Uploaded Text-to-Image.ipynb

Text_to_Image.ipynb

@@ -0,0 +1,121 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "gpuType": "T4"
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "accelerator": "GPU"
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "source": [
+        "import torch\n",
+        "from PIL import Image\n",
+        "from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline\n",
+        "from diffusers import StableDiffusionImg2ImgPipeline\n",
+        "from diffusers import EulerAncestralDiscreteScheduler\n",
+        "\n",
+        "#provide your Hugging Face Authentication token\n",
+        "#you can obtain your token from https://huggingface.co/settings/tokens\n",
+        "auth_token = input(\"Enter your Hugging Face token: \")\n",
+        "\n",
+        "###   image generation   ###\n",
+        "\n",
+        "#using stable diffusion version 2.1 for image generation\n",
+        "modelid = \"stabilityai/stable-diffusion-2-1\"\n",
+        "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
+        "\n",
+        "pipe = StableDiffusionPipeline.from_pretrained(\n",
+        "    modelid,\n",
+        "    revision=\"fp16\",\n",
+        "    torch_dtype= torch.float16,\n",
+        "    use_auth_token=auth_token,\n",
+        "    low_cpu_mem_usage=True\n",
+        ")\n",
+        "#using EulerAncestralDiscreteScheduler for sharper and detailed images\n",
+        "\n",
+        "pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)\n",
+        "\n",
+        "\n",
+        "###    image modification    ###\n",
+        "#using StableDiffusionImg2ImgPipeline for image to image generation\n",
+        "pipe.to(device)\n",
+        "\n",
+        "pipe_img2img = StableDiffusionImg2ImgPipeline.from_pretrained(\"stabilityai/stable-diffusion-2-1\", torch_dtype=torch.float16, low_cpu_mem_usage=True).to(device)\n",
+        "pipe_img2img.to(device)\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "6IveiamACvSG"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import gradio as gr\n",
+        "# Function to generate image from text\n",
+        "def generate_image(prompt, guidance_scale):\n",
+        "    global stored_image\n",
+        "    image = pipe(prompt, guidance_scale=guidance_scale).images[0]\n",
+        "    stored_image = image\n",
+        "    return image\n",
+        "\n",
+        "# Function to modify image (Img2Img)\n",
+        "def modify_image(prompt, strength=0.5):\n",
+        "    global stored_image\n",
+        "    if stored_image is None:\n",
+        "        return \"No generated image available. Generate an image first!\"\n",
+        "\n",
+        "    stored_image = stored_image.convert(\"RGB\")\n",
+        "    modified_image = pipe_img2img(prompt=prompt, image=stored_image, strength=strength, guidance_scale=8.5).images[0]\n",
+        "    return modified_image\n",
+        "\n",
+        "# Gradio UI\n",
+        "with gr.Blocks() as demo:\n",
+        "    gr.Markdown(\"# Stable Diffusion - Generate & Modify Images\")\n",
+        "    with gr.Group():\n",
+        "      with gr.Row():\n",
+        "        prompt_input = gr.Textbox(label=\"Enter Prompt\", placeholder=\"A futuristic city at sunset\")\n",
+        "      with gr.Row():\n",
+        "        guidance_input = gr.Slider(1.0, 15.0, value=8.5, label=\"Guidance Scale (More guidance meansthe model follows the prompt very strictly but is less creative)\")  # User can adjust guidance\n",
+        "\n",
+        "    with gr.Row():\n",
+        "      generate_btn = gr.Button(\"Generate\")\n",
+        "    with gr.Row():\n",
+        "      output_image = gr.Image(label=\"Generated Image\")\n",
+        "\n",
+        "    generate_btn.click(generate_image, inputs=[prompt_input, guidance_input], outputs=output_image)\n",
+        "\n",
+        "\n",
+        "    # Modify Image (After Generation)\n",
+        "    with gr.Tab(\"Modify Image\"):\n",
+        "        modify_prompt = gr.Textbox(label=\"Enter modification prompt\")\n",
+        "        strength_slider = gr.Slider(0.1, 1.0, value=0.5, label=\"Strength (Higher = More Change)\")\n",
+        "        modify_btn = gr.Button(\"Modify\")\n",
+        "        modified_output = gr.Image(label=\"Modified Image\")\n",
+        "\n",
+        "        modify_btn.click(modify_image, inputs=[modify_prompt, strength_slider], outputs=modified_output)\n",
+        "\n",
+        "# Launch Gradio App\n",
+        "demo.launch(share=True)\n"
+      ],
+      "metadata": {
+        "id": "ZuoDNzKH29da"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}