ChatGPT latest update: Finally gets text and object placement right in images
OpenAI has launched ChatGPT Images 2.0, a significant upgrade to its image generation model, with improved accuracy and text rendering. The new model supports up to 8 coherent images per request and is available to ChatGPT and Codex users.
OpenAI has introduced ChatGPT Images 2.0, a major upgrade to its image generation capabilities. The new model can create more realistic images with accurate text in multiple languages. It supports up to 8 coherent images per request, making it easier to create storyboards, comic panels, or presentation assets. The update also introduces 'thinking enabled' workflows, allowing the system to reason through complex prompts and generate multiple distinct outputs. ChatGPT Images 2.0 is available to all ChatGPT and Codex users, with advanced features limited to paid tiers. The new model is also accessible via the API as gpt-image-2, enabling developers to integrate image generation into their applications.
This content was automatically generated and/or translated by AI. It may contain inaccuracies. Please refer to the original sources for verification.