AI画图终于学会“猜你意思”了
你让AI画“一个在公园里看书的人”，它可能画成阴天、草地、坐着——但你其实想的是晴天、长椅、站着。这不是AI笨，是它缺上下文。Qwen-Image-Agent把这事拆成两步：先自己发现缺什么（比如天气、姿势），再主动去搜、去推理、去翻记忆，把缺的信息补上再画。在专门测这种能力的测试里，它比现有模型强一截。它不是你明天就能用的产品，但方向很明确：AI画图不再只靠你一句话，而是学会像人一样“想一下再画”。
📄 原文摘要(英文)
While text-to-image (T2I) models have achieved remarkable progress, they struggle with real-world requests that are often underspecified, implicit, or dependent on up-to-date knowledge. We identify this challenge as the Context Gap: the mismatch between the user context and the sufficient generation context for T2I models. To bridge this gap, we propose Qwen-Image-Agent, a unified agentic framework that integrates plan, reason, search, memory and feedback in a context-centric manner. Qwen-Image-Agent treats user input as partial context and progressively constructs the generation context through Context-Aware Planning and Context Grounding. Specifically, Context-Aware Planning identifies missing context and plans how it should be acquired and used, while Context Grounding gathers this context from reason, search, memory, and feedback. To evaluate agentic image generation, we further introduce Image Agent Bench (IA-Bench), a benchmark covering four core image agent capabilities: Plan, Reason, Search, and Memory. Experiments on IA-Bench, Mindbench and WISE-Verified show that Qwen-Image-Agent outperforms strong baselines and achieves state-of-the-art performance.