Transform images into AI-generated artwork with Florence2-powered prompt extraction! This workflow takes an image, generates a detailed text prompt, and then creates a new image based on the extracted description using Stable Diffusion SDXL.

---

🎯 Features

• Florence2 Image Captioning – Converts an image into a descriptive text prompt.
• Automated Prompt-to-Image – Uses the extracted prompt to generate a brand-new AI image.
• Stable Diffusion SDXL Support – Ensures high-resolution and quality outputs.
• Customizable Negative Prompts – Refine outputs with additional control.

---

💡 Use Cases

• Photo-Based AI Art – Generate stunning AI images inspired by real-world pictures.
• Concept Art & Ideation – Quickly create concept sketches based on photo references.
• AI-Powered Storytelling – Turn images into narrative-driven AI-generated scenes.
• Style Transfer & Remixing – Extract image details and reimagine them in different styles.

---

⚙️ How It Works

1. Upload Your Image – Provide a reference image for AI analysis.
2. Generate a Prompt – Florence2 extracts a descriptive text from the image.
3. Select a Model – Load Juggernaut_X_RunDiffusion or another preferred Stable Diffusion model.
4. Refine Your Prompt – Modify the extracted text if needed.
5. Run Text-to-Image Generation – SDXL creates a new image based on the AI-generated prompt.
6. Preview & Save – Review and export your final artwork.

---

Credits: pixaroma