{"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: fake_diffusion_with_gif"]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio "]}, {"cell_type": "code", "execution_count": null, "id": "288918539441861185822528903084949547379", "metadata": {}, "outputs": [], "source": ["# Downloading files from the demo repo\n", "import os\n", "!wget -q https://github.com/gradio-app/gradio/raw/main/demo/fake_diffusion_with_gif/image.gif"]}, {"cell_type": "code", "execution_count": null, "id": "44380577570523278879349135829904343037", "metadata": {}, "outputs": [], "source": ["import gradio as gr\n", "import numpy as np\n", "import time\n", "import os\n", "from PIL import Image\n", "import requests\n", "from io import BytesIO\n", "\n", "\n", "def create_gif(images):\n", "    pil_images = []\n", "    for image in images:\n", "        if isinstance(image, str):\n", "            response = requests.get(image)\n", "            image = Image.open(BytesIO(response.content))\n", "        else:\n", "            image = Image.fromarray((image * 255).astype(np.uint8))\n", "        pil_images.append(image)\n", "    fp_out = os.path.join(os.path.abspath(''), \"image.gif\")\n", "    img = pil_images.pop(0)\n", "    img.save(fp=fp_out, format='GIF', append_images=pil_images,\n", "            save_all=True, duration=400, loop=0)\n", "    return fp_out\n", "\n", "\n", "def fake_diffusion(steps):\n", "    images = []\n", "    for _ in range(steps):\n", "        time.sleep(1)\n", "        image = np.random.random((600, 600, 3))\n", "        images.append(image)\n", "        yield image, gr.Image(visible=False)\n", "\n", "    time.sleep(1)\n", "    image = \"https://gradio-builds.s3.amazonaws.com/diffusion_image/cute_dog.jpg\"\n", "    images.append(image)\n", "    gif_path = create_gif(images)\n", "\n", "    yield image, gr.Image(value=gif_path, visible=True)\n", "\n", "\n", "demo = gr.Interface(fake_diffusion,\n", "                    inputs=gr.Slider(1, 10, 3, step=1),\n", "                    outputs=[\"image\", gr.Image(label=\"All Images\", visible=False)])\n", "demo.queue()\n", "\n", "if __name__ == \"__main__\":\n", "    demo.launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}