OpenAI Makes a Big Move! Image Generation API Upgrade: Real-Time Streaming Preview + Multi-Round Editing MCP Enables Boundless Creation!

AIbase基地

Published inAI News · 7 min read · May 29, 2025

OpenAI announced a major update to its image generation API (Responses API), introducing new features such as streaming, multi-round editing, and integration with Model Context Protocol (MCP) tools and real-time web data search. These new capabilities not only enhance the efficiency of image generation but also provide developers with more flexible creation methods, marking a new stage in AI-driven visual content creation. AIbase has compiled the core highlights of this update and its far-reaching impact on the industry.

Streaming: Real-Time Preview, More Efficient Creation

The newly added streaming function in OpenAI's image generation API allows users to view partial images in real time during the generation process without waiting for the entire process to complete. This feature significantly shortens the feedback time during creation, enabling developers to instantly adjust prompts or parameters during loading to optimize the generated results. Compared to the traditional full-generation mode, streaming not only improves efficiency but also makes it possible to dynamically adjust the direction of creation, especially suitable for scenarios requiring rapid iteration, such as real-time design or content creation.

Multi-Round Editing: High-Fidelity Modifications, Saving Computing Resources

The newly introduced multi-round editing function brings higher flexibility to image generation. Developers can now perform high-fidelity edits on generated images through multiple rounds of interaction without having to start from scratch each time. This function reduces computing resource consumption significantly through caching optimization technology while maintaining the stability of image quality. For example, designers can make step-by-step adjustments to the details of generated images, such as changing backgrounds, optimizing colors, or adding elements, thus achieving more precise creative control.

MCP Integration and Real-Time Data: Connecting External Tools and Dynamic Content

Another highlight of this update is the integration with MCP servers. OpenAI's image generation API now supports connecting to MCP servers with just a few lines of code, compatible with various tools including Cloudflare, Stripe, Twilio, Shopify, PayPal, and Zapier. This feature enables developers to seamlessly integrate image generation with external data sources or services. For example, they can extract real-time data from corporate databases via MCP servers or call external APIs to complete complex tasks.

In addition, the API also supports real-time web searches, allowing developers to generate images by combining the latest web data. For instance, AI can generate visual charts based on real-time stock data or create customized marketing materials according to social media trends. This dynamic data integration capability greatly expands the application scenarios of image generation, benefiting fields such as advertising design and data visualization.

Industry Impact: Reshaping the AI Visual Creation Ecosystem

This update to OpenAI's image generation API not only enhances technical performance but also provides developers with unprecedented creative freedom through MCP integration and real-time data support. The streaming and multi-round editing functions lower the barrier to creation, making it easier for non-professional users to get started quickly, while the compatibility of MCP provides strong scalability for enterprise-level applications. Industry insiders believe that this update will further promote the popularization of AI in creative industries, e-commerce, and data analysis.

However, the powerful generative capabilities also bring potential ethical challenges. Generated realistic images or dynamic content based on real-time data could be misused, such as spreading false information. OpenAI stated that it will minimize the risk of technology abuse through strict API usage norms and security review mechanisms.

Future Prospects: Infinite Possibilities in AI Creation

OpenAI's Responses API update injects new vitality into image generation technology. The combination of streaming and multi-round editing makes the creation process more intuitive and efficient, while MCP integration paves the way for deep integration between AI and external ecosystems. In the future, developers are expected to use this API to create smarter and more personalized visual content, opening up new possibilities from interactive advertisements to immersive virtual experiences.

Global First AI Proxy Browser Opera Neon Released: Intelligent Chatting and Task Automation Lead the Web4.0 Era

Opera has officially announced the release of its new AI-driven proxy browser, Opera Neon, and opened an Alpha version waiting list. This browser redefines the way users interact with the web by integrating innovative features such as intelligent chatting, task automation, and content creation through its unique proxy function. AIbase has compiled the latest highlights of Opera Neon and its far-reaching impact on future browsing experiences. Global First Proxy Browser: Redefining the Web Experience Opera Neon is positioned as

GPT-4o Voice Mode Fully Upgraded: Singing Function Released, Entering a New Realm of AI Interaction

The Advanced Voice Mode of OpenAI's GPT-4o has undergone significant updates recently, enabling more natural voice interaction and introducing an impressive new singing function. Although the current singing performance is still somewhat immature, this breakthrough undoubtedly opens up new possibilities for AI's multi-modal interaction capabilities. AIbase summarizes the latest information to analyze the latest progress and potential of GPT-4o's voice mode. Singing Function Released: Even AI Can Sing

UAV-Flow Project Breakthroughs in Drone Control with Precise Flight by Voice Commands

The rapid development of drone technology is changing our way of life, and research on controlling drones with voice commands is undoubtedly a pioneer in this field. A project named UAV-Flow is emerging with an innovative approach. By utilizing natural language processing technology, users can precisely control drones with only voice instructions. This technological breakthrough is expected to significantly reduce the threshold for drone operation and promote its widespread use in consumer, industrial, and rescue scenarios. Here is AIbase's in-depth analysis of the project. UAV-Flow Project: Control with Language

Trae v1.3.0 Released: AI-Powered Programming Experience Enhanced

ByteDance's AI-powered Integrated Development Environment (IDE), Trae, has officially released version v1.3.0. This update brings a unified conversational experience, enhanced contextual capabilities, custom rule support, and significantly upgraded Agent functionality. It also adds support for the Model Context Protocol (MCP), providing developers with a more intelligent and flexible programming experience. The following report, compiled from publicly available information, details the highlights of Trae v1.3.0.

OpenAI Releases 34-Page Guide to Building Intelligent Agents: From Web Search to Code Generation

On April 17, 2025, OpenAI announced via social media the release of a 34-page "Practical Guide to Intelligent Agents," offering developers comprehensive guidance on building agent applications. This marks another significant advancement in OpenAI's efforts to promote the practical application and standardization of AI technology. According to the announcement, the guide details how to utilize OpenAI's Responses API to build agents capable of web search, file search, and computer interaction. The Responses API is an evolution of Cha...

FastAPI-MCP Released: Zero-Config Conversion of FastAPI Apps to MCP Servers

The open-source community recently welcomed a heavyweight tool – FastAPI-MCP. This near zero-configuration tool automatically converts FastAPI application interfaces into Model Context Protocol (MCP) tools, opening a new path for seamless interaction between AI models and backend services. According to AIbase, FastAPI-MCP has quickly gained popularity among developers for its ease of use and high flexibility, finding widespread application in AI-driven automation scenarios. The project is now open-source; source code available.

Agent Tool Integration Powerhouse! automcp Enables Multi-Framework Conversion to Standardized MCP Protocol

automcp is an innovative tool that simplifies the conversion of tools, agents, and orchestrators built with various existing Agent frameworks (including CrewAI, LangGraph, Llama Index, OpenAI Agents SDK, and Pydantic AI) into Model Context Protocol (MCP) servers. The key benefit of MCP servers is providing a standardized interface.