Image generation powered by OpenAI's gpt-image-2.6-sunburst (GPT Image 2.6 Sunburst), built for detailed compositions and image editing. OpenAI says that at medium or high quality it brings higher image quality and greater consistency across edits, keeping characters, products and brand details steady. Describe the picture you want in a few sentences and receive a high-resolution illustration or photo-style output; style, aspect ratio and subject are all controllable via prompt. A quality selector above the input box defaults to auto (the model decides from the prompt) and also offers low, medium, high, xhigh and max; higher levels render more detail and take longer. You can also upload up to sixteen pictures and edit them with plain-language instructions such as "replace the background with a city at night" or "change the jacket to red"; if the result is not quite right, just send another instruction and the previous output is reused for continuous refinement, and you can also upload another picture in the same conversation as a reference for editing the previous result. Use Flare to try compositions quickly, then finish with Sunburst. The generated image size is chosen automatically by the model from your prompt: commonly 1024x1024 (square), 1024x1536 (portrait), or 1536x1024 (landscape), and other resolutions are possible, with the longest edge up to 3840 pixels. Prompt example 1: Draw a richly detailed old street at dawn: stone paving, wooden arcades, a tofu pudding cart and rising steam, realistic photo style. Prompt example 2: (Upload a portrait) Dress this person in a dark blue suit; keep the face, hair and pose exactly the same, with a plain studio background. Prompt example 3: (Upload a product photo of a perfume bottle) Make a luxury magazine ad: black marble table, soft side light, with the bottle text and shape unchanged. Prompt example 4: Draw four scenes of the same character: in a classroom, a library, a sports field and at home, with the same face, hair and outfit in all four. Prompt example 5: Draw an interior design proposal: a Nordic living room with light wood floors, a gray fabric sofa and large windows, natural daylight. Prompt example 6: (Upload an old photo) Repair the scratches and fading and add natural color, without changing the facial features. Prompt example 7: Draw a detailed mountain ecology illustration of Taiwan, labeling the Formosan black bear, the Mikado pheasant and mountain cherry blossoms, in a science picture-book style. Prompt example 8: (Upload a brand mascot image) Draw this mascot waving with a coffee cup in hand, with the same design and colors as the original. Prompt example 9: Create a cinematic night scene: a rainy city street with neon signs reflected on the ground and a pedestrian with an umbrella walking past. Prompt example 10: Design an elegant wedding invitation: a soft floral border, You Are Cordially Invited in the center, with space for names and the date. Maximum total upload size per request: 512MB (all files and message content combined). Accepted image formats: jpeg, jpg, png, webp. Maximum number of images: 16. Maximum size per image: 50MB. Maximum total image size per message: 100MB (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: Image Pricing: Medium-high Image output size: chosen automatically by the model from the prompt; commonly 1024x1024, 1024x1536, or 1536x1024 pixels, and other resolutions are possible (longest edge up to 3840 pixels). Continuous conversation: Supported AI can make mistakes. Please verify important information.