Authentic Authentic Japanese Izakaya Friends Group Selfie | AI Photo Prompt

A candid, wide-angle selfie of three joyful friends smiling inside a warmly lit, decorated Japanese Izakaya.

A candid, wide-angle group selfie of three young adult women smiling warmly inside a lively, decorated izakaya or Japanese restaurant, taken at eye-level from an outstretched arm position. In the center, a woman with warm skin and natural freckles, wearing a light blue denim jacket, smiles broadly, flanked by a laughing blonde woman on her left with green earrings and a friendly brunette woman with a short bob on her right wearing a lilac top. Above them, traditional Japanese-style decorations hang from the dark ceiling, including string lights, a large white paper lantern, and multiple paper flag banners with red-and-circle motifs. The environment features warm, ambient lighting, with a clear focus on the faces and a shallow depth of field in the blurred background. Capture the authentic skin textures, expressions, and the textures of the denim and other clothing. Preserve the exact facial identity, bone structure, skin tone, and distinguishing features of all three primary subjects from the uploaded reference photo — do not generate a different face, do not blend features, do not idealize or beautify the faces. Rendered in 4k resolution, 8k resolution, ultra-detailed, masterpiece, free of text artifacts, watermarks, distorted hands, or eyes.

☕ Support Us

Copy the prompt ➡️ Open your preferred AI image-generation tool, such as Midjourney, ChatGPT, Google Gemini, or Stable Diffusion ➡️ Upload your photo if required➡️ Paste the prompt into the tool ➡️ Generate your image and enjoy the result!

Introduction

An AI photo prompt is a descriptive text instruction given to Artificial Intelligence models like Midjourney, ChatGPT, or Google Gemini. It acts as a creative blueprint, telling the AI exactly what kind of image to generate, including details about the subject, lighting, environment, and artistic style. A well-crafted prompt is the secret to unlocking stunning, highly detailed AI-generated artwork.

What This Prompt Creates

This specific prompt generates a highly realistic, candid, wide-angle group selfie of three joyful friends enjoying themselves inside a traditionally decorated Japanese Izakaya. The image focuses on the genuine expressions of the three women, capturing detailed textures of their clothing and authentic skin details. The background is a beautifully blurred, warm environment filled with cultural markers like paper lanterns and string lights, establishing a lively and cozy atmosphere.

The AI Photo Prompt

The power of this prompt lies in its descriptive keywords and structural directives. By using terms like 'candid,' 'wide-angle group selfie,' and 'outstretched arm position,' it provides clear guidance on the camera angle and spontaneous composition. The detailed breakdown of each subject’s appearance (e.g., 'denim jacket,' 'natural freckles,' 'lilac top') ensures accurate rendering of individuals, while environmental descriptors like 'izakaya,' 'paper lantern,' and 'ambient lighting' establish a cohesive, realistic setting. The explicit instructions on identity preservation are crucial for preventing stylized or generic faces.

Recommended Settings

Best Aspect Ratio: 1:1 or 4:5 for a mobile-style selfie feel, though 16:9 works well for capturing more background detail.
Lighting & Camera Style: Warm, ambient interior lighting; Candid, eye-level wide-angle shot with shallow depth of field.

How to Use This Prompt

To use this prompt, copy the full text from the box above and paste it into your favorite AI image generator, such as Midjourney, ChatGPT, Stable Diffusion, or Google Gemini. If your platform supports face reference images (like Midjourney's `--cref`), upload a photo of the people you wish to depict before pasting the prompt to achieve maximum resemblance to your subjects.

How to Customize the Prompt

You can easily customize this scene to fit your own memories or desired aesthetic. Simply change the clothing descriptions to match your friends' styles, such as swapping 'denim jacket' for 'black leather jacket' or 'lilac top' for 'hoodie.' You can also adjust the venue by changing 'izakaya' to 'ramen shop,' 'cozy cafe,' or 'rooftop bar.' If you want to alter the mood, try replacing 'smiling warmly' with 'laughing uncontrollably' or 'making funny faces.'

For Men / Women / Couples Variations

This prompt can be adapted for any combination of subjects. For a group of men, simply change the gender references (e.g., 'three young adult men,' 'bearded man wearing a flannel shirt'). For a mix of genders, adjust the subject descriptions to reflect each person specifically. For a couple’s selfie, change the subject to 'a cheerful young adult couple' and describe the interaction between the two individuals (e.g., 'man taking selfie with arm around smiling woman').

Common Mistakes

One common mistake when generating selfies with multiple subjects is achieving accurate facial likenesses for everyone. Ensure that your reference photos are clear and that you've used any platform-specific identity tools. Another frequent issue is 'weird hands' or distorted limbs from the stretched-arm angle; regenerating or adjusting the prompt to rely less on the arm might help. Finally, ensure the background remains softly blurred ('shallow depth of field') rather than becoming distractingly sharp or completely incoherent.

Example Results

When used effectively, this prompt will generate a high-fidelity image that looks like a genuine, spontaneous moment captured on a smartphone. The three women will be clearly focused, with lifelike expressions and skin textures. The background will provide a rich, culturally immersive atmosphere with warm bokeh from the string lights and lanterns, perfectly framing the joyful interactions of the group.

Frequently Asked Questions

Can I edit my own photos using ChatGPT or Google Gemini?

Yes! Both ChatGPT and Google Gemini allow you to upload your own photos. You can then provide specific prompts to ask the AI to alter the image, change the background, or apply different artistic styles.

How do I upload an image to ChatGPT or Gemini for editing?

In the chat interface of both platforms, look for the "+" or paperclip/image upload icon next to the text box. Select your photo, type your editing prompt (e.g., "Change the background to a cyberpunk city"), and hit send.

What kind of image edits can these AI models do?

They can analyze your image and generate variations, apply artistic filters, or seamlessly blend your photo with new elements described in your text prompt. You can even ask them to change the lighting or clothing style.

Is there a specific aspect ratio I should use for AI photo editing?

While you can upload an image of any size, it is best to know your target aspect ratio (like 16:9 for desktop or 9:16 for mobile). The AI usually maintains the original aspect ratio of the uploaded photo unless you specifically ask it to expand or crop the image.

Why isn't the AI changing the specific detail I asked for?

AI models can sometimes be unpredictable. If it misses a detail, try to be more specific in your prompt. Use instructions like "preserve the original face exactly as it is but change the jacket to red" to guide the AI more accurately.

❓ Can I use someone else’s photo for AI photo editing?

It’s best to use your own photo for AI photo editing. If you want to edit or transform someone else’s photo, make sure you have their permission or consent first. Respect people’s privacy and use AI responsibly.