and outputs a batched image tensor\n",
-        "- Inputs the path to an image (or directory of images) and saves the output results at a given path (of file or directory)\n",
-        "- Inputs the path to an image and outputs a batched image tensor \n",
-        "\n",
-        "Some example CLI calls:\n",
-        "```bash\n",
-        "unreflect inference path/to/image/dir/ -o output/dir/ --threshold 0.3 --dilation 40\n",
-        "```\n",
-        "```bash\n",
-        "unreflect inference path/to/image.png -o path/to/output.png --threshold 0.3 --dilation 40\n",
-        "```"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Pick a sample image from the downloaded assets. `input` can also be the path to a dir\n",
-        "input_path = list(images_dir.glob(\"*.png\"))[0]\n",
-        "print(\"Input file: \", input_path)\n",
-        "# Specify the outptut name. If `input` is a path to a dir, `output` should be too.\n",
-        "output_path = Path(\"output_example.png\").resolve()\n",
-        "print(\"Output file: \", output_path)\n",
-        "\n",
-        "unreflectanything.inference(\n",
-        "    input=input_path,\n",
-        "    output=output_path,\n",
-        "    device=device,\n",
-        "    threshold=THRESHOLD, \n",
-        "    dilation=DILATION,  \n",
-        ")\n",
-        "\n",
-        "# Loading the saved output and original input from files, then displaying them\n",
-        "input_img = Image.open(input_path).convert(\"RGB\")\n",
-        "output_img = Image.open(output_path).convert(\"RGB\")\n",
-        "\n",
-        "def to_tensor(img):\n",
-        "    return torch.from_numpy(np.array(img)).permute(2, 0, 1).float() / 255.\n",
-        "\n",
-        "input_tensor = to_tensor(input_img)\n",
-        "output_tensor = to_tensor(output_img)\n",
-        "concat = torch.cat([input_tensor, output_tensor], dim=2)\n",
-        "concat_uint8 = (concat.permute(1,2,0).numpy() * 255).clip(0,255).astype(np.uint8)\n",
-        "display(Image.fromarray(concat_uint8))"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "5118ea92",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(\"Equivalent CLI command:\\n\")\n",
-        "print(f\"unreflect inference {input_path} -o {output_path} --threshold {THRESHOLD} --dilation {DILATION}\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "562c17f1",
-      "metadata": {},
-      "source": [
-        "`inference` initializes the model every time by default. To run it without this step, pass them model to the API call"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "89fbbf62",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Pick a sample image from the downloaded assets. `input` can also be the path to a dir\n",
-        "input_path = list(images_dir.glob(\"*.png\"))[6]\n",
-        "# Specify the outptu name\n",
-        "output_path = Path(\"output_example.png\")\n",
-        "                   \n",
-        "unreflectanything.inference(\n",
-        "    model=unreflect, # <<<<<<<<< Pass the model instance and it won't be loaded at every `inference` call\n",
-        "    input=input_path,\n",
-        "    output=output_path,\n",
-        "    device=device,\n",
-        "    threshold=THRESHOLD, \n",
-        "    dilation=DILATION,  \n",
-        ")\n",
-        "\n",
-        "# Loading the saved output and original input from files, then displaying them\n",
-        "input_img = Image.open(input_path).convert(\"RGB\")\n",
-        "output_img = Image.open(output_path).convert(\"RGB\")\n",
-        "\n",
-        "def to_tensor(img):\n",
-        "    return torch.from_numpy(np.array(img)).permute(2, 0, 1).float() / 255.\n",
-        "\n",
-        "input_tensor = to_tensor(input_img)\n",
-        "output_tensor = to_tensor(output_img)\n",
-        "concat = torch.cat([input_tensor, output_tensor], dim=2)\n",
-        "concat_uint8 = (concat.permute(1,2,0).numpy() * 255).clip(0,255).astype(np.uint8)\n",
-        "display(Image.fromarray(concat_uint8))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "57441af0",
-      "metadata": {},
-      "source": [
-        "### 4. The Cache Directory\n",
-        "\n",
-        "`unreflectanything download` saves the downloaded asset in your system cache. Print this path with\n",
-        "```bash\n",
-        "unreflectanything cache --dir\n",
-        "```\n",
-        "or clear the cache with \n",
-        "```bash\n",
-        "unreflectanything cache --clear\n",
-        "```\n",
-        "The same endopoints are also on the API"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "b331050d",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "unreflectanything.cache(\"dir\")  # Also unreflectanything.cache()\n",
-        "unreflectanything.cache(\"clear\")\n",
-        "# unreflectanything.cache.clear()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 4. Verify Assets\n",
-        "\n",
-        "You can verify that the weights are correctly downloaded and loadable."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "is_valid = unreflectanything.verify(\"weights\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### CLI Equivalent\n",
-        "\n",
-        "```bash\n",
-        "unreflect verify --weights\n",
-        "```\n",
-        "```bash\n",
-        "unreflect verify --weights\n",
-        "```"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "85947e38",
-      "metadata": {},
-      "outputs": [],
-      "source": []
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## 5. Cite\n",
-        "\n",
-        "If you use UnReflectAnything in your research, please cite it:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(ura.cite(format=\"bibtex\"))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### CLI Equivalent\n",
-        "\n",
-        "```bash\n",
-        "unreflect cite --bibtex\n",
-        "```"
-      ]
-    }
-  ],
-  "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
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9be5cfa9f72f715a1a043bf88e201ada87c4344b18356e14b89f13c79f63213
+size 12164640