Sam Altman Turns K-Pop Idol With New 'Images 1.5' For ChatGPT: Steps To Create Your Own Version

OpenAI launched 'Images 1.5' on Wednesday in ChatGPT and the API. The new version offers faster image generation, improved quality and better details.

"Introducing ChatGPT Images, powered by our flagship new image generation model: Stronger instruction following, Precise editing, Detail preservation, 4x faster than before," OpenAI announced in an X post.

OpenAI CEO Sam Altman described the new tool as generating much better images in “tons of ways.”

“Images 1.5 launches today in ChatGPT and the API! Much better images in tons of ways, faster, and new editing capability,” he said on X. The new editing feature in ChatGPT makes it easier to modify images directly.

To showcase the capabilities of the new ChatGPT image editing model, OpenAI also shared an image of CEO Sam Altman as a K-pop idol. The viral image features Altman dressed in a glitter-accent white jacket, black pants, ear piercings and a bracelet.

ChatGPT shared a prompt in an X post to create a K-pop idol-style image. “Prompt: Using the provided image of the subject as reference, transform them into a K-pop idol–style version of themselves, fully preserving their natural facial features, skin tone, ethnicity, and identity. Style the subject with a polished, high-fashion idol aesthetic inspired by contemporary K-pop concept photoshoots, featuring editorial studio lighting with soft glow and clean highlights, a flawless but natural dewy skin finish, and subtle enhancement of the eyes, lips, and hair for a camera-ready look. The subject poses confidently with expressive yet controlled body language, styled in fashion-forward outfits influenced by modern K-pop trends such as elevated streetwear, Y2K accents, chic tailoring, glam punk, or soft ethereal looks, adapted to complement their original clothing style. The atmosphere resembles a professional idol photoshoot, using bold colored backdrops or moody dramatic environments, studio or concert-style lighting, cinematic shadows, and refined color grading, with optional tasteful details like layered jewelry, belts, or statement accessories kept cohesive and restrained. The final image should feel like an authentic K-pop concept photo—crisp, stylish, and aspirational—projecting polished charisma and star presence while clearly remaining the same person.”

• Visit the ChatGPT website or app.

• Add the above prompt and hit enter.

• Share or modify the image as you please.

Since launch, users have been generating their own images by using the prompt on ChatGPT. Many were also quick to compare the images generated by ChatGPT with Google’s Nano Banana Pro.

OpenAI’s announcement follows as the artificial intelligence landscape continues to face intensified competition. Last month, Google launched its enhanced AI model - Gemini 3 - which became an instant hit with users. Google described the model as being "much better at figuring out the context and intent behind your request, so you get what you need with less prompting."

At the same time, Google launched Nano Banana Pro, its latest AI-powered image generation model with smarter capabilities. Nano Banana Pro was widely praised by the audience for its ability to generate much superior quality images without losing context.