Upload test_model_card_template_t2i.ipynb

test_model_card_template_t2i.ipynb

@@ -0,0 +1,306 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "4mDGz9V6JC0a",
+        "outputId": "75309249-37c8-4ba6-e950-facc85a4c249"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
+            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
+            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
+            "  Building wheel for diffusers (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip install git+https://github.com/cosmo3769/diffusers@standardize-model-card-t2i -q"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!pip install --upgrade wandb -q"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "hWoT-7tLrC3X",
+        "outputId": "25b205fa-5723-41c4-bf0f-e6c0604c2c19"
+      },
+      "execution_count": 2,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.2/2.2 MB\u001b[0m \u001b[31m10.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m196.4/196.4 kB\u001b[0m \u001b[31m27.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m257.8/257.8 kB\u001b[0m \u001b[31m33.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.7/62.7 kB\u001b[0m \u001b[31m9.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25h"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import os\n",
+        "import wandb\n",
+        "from argparse import Namespace\n",
+        "from diffusers.utils import is_wandb_available, make_image_grid\n",
+        "from diffusers.utils.hub_utils import load_or_create_model_card, populate_model_card"
+      ],
+      "metadata": {
+        "id": "r0rK5JfUrAfc"
+      },
+      "execution_count": 3,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def save_model_card(\n",
+        "    args,\n",
+        "    repo_id: str,\n",
+        "    images=None,\n",
+        "    repo_folder=None,\n",
+        "):\n",
+        "    img_str = \"\"\n",
+        "    if len(images) > 0:\n",
+        "        image_grid = make_image_grid(images, 1, len(args.validation_prompts))\n",
+        "        image_grid.save(os.path.join(repo_folder, \"val_imgs_grid.png\"))\n",
+        "        img_str += \"![val_imgs_grid](./val_imgs_grid.png)\\n\"\n",
+        "\n",
+        "    model_description = f\"\"\"\n",
+        "# Text-to-image finetuning - {repo_id}\n",
+        "\n",
+        "This pipeline was finetuned from **{args.pretrained_model_name_or_path}** on the **{args.dataset_name}** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: {args.validation_prompts}: \\n\n",
+        "{img_str}\n",
+        "\n",
+        "## Pipeline usage\n",
+        "\n",
+        "You can use the pipeline like so:\n",
+        "\n",
+        "```python\n",
+        "from diffusers import DiffusionPipeline\n",
+        "import torch\n",
+        "\n",
+        "pipeline = DiffusionPipeline.from_pretrained(\"{repo_id}\", torch_dtype=torch.float16)\n",
+        "prompt = \"{args.validation_prompts[0]}\"\n",
+        "image = pipeline(prompt).images[0]\n",
+        "image.save(\"my_image.png\")\n",
+        "```\n",
+        "\n",
+        "## Training info\n",
+        "\n",
+        "These are the key hyperparameters used during training:\n",
+        "\n",
+        "* Epochs: {args.num_train_epochs}\n",
+        "* Learning rate: {args.learning_rate}\n",
+        "* Batch size: {args.train_batch_size}\n",
+        "* Gradient accumulation steps: {args.gradient_accumulation_steps}\n",
+        "* Image resolution: {args.resolution}\n",
+        "* Mixed-precision: {args.mixed_precision}\n",
+        "\n",
+        "\"\"\"\n",
+        "    wandb_info = \"\"\n",
+        "    if is_wandb_available():\n",
+        "        wandb_run_url = None\n",
+        "        if wandb.run is not None:\n",
+        "            wandb_run_url = wandb.run.url\n",
+        "\n",
+        "    if wandb_run_url is not None:\n",
+        "        wandb_info = f\"\"\"\n",
+        "More information on all the CLI arguments and the environment are available on your [`wandb` run page]({wandb_run_url}).\n",
+        "\"\"\"\n",
+        "\n",
+        "    model_description += wandb_info\n",
+        "\n",
+        "    model_card = load_or_create_model_card(\n",
+        "        repo_id_or_path=repo_id,\n",
+        "        from_training=True,\n",
+        "        license=\"creativeml-openrail-m\",\n",
+        "        base_model=args.pretrained_model_name_or_path,\n",
+        "        model_description=model_description,\n",
+        "        inference=True,\n",
+        "    )\n",
+        "\n",
+        "    tags = [\"stable-diffusion\", \"stable-diffusion-diffusers\", \"text-to-image\", \"diffusers\"]\n",
