Sam Altman says India created over 1 billion images with ChatGPT Images 2.0: Here are top top trends and prompts

OpenAI’s latest AI image generator has hit a massive milestone in the Indian market. The company released its answer to Gemini Nano Banana 2 less than a month ago, dubbed ChatGPT Images 2.0, and the model has now been used to generate over a billion images in India alone.

Taking to X (formerly Twitter), OpenAI CEO Sam Altman celebrated the rapid adoption of ChatGPT Images in India, writing: “ChatGPT Images 2.0 💚 India. Already more than 1 billion images created there; awesome to see.”

If you are also looking to try out ChatGPT Images 2.0, OpenAI shared some of the most popular prompts used with ChatGPT over the last 14 days with Mint. You can check them out below.

Trending ChatGPT Images 2.0 prompts:

1) Aesthetic Collages

Prompt: “Use the main subject in this image to create a 9:16 image of a warm-toned layered, overlapping photo collage. Golden hour lighting, soft shadows, cozy mood, burgundy, luxe, embroidered indian clothing, gold accessories. Collage with close-ups (eyes, lips, side profile), floral elements (beige/orange lilies). Soft glam, aesthetic social media style, high detail, shallow depth, ultra-realistic, 4K.”

2) ‘Mini Me’ images:

Prompt: “Turn this photo into a magical “Mini Me” world where tiny animated versions of yourself come to life around you. These cute 3D-style mini characters interact with your everyday surroundings — climbing onto your shoulders, sitting on your bag, waving, playing, and copying your poses — creating a playful yet emotional social media story-worthy scene full of personality and story. The original photo remains untouched while the tiny characters bring the image to life with depth, movement, realistic shadows, and a soft aesthetic vibe.”

3) AI photo enhancement

Prompt: “⁠Improve the lighting while keeping everything else exactly the same. Do not change the person, pose, expression, background, or composition. Fix issues like back lighting, harsh shadows, underexposure or uneven lighting. Transform the original lighting into soft, natural, flattering light coming from slightly above eye level and facing the subject, so the face is evenly lit with realistic skin tones. Keep the result photorealistic and consistent with the original scene.”

4) Chibi sticker pack:

Prompt: “⁠Using the uploaded photograph, create a cute illustrated chibi sticker-pack. Clean, white background, vertical output with a thick white border. Create diverse cute expressions: laughing, crying, sleepy, surprised, confused, eating, grumpy, cute expressions… Each expression should include cute text, for example: Good morning! Whattt? / Huh? / I’m reminding you! / So sleepy / Wow! Approved! / Nice! / Hey you! Achoo! / Angry! / Huh??? / Good night :3 / Too cuteee”

5) Anime Conversion

⁠Prompt: “Create a trending anime art style image from the uploaded subject. Use confident line-work with slight variation and minimal cel shading using flat shadow shapes. Use bright, saturated colors and clean graphic lighting. The style is defined by exaggerated, cartoonish character proportions featuring highly expressive, simplistic facial features that allow for immense emotional range, with highly varied stretched anatomy. Transform the environment into a slightly warped space with playful perspective distortion and simplified objects. Composition and tone should be energetic, lively, and comedic in a fully stylized, non-realistic world.”

6) Fashion Studio Portraits:

Prompt: “⁠Transform this photo into an elevated fashion studio portrait. Choose a complementing-color background that enhances the subject’s skin tone. Keep a tight head-and-shoulder composition with the subject centered and facing the camera straight with an optimistic expression. Apply directional lighting with subtle shadows. Preserve natural skin tones while making the image polished, minimal, and editorial—like a magazine photoshoot.”

7) Quality enhancements:

Prompt: “⁠Improve the quality of my photo and make it clearer.”

8) Travel collage:

Prompt: “⁠Use this image to create a travel collage by placing the main subject of the original image in a travel destination location with location appropriate styling as an instant photo with instant photo style lighting, color and quality. Include a postcard from a random less traveled destination in blue ink pen inspiring me to travel to new places. It should feel intimate, personal, and cleanly curated. Add souvenirs and small details that create a sense of a memento in a balanced layout with natural lighting.”

9) Underwater portrait:

Prompt: ⁠”Create an extreme close-up underwater portrait after the subject has just jumped into a swimming pool or clear shallow water. Keep the mood calm, weightless, and ethereal, emphasizing light reflections. No struggle or urgency.”

10) Retro Manga Strips:

Prompt: “⁠Create a wholly original, simple black-and-white comic strip in a retro hand-inked manga style. Use 2-3 horizontal panels. Treat the uploaded image as the character reference; redraw the character entirely in manga form with consistent line work and shading across every panel. Interpret the person as the main character and, based on their appearance, generate an uplifting encounter with a clear “setup-reinforce-turnaround” structure: the first panel establishes context, the second develops the situation, and the third delivers a surprise twist. Keep the dialogue short, natural, and upbeat. No technology.”

What’s new with ChatGPT Images 2.0?

The sudden rise in popularity of ChatGPT for image generation is not completely unexpected since Images 2.0 brought a lot of major upgrades over its predecessor, such as better instruction following, more accurate object placement, and stronger text rendering.

Here are the top reasons why ChatGPT Images 2.0 could be winning the hearts of Indian users:

Greater Precision and Control: The new model is capable of handling more precise instructions, preserving the requested details, and rendering fine-grained elements like small text, iconography, UI elements, dense compositions, and subtle stylistic constraints. The model also comes with support for generating images in up to 2K resolution.

Multilingual Text Rendering: One of the biggest problems with image models was that they were incapable of rendering precise text in local languages. ChatGPT Images 2.0 fixes that and is capable of rendering non-English text with the same fluency, while also supporting a number of Indian languages such as Hindi.

Thinking-Level Intelligence: When using a “thinking model” in ChatGPT, Images 2.0 can search the web for real-time information, generate multiple distinct images from a single prompt, double-check its own outputs for accuracy, and even create scannable, functional QR codes. However, this is currently limited to paid ChatGPT users.