{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-09-22T15:00:59.990Z","headline":"Google Antigravity 系列教程 Part 2：用 generate_image 工具自动化图像生成","description":"这篇是 Google 团队 Elevating Antigravity Agent Skills 五部曲的第二部分，讲解如何在 agent skill 中使用 generate_image 工具，把结构化提示词合成与原生图像生成结合，让 agent 产出符合开发者规范的图像。","url":"https://www.aioga.com/news/cmtiyodib01zuroelumvkcmcj/","mainEntityOfPage":"https://www.aioga.com/news/cmtiyodib01zuroelumvkcmcj/","datePublished":"2026-09-01T16:51:26.000Z","dateModified":"2026-09-01T16:51:26.000Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://dev.to/googleai/elevating-antigravity-agent-skills-part-2-image-generation-2jno","https://aihot.virxact.com/items/cmtiyodib01zuroelumvkcmcj"],"canonicalUrl":"https://www.aioga.com/news/cmtiyodib01zuroelumvkcmcj/","directAnswer":{"@type":"Answer","text":"Google 团队发布 Antigravity Agent Skills 系列第二部分教程，主题是使用 generate_image 工具实现图像生成。文章介绍将结构化提示词合成与原生图像生成结合，使 agent 根据开发者规范产出图像。","url":"https://www.aioga.com/news/cmtiyodib01zuroelumvkcmcj/","dateCreated":"2026-09-01T16:51:26.000Z","author":{"@type":"Organization","@id":"https://www.aioga.com/authors/aioga-editorial/#editorial-team","name":"Aioga Editorial Team","url":"https://www.aioga.com/authors/aioga-editorial/"}},"evidence":[{"@type":"CreativeWork","name":"dev.to source article","url":"https://dev.to/googleai/elevating-antigravity-agent-skills-part-2-image-generation-2jno","datePublished":"2026-09-01T16:51:26.000Z","provider":{"@type":"Organization","name":"dev.to","url":"https://dev.to/googleai/elevating-antigravity-agent-skills-part-2-image-generation-2jno"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.virxact.com/items/cmtiyodib01zuroelumvkcmcj","datePublished":"2026-09-01T16:51:26.000Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.virxact.com/items/cmtiyodib01zuroelumvkcmcj"}}],"aggregationSource":"Google AI：DEV 作者专属（RSS）","originalPublisher":{"name":"dev.to","url":"https://dev.to/googleai/elevating-antigravity-agent-skills-part-2-image-generation-2jno"},"geoDeepAnswer":null,"article":{"id":"cmtiyodib01zuroelumvkcmcj","slug":"cmtiyodib01zuroelumvkcmcj","url":"https://www.aioga.com/news/cmtiyodib01zuroelumvkcmcj/","title":"Google Antigravity 系列教程 Part 2：用 generate_image 工具自动化图像生成","title_en":"","summary":"这篇是 Google 团队 Elevating Antigravity Agent Skills 五部曲的第二部分，讲解如何在 agent skill 中使用 generate_image 工具，把结构化提示词合成与原生图像生成结合，让 agent 产出符合开发者规范的图像。","source":"Google AI：DEV 作者专属（RSS）","sourceUrl":"https://dev.to/googleai/elevating-antigravity-agent-skills-part-2-image-generation-2jno","aiHotUrl":"https://aihot.virxact.com/items/cmtiyodib01zuroelumvkcmcj","publishedAt":"2026-09-01T16:51:26.000Z","category":"行业动态","score":58,"selected":false,"articleBody":["By coupling native image generation directly with structured prompt synthesis, you turn your AI agent from a text generator into an image studio producing clean, consistent images grounded in developer specs.","Here is what you will get out of this deep dive:","📝 About this series: Welcome to Elevating Antigravity Agent Skills series, a 5-part engineering guide to mastering the agent tools that reduce orchestration tax and transform AI agents into autonomous collaborators: ask_question , generate_image , define_subagent + invoke_subagent , send_message and manage_subagents .","Many of us building web applications, developer tools, or component libraries have used grey placeholder boxes while waiting for sample visual assets.","This is where the generate_image ：https://antigravity.google/docs/hooks?utm_campaign=CDR_0xc0d3ff05_awareness_b536569204&utm_medium=external&utm_source=blog#interaction-and-media tool comes in. When an Antigravity agent executes generate_image , it synthesizes text prompts and visual parameters into images saved directly into the conversation artifact storage.","Passing un-processed prompts without structure directly to generate_image leads to inconsistency. By encoding lighting, camera, and scene specifications into your skill's prompt generator, your agent produces images that consistently match your intent.","Before diving into skill authoring, let's review how Antigravity manages generated media.","When generate_image runs, the system automatically saves the output asset to the conversation's internal artifacts directory ( /brain/ / ). The tool returns