Upload any image and the model reverse-engineers the prompt that would recreate it. Returns a detailed description covering subject, style, lighting, composition, color palette, and camera setup. Perfect for analyzing reference imagery, reproducing an art style, or building a prompt library. Runs on Gemini 3.1 Pro for strong multimodal reasoning. Prompt example 1: (Upload a watercolor illustration whose style you want to reuse, then send it as is) Prompt example 2: (Upload an interior photo of a coffee shop, then send it as is) Prompt example 3: (Upload a product key visual poster, then send it as is) Prompt example 4: (Upload an anime-style character illustration, then send it as is) Prompt example 5: (Upload a coastal landscape photo taken at sunset, then send it as is) Prompt example 6: (Upload a 3D-style app icon, then send it as is) Prompt example 7: (Upload a food photography shot, then send it as is) Prompt example 8: (Upload a floral still-life oil painting, then send it as is) Prompt example 9: (Upload a vintage film-style street portrait, then send it as is) Prompt example 10: (Upload a neon cyberpunk city illustration, then send it as is) Maximum total upload size per request: 512MB (all files and message content combined). Accepted document formats: pdf, docx, xlsx, pptx, txt, csv (file content is provided to the model as extracted text). Accepted image formats: heic, heif, jpeg, jpg, png, webp. Maximum number of images: 3600. Maximum size per image: 64MB. Maximum total image size per message: 64MB (text and history share the same request size limit; uploads close to the limit may still be rejected). Image dimensions: at least 200 pixels per side. Maximum image resolution: 36,000,000 pixels in total. Output content formats: Text Pricing: Medium-high Continuous conversation: Not supported AI can make mistakes. Please verify important information.