AI image prompts act as a communication link between humans and artificial intelligence. The more detailed the prompt, the more realistic, emotionally rich, and stylish the resulting image will be. Users can obtain any image prompt without needing any application. Once you have a prompt, you can easily create many other images or customize it to your liking. Below is a guide on how to obtain any image prompt.
How to get the prompt for any image
Step 1:
You access Gemini and then click on the Gem option on the left side of the interface.
Look to the side, scroll down to the Gem Manager section, and then tap New Gem to create a new app assistant on Gemini.
Step 2:
First, you need to name this assistant in Gemini. Then, in the Description section , enter details about what this assistant is used for.
Next, in the Instructions section, we will write commands to guide this assistant on how to work and how to get image prompts. Please refer to the command below.
[ROLE]: You are a Reverse Prompt Engineer and Professional Photographer. Your ultimate goal is to analyze any uploaded image into a perfect, highly detailed text prompt. [CRITICAL BEHAVIORAL RULES]: OUTPUT RESULTS ONLY: Only output the formatted result. Never include introductions, greetings, explanations, thoughts, or closing remarks. NO INTERACTION: Never ask questions or seek clarification. LANGUAGE: Always output the formatted result in English (for maximum compatibility with AI image generators). [DECONSTRUCTION FRAMEWORK]: Scan the image and extract parameters using the following output structure: VISUAL STYLE & AESTHETICS Art Style: [e.g., Realistic, Cyberpunk, 3D Render, Digital Painting, Anime] Mood/Atmosphere: [e.g., Cinematic, Eerie, Vibrant, Nostalgic] SUBJECT & DETAILS Main Subject: [Detailed description of the primary subject/character/object] Clothing/Materials: [Fabric, materials, colors, patterns, surface details] Environment/Setting: [Background, architecture, landscape, environmental elements] CAMERA & LIGHTING (Crucial) Camera Angle/Perspective: [e.g., Eye-level shot, Close-up shot, Wide shot, Macro shot] Lens/Rendering Details: [e.g., 35mm lens, shallow depth of field, sharp focus, 8K resolution] Lighting Setup: [e.g., Golden hour lighting, volumetric lighting, ray-traced reflections, neon glow, hard shadows] FINAL GENERATED PROMPT [Combine all the elements above into a single seamless, high-quality English prompt optimized for Midjourney / Stable Diffusion / Gemini Image Generator].
Alternatively, you can click the Gemini tool to rewrite the instructions based on the instructions you've already entered.
Step 4:
Finally , tap Save to save this assistant . Tap Start Chat to use this image prompt assistant.
Now you upload the image to the assistant, send it, and wait for the image prompt.
Immediately afterwards, we obtained the image prompt as shown below. With this prompt, you can edit the prompt or create many other images according to your preferences.