the absolute file path, allowing your skills to render the asset directly in chat responses using standard markdown syntax: ![Caption](file:///path/to/image.png) .","To see this architecture in action, let's examine an example generating-mock-images ：https://github.com/GoogleCloudPlatform/devrel-demos/blob/main/elevating-antigravity/skills/generating-mock-images/SKILL.md skill. Using a plant and flower e-commerce store as my example, this skill generates mock product assets, displays the resulting image for interactive review, and handles workspace asset persistence.","：https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fgw4uw6nd6itqwdpdhcsr.jpg","Figure 1: When we prompt \"Create mock photo of white lilies.\" or \"...Jasmine\", or \"...multi-colored roses\", the generating-mock-images skill is auto-discovered by the agent and read into context. The skill instructs the agent to follow the playbook we created.","The skill pairs the selected product subject (user provided houseplant or floral arrangement) with hardcoded photography parameters detailed in the skill:","Following the skill instructions, the agent automatically creates and issues a structured tool call to generate_image . The following is a mock representation of what that structured tool call would look like:","Note, not shown in this example but generate_image natively supports visual composition. Passing up to three absolute file paths into the ImagePaths array parameter instructs the agent to blend existing logos, background textures, or reference wireframes into composite graphics.","Upon receiving the generated image path from generate_image , the agent renders the asset immediately in chat:","In my previous post, Elevating Antigravity Agent skills with interactive UI workflows：https://www.linkedin.com/pulse/elevating-antigravity-agent-skills-interactive-ui-james-o-reilly-kz8fc/, I established how to convert passive agents into active interviewers using the ask_question tool. By interrogating developers upfront, we eliminated prompt ambiguity.","Rather than assuming the generated asset is immediately production-ready, the agent prompts the developer using ask_question :","If the developer approves the asset, the agent copies the file from temporary artifact storage to /public/images/ and returns a clickable markdown link:","If the developer chooses to delete or regenerate, the agent purges the temporary artifact to prevent uncurated asset accumulation.","If your agent dumps uncurated artifacts directly into production asset paths, you aren't automating design, you're automating visual tech debt.","As you integrate expensive tool calls, like generate_image into automated developer workflows, observe these three rules to maintain consistency and efficiency:","Avoid passing raw user inputs directly to generate_image . Build a prompt generator inside your skill that injects specific parameters (such as scene, lighting, camera, and style preferences) to ensure deterministic outputs across runs.","Use the absolute artifact path returned by generate_image and move approved images to a permanent location. Storing assets in temporary directories ( /tmp ) causes link decay when context windows clear or workspace sessions restart.","Before triggering generate_image , instruct your skill to check if a valid asset with the target ImageName already exists. Re-running image generation without parameter changes wastes compute budget and slows down workflow execution.","Now that you have mastered parameterized image generation with generate_image , here is an engineering challenge to take your visual asset skills to the next level:","Build an Automated Multi-Aspect Ratio Asset Suite Generator.","Currently, our skill requires the user to include details in their prompt.","Extend your skill's prompt generator to accept target layout presets (e.g., Hero Banner , Product Card , Mobile Thumbnail ) or aspect ratios (e.g. 1:1 , 2:1 , 4:3 , 16:9 ) using the ask_question tool.","Extend your skill's prompt generator to use pre-made reference images passed into generate_image using ImagePaths param. You can include up to 3 images.","Did you attempt the challenge? Share your skill's strategy in the comments below!","Static text descriptions and broken image icons belong to an earlier generation of