+        "    model_card = populate_model_card(model_card, tags=tags)\n",
+        "\n",
+        "    model_card.save(os.path.join(repo_folder, \"README.md\"))"
+      ],
+      "metadata": {
+        "id": "6mgnDhfzrTp4"
+      },
+      "execution_count": 4,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "args = Namespace(\n",
+        "    pretrained_model_name_or_path=\"runwayml/stable-diffusion-v1-5\",\n",
+        "    dataset_name=\"your_dataset_name\",\n",
+        "    validation_prompts=[\"prompt1\", \"prompt2\", \"prompt3\"],\n",
+        "    num_train_epochs=\"num_train_epochs\",\n",
+        "    learning_rate=\"lr\",\n",
+        "    train_batch_size=\"batch_size\",\n",
+        "    gradient_accumulation_steps=\"ga_steps\",\n",
+        "    resolution=\"img_resolution\",\n",
+        "    mixed_precision=\"boolean\"\n",
+        ")"
+      ],
+      "metadata": {
+        "id": "UfgqlRHw0hQE"
+      },
+      "execution_count": 5,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from diffusers.utils import load_image\n",
+        "\n",
+        "images = [\n",
+        "    load_image(\"https://huggingface.co/datasets/diffusers/docs-images/resolve/main/amused/A%20mushroom%20in%20%5BV%5D%20style.png\")\n",
+        "    for _ in range(3)\n",
+        "]\n",
+        "\n",
+        "save_model_card(\n",
+        "    args,\n",
+        "    repo_id=\"cosmo3769/test\",\n",
+        "    images=images,\n",
+        "    repo_folder=\".\",\n",
+        ")"
+      ],
+      "metadata": {
+        "id": "JTEDsOd_rm7-"
+      },
+      "execution_count": 6,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!cat README.md"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "NwCOmASdsUCT",
+        "outputId": "37a56224-e66a-4b51-8233-b9b40958539a"
+      },
+      "execution_count": 7,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "---\n",
+            "license: creativeml-openrail-m\n",
+            "library_name: diffusers\n",
+            "tags:\n",
+            "- stable-diffusion\n",
+            "- stable-diffusion-diffusers\n",
+            "- text-to-image\n",
+            "- diffusers\n",
+            "inference: true\n",
+            "base_model: runwayml/stable-diffusion-v1-5\n",
+            "---\n",
+            "\n",
+            "<!-- This model card has been generated automatically according to the information the training script had access to. You\n",
+            "should probably proofread and complete it, then remove this comment. -->\n",
+            "\n",
+            "\n",
+            "# Text-to-image finetuning - cosmo3769/test\n",
+            "\n",
+            "This pipeline was finetuned from **runwayml/stable-diffusion-v1-5** on the **your_dataset_name** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['prompt1', 'prompt2', 'prompt3']: \n",
+            "\n",
+            "![val_imgs_grid](./val_imgs_grid.png)\n",
+            "\n",
+            "\n",
+            "## Pipeline usage\n",
+            "\n",
+            "You can use the pipeline like so:\n",
+            "\n",
+            "```python\n",
+            "from diffusers import DiffusionPipeline\n",
+            "import torch\n",
+            "\n",
+            "pipeline = DiffusionPipeline.from_pretrained(\"cosmo3769/test\", torch_dtype=torch.float16)\n",
+            "prompt = \"prompt1\"\n",
+            "image = pipeline(prompt).images[0]\n",
+            "image.save(\"my_image.png\")\n",
+            "```\n",
+            "\n",
+            "## Training info\n",
+            "\n",
+            "These are the key hyperparameters used during training:\n",
+            "\n",
+            "* Epochs: num_train_epochs\n",
+            "* Learning rate: lr\n",
+            "* Batch size: batch_size\n",
+            "* Gradient accumulation steps: ga_steps\n",
+            "* Image resolution: img_resolution\n",
+            "* Mixed-precision: boolean\n",
+            "\n",
+            "\n",
+            "\n",
+            "## Intended uses & limitations\n",
+            "\n",
+            "#### How to use\n",
+            "\n",
+            "```python\n",
+            "# TODO: add an example code snippet for running this diffusion pipeline\n",
+            "```\n",
+            "\n",
+            "#### Limitations and bias\n",
+            "\n",
+            "[TODO: provide examples of latent issues and potential remediations]\n",
+            "\n",
+            "## Training details\n",
+            "\n",
+            "[TODO: describe the data used to train the model]"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "w7IqDNR72RGf"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}