TMTPOST – OpenAI has announced the launch of its GPT-4o image generation feature, integrating "the most advanced image generator to date" into GPT-4o. Starting Wednesday, users across Plus, Pro, Team, and Free tiers will gradually gain access to this capability in ChatGPT and Sora, with enterprise and education versions to follow soon. The Sora platform will also enable this feature, while developers will be able to access it via API in the coming weeks as interface permissions are progressively opened. According to OpenAI, the GPT-4o image generation function excels in precise text rendering, strict adherence to prompt instructions, deep integration with the GPT-4o knowledge base, and contextual understanding within conversations. It also supports secondary creation based on uploaded images, transforming them into new visual inspirations.