developer tooling. By leveraging parameterized asset generation in generate_image , you empower your agents to produce clean, consistent and visually grounded technical artifacts.","Take 15 minutes today to audit your component scaffolding and asset generation skills.","Templates let you quickly answer FAQs or store snippets for re-use.","Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink：#.","For further actions, you may consider blocking this person and/or reporting abuse：/report-abuse","Google AI Studio is the fastest way to start building with Gemini. Ready to build?","DEV Community：/ — A space to discuss and keep up software development and manage your software career","Built on Forem：https://www.forem.com — the open source：https://dev.to/t/opensource software that powers DEV：https://dev.to and other inclusive communities.","Made with love and Ruby on Rails：https://dev.to/t/rails. DEV Community © 2016 - 2026.","We're a place where coders share, stay up-to-date and grow their careers."],"articleImages":[{"sourceUrl":"https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fgw4uw6nd6itqwdpdhcsr.jpg","alt":"Mock photos of flowers","afterParagraph":8,"url":"/media/articles/cmtiyodib01zuroelumvkcmcj/e69ffc7660d33000.webp"},{"sourceUrl":"https://media2.dev.to/dynamic/image/width=256,height=,fit=scale-down,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2F8j7kvp660rqzt99zui8e.png","alt":"pic","afterParagraph":31,"url":"/media/articles/cmtiyodib01zuroelumvkcmcj/f75d1e7bc8b434f4.webp"},{"sourceUrl":"https://assets.dev.to/assets/multi-unicorn-b44d6f8c23cdd00964192bedc38af3e82463978aa611b4365bd33a0f1f4f3e97.svg","alt":"","afterParagraph":39,"url":"/media/articles/cmtiyodib01zuroelumvkcmcj/ae2a1867ed3e47a7.jpg"}],"mediaStatus":"ok","articleBodyZh":["通过将原生图像生成直接与结构化提示合成结合，你可以将你的 AI 代理从文本生成器转变为图像工作室，生成符合开发者规范的干净、一致的图像。","以下是你通过这次深入研究将获得的内容：","📝 关于本系列：欢迎来到《提升反重力代理技能》系列，这是一份五部分的工程指南，旨在掌握那些减少协调负担并将 AI 代理转变为自主协作者的代理工具：ask_question、generate_image、define_subagent + invoke_subagent、send_message 和 manage_subagents。","我们许多开发 Web 应用程序、开发者工具或组件库的人，在等待示例视觉素材时都曾使用过灰色占位框。","generate_image 工具正是在此时派上用场：https://antigravity.google/docs/hooks?utm_campaign=CDR_0xc0d3ff05_awareness_b536569204&utm_medium=external&utm_source=blog#interaction-and-media。当反重力代理执行 generate_image 时，它将文本提示和视觉参数合成成图像，并直接保存到会话工件存储中。","将未经处理、没有结构的提示直接传递给 generate_image 会导致结果不一致。通过将光线、相机和场景规格编码到你的技能提示生成器中，你的代理可以生成始终符合你意图的图像。","在深入技能创作之前，让我们回顾一下反重力如何管理生成的媒体。","当 generate_image 运行时，系统会自动将输出资源保存到会话的内部工件目录（/brain/ /）。该工具返回绝对文件路径，使你的技能能够使用标准 Markdown 语法在聊天响应中直接呈现资源：![说明](file:///path/to/image.png)。","为了实际查看该架构的运作，让我们看看生成模拟图像示例技能：https://github.com/GoogleCloudPlatform/devrel-demos/blob/main/elevating-antigravity/skills/generating-mock-images/SKILL.md。以植物和花卉电商商店为例，该技能生成模拟产品素材，展示生成的图像供交互式审核，并处理工作区资源的持久化。","：https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fgw4uw6nd6itqwdpdhcsr.jpg","图1：当我们提示“创建白色百合的模拟照片”或“...茉莉”，或“...多彩玫瑰”时，生成模拟图像技能会被代理自动发现并解读到上下文中。该技能指示代理按照我们创建的操作手册操作。","该技能将选定的产品主题（用户提供的室内植物或花卉布置）与技能中详细描述的硬编码摄影参数进行匹配：","按照技能指令，代理会自动创建并向generate_image发出结构化工具调用。以下是该结构化工具调用的模拟表示：","注意，本例未显示，但generate_image原生支持视觉合成。将最多三个绝对文件路径传递到ImagePaths数组参数中，指示代理将现有logo、背景纹理或参考线框混合成复合图形。","收到来自generate_image生成的图像路径后，代理立即在聊天中渲染该资产：","在我之前的文章《利用交互式界面工作流程提升反重力代理人技能：https：//www.LinkedIn.com/pulse/elevating-antigravity-agent-skills-interactive-ui-james-o-reilly-kz8fc/》中，我阐述了如何利用ask_question工具将被动代理人转化为主动面试官。通过提前询问开发者，我们消除了提示上的歧义。","代理不会假设生成的资产立即准备好生产，而是用ask_question提示开发者：","如果开发者批准了该资源，代理会将文件从临时工件存储复制到 /public/images/，并返回可点击的 markdown 链接：","如果开发者选择删除或重生，代理会清除临时工件，以防止未被策划的资产累积。","如果你的代理直接把未策划的工件导入生产资源路径，你不是在自动化设计，而是在自动化视觉技术债务。","当你将昂贵的工具调用（如 generate_image）集成到自动化开发者工作流中时，请遵守以下三条规则以保持一致性和效率：","避免将原始用户输入直接传递给 generate_image。在你的技能中构建一个提示生成器，注入特定参数（如场景、灯光、摄像机和风格偏好），以确保跨运行的确定性输出。","使用 generate_image 返回的绝对资源路径，并将批准的图像移动到永久存储位置。将资产存储在临时目录（/tmp）中会在上下文窗口清除或工作区会话重启时导致链接失效。","在触发 generate_image 之前，让你的技能检查是否已经存在具有目标 ImageName 的有效资产。未更改参数重新生成图像会浪费计算预算并降低工作流执行速度。","现在你已经掌握了使用 generate_image 的参数化图像生成，这里有一个工程挑战，可以将你的视觉资产技能提升到新水平：","构建一个自动化多纵横比资产套件生成器。","目前，我们的技能要求用户在提示中包含详细信息。","扩展你的技能提示生成器，以使用 ask_question 工具接受目标布局预设（例如，英雄横幅、产品卡片、移动缩略图）或纵横比（例如 1:1、2:1、4:3、16:9）。","扩展你的技能提示生成器，以使用传递给 generate_image 的预制参考图像（通过 ImagePaths 参数传入）。你最多可以包含 3 张图像。","你尝试了这个挑战吗？在下面的评论中分享你的技能策略！","静态文本描述和损坏的图像图标属于早期一代的开发者工具。