Image generation powered by OpenAI's gpt-image-2.5-flare (GPT Image 2.5 Flare), the fastest model in the GPT Image 2.5 family, positioned for high-quality everyday image generation: it renders noticeably faster than Sunburst while keeping next-generation detail, and handles photo-realistic scenes, illustrations, product shots and many design styles. Describe the picture you want in a few sentences and receive a high-resolution output quickly; 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 beach" or "make the cup 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 for fast iteration and bulk drafts, then switch to Sunburst for the final precision edit. 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 warm illustration of a small breakfast shop on a street corner at dawn, steam rising from bamboo steamers, a cook frying egg pancakes, soft morning light. Prompt example 2: (Upload a product photo of a thermos) Replace the background with a light wood tabletop and natural window light; keep the product's original color and shape. Prompt example 3: Design a square social post: a glass of iced tea on a seaside boardwalk, with the words Summer Special in large letters in the open sky above, flat illustration style. Prompt example 4: Draw a four-panel recipe illustration: crack the eggs, add the tomatoes, stir-fry, then plate, with the step number under each panel, simple clean line art. Prompt example 5: (Upload three product photos of tote bags in different colors) Place all three side by side on one white background with soft shadows for a catalog hero image. Prompt example 6: Draw a birthday card illustration: a three-layer strawberry cake with candles, ribbons and balloons around it, and Happy Birthday Amy on top, cute hand-drawn style. Prompt example 7: Design a round lid sticker for my homemade jam: strawberry and blueberry motifs with Fang's Homemade in the middle, hand-drawn vintage style. Prompt example 8: (Upload a travel photo taken in front of a waterfall) Remove all the passing tourists in the background, keeping only me and the waterfall, with the filled-in areas looking natural. Prompt example 9: Draw a notice illustration for a community beach cleanup: volunteers picking up trash on the sand next to sorting bins, with Protect Our Ocean on top, bright flat style. Prompt example 10: Create a realistic photo-style scene: coworkers chatting over coffee in an office pantry in the afternoon, natural light, for a company careers page. 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.