通过利用 generate_image 中的参数化资产生成，你可以让你的代理生成清晰、一致且视觉上有基准的技术资产。","今天花 15 分钟审查你的组件脚手架和资产生成技能。","模板让你快速回答常见问题或存储片段以便重用。","你确定要隐藏这条评论吗？它将在你的帖子中被隐藏，但仍可通过评论的永久链接查看：#。","对于进一步操作，您可以考虑屏蔽此人和/或举报滥用行为：/report-abuse","Google AI Studio 是开始使用 Gemini 构建的最快方式。准备好开始构建了吗？","DEV 社区：/ — 一个讨论和跟进软件开发以及管理您软件职业生涯的空间","基于 Forem 构建：https://www.forem.com — 开源软件：https://dev.to/t/opensource 驱动 DEV：https://dev.to 及其他包容性社区。","用爱和 Ruby on Rails 制作：https://dev.to/t/rails。DEV 社区 © 2016 - 2026。","我们是一个程序员分享、保持最新动态并发展职业生涯的地方。"],"translationStatus":"translated","bodyOrigin":"source-page","editorial":{"summary":"Google 团队发布 Antigravity Agent Skills 系列第二部分教程，主题是使用 generate_image 工具实现图像生成。文章介绍将结构化提示词合成与原生图像生成结合，使 agent 根据开发者规范产出图像。","background":"教程属于 Elevating Antigravity Agent Skills 五部曲，系列覆盖 ask_question、generate_image、define_subagent 与 invoke_subagent、send_message、manage_subagents 等工具。文章还说明，生成资产会保存至对话内部 artifacts 目录，并返回绝对文件路径。","viewpoint":"Aioga 判断：文章重点不只是调用图像生成工具，而是把灯光、相机和场景等视觉参数纳入提示词生成流程。该方法体现了从直接提交未处理提示词，转向按规范组织生成条件的编辑思路。","implications":"可能影响：开发者使用 generate_image 时，需要关注提示词结构和视觉参数的一致性；工具返回文件路径可能便于在对话响应中引用资产，但这不代表所有生成结果都能自动满足具体项目规范。","nextStep":"后续观察：应关注后续教程是否进一步说明 generate_image 的配置边界、资产管理方式和在实际开发流程中的使用条件；当前材料不足以判断其生成质量、适用范围或对开发效率的具体影响。","evidenceRefs":["title","summary","articleBody","source"],"status":"published","aiGenerated":true,"autoApproved":true,"generatedBy":"aioga-editorial:gpt-5.6-sol","reviewedBy":"aioga-editorial-review:gpt-5.6-sol","generatedAt":"2026-09-06T18:45:26.949Z","sourceHash":"6204e45f29437d50","review":{"approved":true,"groundedness":96,"clarity":92,"duplicationRisk":18,"blockingIssues":[],"notes":["“Google 团队发布”可由来源中的 Google AI 作者信息及正文系列介绍支持。","“工具返回文件路径可能便于在对话响应中引用资产”属于基于来源所述 Markdown 引用方式的合理推断，且已使用“可能”限定。","“当前材料不足以判断……”准确体现证据边界。"]},"validation":{"passed":true,"mode":"ai-auto","revisions":0,"checks":["schema","length","source-attribution","editorial-labels","inference-boundary","low-source-overlap","no-html","independent-ai-review"]}},"tags":["行业动态","Google AI：DEV 作者专属（RSS）"],"translations":{"zh-CN":{"title":"Google Antigravity 系列教程 Part 2：用 generate_image 工具自动化图像生成","summary":"这篇是 Google 团队 Elevating Antigravity Agent Skills 五部曲的第二部分，讲解如何在 agent skill 中使用 generate_image 工具，把结构化提示词合成与原生图像生成结合，让 agent 产出符合开发者规范的图像。","category":"行业动态","source":"dev.to","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"Google Antigravity 系列教程 Part 2：用 generate_image 工具自动化图像生成 - Aioga AI资讯","description":"这篇是 Google 团队 Elevating Antigravity Agent Skills 五部曲的第二部分，讲解如何在 agent skill 中使用 generate_image 工具，把结构化提示词合成与原生图像生成结合，让 agent 产出符合开发者规范的图像。","url":"https://www.aioga.com/news/cmtiyodib01zuroelumvkcmcj/","articleBody":["通过将原生图像生成直接与结构化提示合成结合，你可以将你的 AI 代理从文本生成器转变为图像工作室，生成符合开发者规范的干净、一致的图像。","以下是你通过这次深入研究将获得的内容：","📝 关于本系列：欢迎来到《提升反重力代理技能》系列，这是一份五部分的工程指南，旨在掌握那些减少协调负担并将 AI 代理转变为自主协作者的代理工具：ask_question、generate_image、define_subagent + invoke_subagent、send_message 和 manage_subagents。","我们许多开发 Web 应用程序、开发者工具或组件库的人，在等待示例视觉素材时都曾使用过灰色占位框。","generate_image 工具正是在此时派上用场：https://antigravity.google/docs/hooks?utm_campaign=CDR_0xc0d3ff05_awareness_b536569204&utm_medium=external&utm_source=blog#interaction-and-media。当反重力代理执行 generate_image 时，它将文本提示和视觉参数合成成图像，并直接保存到会话工件存储中。","将未经处理、没有结构的提示直接传递给 generate_image 会导致结果不一致。通过将光线、相机和场景规格编码到你的技能提示生成器中，你的代理可以生成始终符合你意图的图像。","在深入技能创作之前，让我们回顾一下反重力如何管理生成的媒体。","当 generate_image 运行时，系统会自动将输出资源保存到会话的内部工件目录（/brain/ /）。该工具返回绝对文件路径，使你的技能能够使用标准 Markdown 语法在聊天响应中直接呈现资源：![说明](file:///path/to/image.png)。","为了实际查看该架构的运作，让我们看看生成模拟图像示例技能：https://github.com/GoogleCloudPlatform/devrel-demos/blob/main/elevating-antigravity/skills/generating-mock-images/SKILL.md。以植物和花卉电商商店为例，该技能生成模拟产品素材，展示生成的图像供交互式审核，并处理工作区资源的持久化。","：https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fgw4uw6nd6itqwdpdhcsr.jpg","图1：当我们提示“创建白色百合的模拟照片”或“...茉莉”，或“...多彩玫瑰”时，生成模拟图像技能会被代理自动发现并解读到上下文中。该技能指示代理按照我们创建的操作手册操作。","该技能将选定的产品主题（用户提供的室内植物或花卉布置）与技能中详细描述的硬编码摄影参数进行匹配：","按照技能指令，代理会自动创建并向generate_image发出结构化工具调用。以下是该结构化工具调用的模拟表示：","注意，本例未显示，但generate_image原生支持视觉合成。将最多三个绝对文件路径传递到ImagePaths数组参数中，指示代理将现有logo、背景纹理或参考线框混合成复合图形。","收到来自generate_image生成的图像路径后，代理立即在聊天中渲染该资产：","在我之前的文章《利用交互式界面工作流程提升反重力代理人技能：https：//www.LinkedIn.com/pulse/elevating-antigravity-agent-skills-interactive-ui-james-o-reilly-kz8fc/》中，我阐述了如何利用ask_question工具将被动代理人转化为主动面试官。通过提前询问开发者，我们消除了提示上的歧义。","代理不会假设生成的资产立即准备好生产，而是用ask_question提示开发者：","如果开发者批准了该资源，代理会将文件从临时工件存储复制到 /public/images/，并返回可点击的 markdown 链接：","如果开发者选择删除或重生，代理会清除临时工件，以防止未被策划的资产累积。","如果你的代理直接把未策划的工件导入生产资源路径，你不是在自动化设计，而是在自动化视觉技术债务。","当你将昂贵的工具调用（如 generate_image）集成到自动化开发者工作流中时，请遵守以下三条规则以保持一致性和效率：","避免将原始用户输入直接传递给 generate_image。在你的技能中构建一个提示生成器，注入特定参数（如场景、灯光、摄像机和风格偏好），以确保跨运行的确定性输出。","使用 generate_image 返回的绝对资源路径，并将批准的图像移动到永久存储位置。将资产存储在临时目录（/tmp）中会在上下文窗口清除或工作区会话重启时导致链接失效。","在触发 generate_image 之前，让你的技能检查是否已经存在具有目标 ImageName 的有效资产。未更改参数重新生成图像会浪费计算预算并降低工作流执行速度。","现在你已经掌握了使用 generate_image 的参数化图像生成，这里有一个工程挑战，可以将你的视觉资产技能提升到新水平：","构建一个自动化多纵横比资产套件生成器。","目前，我们的技能要求用户在提示中包含详细信息。","扩展你的技能提示生成器，以使用 ask_question 工具接受目标布局预设（例如，英雄横幅、产品卡片、移动缩略图）或纵横比（例如 1:1、2:1、4:3、16:9）。","扩展你的技能提示生成器，以使用传递给 generate_image 的预制参考图像（通过 ImagePaths 参数传入）。你最多可以包含 3 张图像。","你尝试了这个挑战吗？在下面的评论中分享你的技能策略！","静态文本描述和损坏的图像图标属于早期一代的开发者工具。通过利用 generate_image 中的参数化资产生成，你可以让你的代理生成清晰、一致且视觉上有基准的技术资产。","今天花 15 分钟审查你的组件脚手架和资产生成技能。","模板让你快速回答常见问题或存储片段以便重用。","你确定要隐藏这条评论吗？它将在你的帖子中被隐藏，但仍可通过评论的永久链接查看：#。","对于进一步操作，您可以考虑屏蔽此人和/或举报滥用行为：/report-abuse","Google AI Studio 是开始使用 Gemini 构建的最快方式。准备好开始构建了吗？","DEV 社区：/ — 一个讨论和跟进软件开发以及管理您软件职业生涯的空间","基于 Forem 构建：https://www.forem.com — 开源软件：https://dev.to/t/opensource 驱动 DEV：https://dev.to 及其他包容性社区。","用爱和 Ruby on Rails 制作：https://dev.to/t/rails。DEV 社区 © 2016 - 2026。","我们是一个程序员分享、保持最新动态并发展职业生涯的地方。"]},"en":{"title":"Google Antigravity Series Tutorial Part 2: Automating Image Generation with the generate_image Tool","summary":"This is the second part of the Google team's five-part series 'Elevating Antigravity Agent Skills,' explaining how to use the generate_image tool in agent skills, combining structured prompt synthesis with native image generation, allowing the agent to produce images that meet developer specifications.","category":"Industry","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"Google Antigravity Series Tutorial Part 2: Automating Image Generation with the generate_image Tool - Aioga AI News","description":"This is the second part of the Google team's five-part series 'Elevating Antigravity Agent Skills,' explaining how to use the generate_image tool in agent skills, combining structu...","url":"https://www.aioga.com/en/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:02:32.620Z"},"ja":{"title":"Google Antigravity シリーズチュートリアル Part 2：generate_image ツールを使った画像生成の自動化","summary":"これは Google チームの『Elevating Antigravity Agent Skills』五部作の第2部で、エージェントスキルで generate_image ツールを使用する方法を解説し、構造化されたプロンプトとネイティブ画像生成を組み合わせて、エージェントが開発者の規範に沿った画像を生成する方法を説明しています。","category":"業界動向","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"Google Antigravity シリーズチュートリアル Part 2：generate_image ツールを使った画像生成の自動化 - Aioga AIニュース","description":"これは Google チームの『Elevating Antigravity Agent Skills』五部作の第2部で、エージェントスキルで generate_image ツールを使用する方法を解説し、構造化されたプロンプトとネイティブ画像生成を組み合わせて、エージェントが開発者の規範に沿った画像を生成する方法を説明しています。","url":"https://www.aioga.com/ja/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:02:44.226Z"},"ko":{"title":"Google Antigravity 시리즈 튜토리얼 Part 2: generate_image 도구를 이용한 이미지 자동 생성","summary":"이 글은 Google 팀의 Elevating Antigravity Agent Skills 5부작 중 두 번째 부분으로, 에이전트 스킬에서 generate_image 도구를 사용하는 방법을 설명하며, 구조화된 프롬프트를 합성하고 원본 이미지 생성과 결합하여 에이전트가 개발자 규격에 맞는 이미지를 생성하도록 합니다.","category":"업계 동향","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"Google Antigravity 시리즈 튜토리얼 Part 2: generate_image 도구를 이용한 이미지 자동 생성 - Aioga AI 뉴스","description":"이 글은 Google 팀의 Elevating Antigravity Agent Skills 5부작 중 두 번째 부분으로, 에이전트 스킬에서 generate_image 도구를 사용하는 방법을 설명하며, 구조화된 프롬프트를 합성하고 원본 이미지 생성과 결합하여 에이전트가 개발자 규격에 맞는 이미지를 생성하도록 합니다.","url":"https://www.aioga.com/ko/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:03:24.263Z"},"es":{"title":"Serie de tutoriales Google Antigravity Parte 2: Automatización de la generación de imágenes con la herramienta generate_image","summary":"Este es la segunda parte de la serie de cinco de Google Team Elevating Antigravity Agent Skills, que explica cómo usar la herramienta generate_image en las habilidades del agente, combinando las indicaciones estructuradas con la generación de imágenes nativa, para que el agente produzca imágenes que cumplan con las normas del desarrollador.","category":"Industria","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"Serie de tutoriales Google Antigravity Parte 2: Automatización de la generación de imágenes con la herramienta generate_image - Aioga Noticias de IA","description":"Este es la segunda parte de la serie de cinco de Google Team Elevating Antigravity Agent Skills, que explica cómo usar la herramienta generate_image en las habilidades del agente,...","url":"https://www.aioga.com/es/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:03:20.951Z"},"fr":{"title":"Tutoriel de la série Google Antigravity Partie 2 : Utiliser l'outil generate_image pour automatiser la génération d'images","summary":"Ceci est la deuxième partie de la série en cinq parties 'Elevating Antigravity Agent Skills' de l'équipe Google, expliquant comment utiliser l'outil generate_image dans les compétences des agents, en combinant les invites structurées avec la génération d'images native, afin que l'agent produise des images conformes aux normes des développeurs.","category":"Industrie","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"Tutoriel de la série Google Antigravity Partie 2 : Utiliser l'outil generate_image pour automatiser la génération d'images - Aioga Actualités IA","description":"Ceci est la deuxième partie de la série en cinq parties 'Elevating Antigravity Agent Skills' de l'équipe Google, expliquant comment utiliser l'outil generate_image dans les compéte...","url":"https://www.aioga.com/fr/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:04:02.272Z"},"de":{"title":"Google Antigravity Serien-Tutorial Teil 2: Automatisierte Bildgenerierung mit dem generate_image Tool","summary":"Dies ist der zweite Teil der fünfteiligen Reihe des Google-Teams \"Elevating Antigravity Agent Skills\". Es wird erklärt, wie man im Agenten-Fähigkeiten-Setup das Werkzeug generate_image verwendet, um strukturierte Prompts mit nativer Bilderzeugung zu kombinieren, sodass der Agent Bilder liefert, die den Entwicklerstandards entsprechen.","category":"行业动态","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"Google Antigravity Serien-Tutorial Teil 2: Automatisierte Bildgenerierung mit dem generate_image Tool - Aioga KI-News","description":"Dies ist der zweite Teil der fünfteiligen Reihe des Google-Teams \"Elevating Antigravity Agent Skills\". Es wird erklärt, wie man im Agenten-Fähigkeiten-Setup das Werkzeug generate_i...","url":"https://www.aioga.com/de/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:04:05.059Z"},"pt-BR":{"title":"Série de Tutoriais Google Antigravity Parte 2: Automatizando a Geração de Imagens com a Ferramenta generate_image","summary":"Esta é a segunda parte da série de cinco sobre Elevating Antigravity Agent Skills da equipe do Google, explicando como usar a ferramenta generate_image nas habilidades do agente, combinando palavras-chave estruturadas com geração de imagens nativa, permitindo que o agente produza imagens de acordo com as normas do desenvolvedor.","category":"行业动态","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"Série de Tutoriais Google Antigravity Parte 2: Automatizando a Geração de Imagens com a Ferramenta generate_image - Aioga Notícias de IA","description":"Esta é a segunda parte da série de cinco sobre Elevating Antigravity Agent Skills da equipe do Google, explicando como usar a ferramenta generate_image nas habilidades do agente, c...","url":"https://www.aioga.com/pt-BR/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:04:39.896Z"},"ru":{"title":"Серия учебных курсов Google Antigravity Часть 2: автоматизация генерации изображений с помощью инструмента generate_image","summary":"Это вторая часть пятисерийного цикла команды Google 'Elevating Antigravity Agent Skills', в которой объясняется, как использовать инструмент generate_image в навыках агента, сочетая структурированные подсказки с генерацией изображений, чтобы агент создавал изображения, соответствующие стандартам разработчика.","category":"行业动态","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"Серия учебных курсов Google Antigravity Часть 2: автоматизация генерации изображений с помощью инструмента generate_image - Aioga Новости ИИ","description":"Это вторая часть пятисерийного цикла команды Google 'Elevating Antigravity Agent Skills', в которой объясняется, как использовать инструмент generate_image в навыках агента, сочета...","url":"https://www.aioga.com/ru/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:04:47.340Z"},"ar":{"title":"سلسلة دروس Google Antigravity الجزء 2: استخدام أداة generate_image لتوليد الصور تلقائيًا","summary":"هذه المقالة هي الجزء الثاني من سلسلة خمسية لفريق Google بعنوان رفع مهارات الوكيل المضاد للجاذبية، وتوضح كيفية استخدام أداة إنشاء الصور في مهارات الوكيل، ودمج الكلمات الإرشادية البنيوية مع إنشاء الصور الأصلية، لتمكين الوكيل من إنتاج صور تتوافق مع معايير المطورين.","category":"行业动态","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"سلسلة دروس Google Antigravity الجزء 2: استخدام أداة generate_image لتوليد الصور تلقائيًا - Aioga أخبار الذكاء الاصطناعي","description":"هذه المقالة هي الجزء الثاني من سلسلة خمسية لفريق Google بعنوان رفع مهارات الوكيل المضاد للجاذبية، وتوضح كيفية استخدام أداة إنشاء الصور في مهارات الوكيل، ودمج الكلمات الإرشادية البن...","url":"https://www.aioga.com/ar/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:05:30.487Z"},"hi":{"title":"Google Antigravity सीरीज ट्यूटोरियल पार्ट 2: generate_image टूल का उपयोग करके छवि उत्पन्न करना स्वचालित करना","summary":"यह Google टीम की 'Elevating Antigravity Agent Skills' पाँच-भाग श्रृंखला का दूसरा भाग है, जिसमें यह बताया गया है कि एजेंट स्किल में generate_image टूल का उपयोग कैसे किया जाता है, संरचित संकेतों को मूल चित्र निर्माण के साथ मिलाकर कैसे संयोजित किया जाता है, ताकि एजेंट डेवलपर के मानकों के अनुसार चित्र उत्पन्न कर सके।","category":"行业动态","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"Google Antigravity सीरीज ट्यूटोरियल पार्ट 2: generate_image टूल का उपयोग करके छवि उत्पन्न करना स्वचालित करना - Aioga AI समाचार","description":"यह Google टीम की 'Elevating Antigravity Agent Skills' पाँच-भाग श्रृंखला का दूसरा भाग है, जिसमें यह बताया गया है कि एजेंट स्किल में generate_image टूल का उपयोग कैसे किया जाता है, सं...","url":"https://www.aioga.com/hi/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:05:32.047Z"},"it":{"title":"Serie di tutorial Google Antigravity Parte 2: automatizzare la generazione di immagini con lo strumento generate_image","summary":"Questo è la seconda parte della serie in cinque episodi del team Google \"Elevating Antigravity Agent Skills\", che spiega come utilizzare lo strumento generate_image nelle competenze dell'agente, combinando prompt strutturati con la generazione di immagini nativa, permettendo all'agente di produrre immagini conformi agli standard degli sviluppatori.","category":"行业动态","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"Serie di tutorial Google Antigravity Parte 2: automatizzare la generazione di immagini con lo strumento generate_image - Aioga Notizie IA","description":"Questo è la seconda parte della serie in cinque episodi del team Google \"Elevating Antigravity Agent Skills\", che spiega come utilizzare lo strumento generate_image nelle competenz...","url":"https://www.aioga.com/it/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:06:14.122Z"},"nl":{"title":"Google Antigravity-seriehandleiding Deel 2: Automatisch afbeeldingen genereren met de generate_image-tool","summary":"Dit is het tweede deel van de vijfdelige serie 'Elevating Antigravity Agent Skills' van het Google-team, waarin wordt uitgelegd hoe je in agentvaardigheden de generate_image-tool kunt gebruiken, en hoe je gestructureerde prompts kunt combineren met native afbeeldingsgeneratie, zodat de agent afbeeldingen kan produceren die voldoen aan de ontwikkelaarsnormen.","category":"行业动态","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"Google Antigravity-seriehandleiding Deel 2: Automatisch afbeeldingen genereren met de generate_image-tool - Aioga AI-nieuws","description":"Dit is het tweede deel van de vijfdelige serie 'Elevating Antigravity Agent Skills' van het Google-team, waarin wordt uitgelegd hoe je in agentvaardigheden de generate_image-tool k...","url":"https://www.aioga.com/nl/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:06:08.953Z"},"tr":{"title":"Google Antigravity Serisi Eğitimleri Bölüm 2: generate_image Aracı ile Görüntü Oluşturmayı Otomatikleştirme","summary":"Bu, Google ekibinin Elevating Antigravity Agent Skills beşlemesinin ikinci kısmıdır ve agent becerilerinde generate_image aracının nasıl kullanılacağını, yapılandırılmış ipuçlarının sentezlenmesini ve doğal görüntü üretimi ile birleştirilmesini anlatarak, agent'ın geliştirici standartlarına uygun görüntüler üretmesini anlatıyor.","category":"行业动态","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"Google Antigravity Serisi Eğitimleri Bölüm 2: generate_image Aracı ile Görüntü Oluşturmayı Otomatikleştirme - Aioga AI Haberleri","description":"Bu, Google ekibinin Elevating Antigravity Agent Skills beşlemesinin ikinci kısmıdır ve agent becerilerinde generate_image aracının nasıl kullanılacağını, yapılandırılmış ipuçlarını...","url":"https://www.aioga.com/tr/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:06:58.926Z"},"vi":{"title":"Hướng dẫn Google Antigravity phần 2: Sử dụng công cụ generate_image để tự động tạo hình ảnh","summary":"Bài này là phần thứ hai trong chuỗi năm phần của nhóm Google về Nâng cao Kỹ năng Tác nhân Chống trọng lực, giải thích cách sử dụng công cụ generate_image trong kỹ năng tác nhân, kết hợp việc tổng hợp các từ gợi ý có cấu trúc với tạo hình ảnh nguyên sinh, để tác nhân tạo ra hình ảnh phù hợp với tiêu chuẩn của nhà phát triển.","category":"行业动态","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"Hướng dẫn Google Antigravity phần 2: Sử dụng công cụ generate_image để tự động tạo hình ảnh - Tin tức AI Aioga","description":"Bài này là phần thứ hai trong chuỗi năm phần của nhóm Google về Nâng cao Kỹ năng Tác nhân Chống trọng lực, giải thích cách sử dụng công cụ generate_image trong kỹ năng tác nhân, kế...","url":"https://www.aioga.com/vi/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:06:57.162Z"},"id":{"title":"Seri Tutorial Google Antigravity Bagian 2: Mengotomatiskan Pembuatan Gambar dengan Alat generate_image","summary":"Ini adalah bagian kedua dari seri lima bagian Google Tim 'Elevating Antigravity Agent Skills', menjelaskan bagaimana menggunakan alat generate_image dalam keterampilan agen, menggabungkan kata-kata prompt terstruktur dengan pembuatan gambar asli, sehingga agen menghasilkan gambar yang sesuai dengan spesifikasi pengembang.","category":"行业动态","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"Seri Tutorial Google Antigravity Bagian 2: Mengotomatiskan Pembuatan Gambar dengan Alat generate_image - Berita AI Aioga","description":"Ini adalah bagian kedua dari seri lima bagian Google Tim 'Elevating Antigravity Agent Skills', menjelaskan bagaimana menggunakan alat generate_image dalam keterampilan agen, mengga...","url":"https://www.aioga.com/id/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:07:34.702Z"},"th":{"title":"ชุดบทเรียน Google Antigravity ตอนที่ 2: ใช้เครื่องมือ generate_image ในการสร้างภาพอัตโนมัติ","summary":"บทความนี้เป็นส่วนที่สองของห้าส่วนของชุดเรื่อง Elevating Antigravity Agent Skills ของทีม Google อธิบายวิธีการใช้เครื่องมือ generate_image ในทักษะของเอเย่นต์ ซึ่งรวมคำสั่งเชิงโครงสร้างเข้ากับการสร้างภาพดั้งเดิม ทำให้เอเย่นต์สร้างภาพที่ตรงตามมาตรฐานของนักพัฒนาได้","category":"行业动态","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"ชุดบทเรียน Google Antigravity ตอนที่ 2: ใช้เครื่องมือ generate_image ในการสร้างภาพอัตโนมัติ - ข่าว AI Aioga","description":"บทความนี้เป็นส่วนที่สองของห้าส่วนของชุดเรื่อง Elevating Antigravity Agent Skills ของทีม Google อธิบายวิธีการใช้เครื่องมือ generate_image ในทักษะของเอเย่นต์ ซึ่งรวมคำสั่งเชิงโครงสร้...","url":"https://www.aioga.com/th/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:07:43.331Z"},"pl":{"title":"Seria samouczków Google Antigravity Część 2: Automatyzacja generowania obrazów za pomocą narzędzia generate_image","summary":"To jest druga część pięcioczęściowej serii zespołu Google \"Elevating Antigravity Agent Skills\", omawiająca, jak używać narzędzia generate_image w umiejętnościach agenta, łącząc strukturalne wskazówki w generowaniu obrazu z rodzimym generowaniem obrazów, aby agent tworzył obrazy zgodne ze specyfikacjami dewelopera.","category":"行业动态","source":"Google AI：DEV 作者专属（RSS）","aggregationSource":"Google AI：DEV 作者专属（RSS）","pageTitle":"Seria samouczków Google Antigravity Część 2: Automatyzacja generowania obrazów za pomocą narzędzia generate_image - Aioga Wiadomości AI","description":"To jest druga część pięcioczęściowej serii zespołu Google \"Elevating Antigravity Agent Skills\", omawiająca, jak używać narzędzia generate_image w umiejętnościach agenta, łącząc str...","url":"https://www.aioga.com/pl/news/cmtiyodib01zuroelumvkcmcj/","contentTranslated":true,"sourceHash":"c3740abaa44a3053","translatedAt":"2026-09-01T18:08:27.680Z"}},"evidenceTier":"verified-news","reviewStatus":"automated-ingest","indexable":true,"editorialCover":""}}