一个兼容 OpenAI 的 API,接入 500+ 图像、视频、音频与大模型
覆盖 459 类工作流,通过流量估算、产品功能与替代方案辅助选型。
“reference image” · 编程与软件开发·126 个结果
重新开始一个兼容 OpenAI 的 API,接入 500+ 图像、视频、音频与大模型
Hyper3D Rodin is an AI 3D asset generator that converts text prompts or reference images into detailed, editable 3D models with ready-to-use UVs. It pairs generative 3D with ControlNet-style spatial guidance, partial editing, texture, HDRI and avatar tools, an API, MCP access and plug-ins for major 3D pipelines.
Hyper3D Rodin is an AI 3D asset generator that converts text prompts or reference images into detailed, editable 3D models with ready-to-use UVs. It pairs generative 3D with ControlNet-style spatial guidance, partial editing, texture, HDRI and avatar tools, an API, MCP access and plug-ins for major 3D pipelines.
Vidu is a multimodal generative video platform from ShengShu Technology. It turns text prompts, still images, and reference footage into short cinematic clips, with tools for subject-consistent characters, anime styles, and sound-effect generation.
Vidu is a multimodal generative video platform from ShengShu Technology. It turns text prompts, still images, and reference footage into short cinematic clips, with tools for subject-consistent characters, anime styles, and sound-effect generation.

Srefs.co is the largest Midjourney style reference library, with tens of thousands of srefs you can browse, search, save and reuse. It includes a Multiprompt tool for blending several styles at once and a generator that applies selected srefs directly, so you can keep a consistent look across an entire project.
Srefs.co is the largest Midjourney style reference library, with tens of thousands of srefs you can browse, search, save and reuse. It includes a Multiprompt tool for blending several styles at once and a generator that applies selected srefs directly, so you can keep a consistent look across an entire project.


用文本或图片无限生成 AI 3D 模型

永不重绘产品的 AI 产品摄影
集抠图、修图、放大与图像生成于一体的 AI 图片编辑套件
一站式浏览器工作台,AI 照片与视频编辑加生成能力
Glif is an AI creative agent that turns a written brief into finished images, videos and audio from one chat interface. Rather than making you pick a model and learn its settings, Glif analyses each part of your request, chooses from a library of leading image, video, audio and language models, uses its own design-evaluation tools to judge which output is strongest, and selectively regenerates weak results. Characters, references and project context persist across a project, so the hundredth asset still matches the first, and you can connect Glif to Claude, Cursor, ChatGPT, Codex or VS Code to use it inside the agents you already run.
Glif is an AI creative agent that turns a written brief into finished images, videos and audio from one chat interface. Rather than making you pick a model and learn its settings, Glif analyses each part of your request, chooses from a library of leading image, video, audio and language models, uses its own design-evaluation tools to judge which output is strongest, and selectively regenerates weak results. Characters, references and project context persist across a project, so the hundredth asset still matches the first, and you can connect Glif to Claude, Cursor, ChatGPT, Codex or VS Code to use it inside the agents you already run.

把 PNG、JPG、BMP 图片转换为可缩放的 SVG、EPS、DXF 矢量图

一个 API 调用 LLM、图像、视频与音频模型,直达生产环境

Flux1 AI is a browser-based AI image and video generator that runs Black Forest Labs' FLUX models alongside other leading image and video models, with no GPU or installation required.
Flux1 AI is a browser-based AI image and video generator that runs Black Forest Labs' FLUX models alongside other leading image and video models, with no GPU or installation required.

GitBook is a documentation platform that helps teams create, publish, and maintain product docs, API references, and knowledge bases. It pairs a block-based editor and Git Sync with AI tooling that answers reader questions, flags stale content, and keeps docs accurate for both people and AI agents.
GitBook is a documentation platform that helps teams create, publish, and maintain product docs, API references, and knowledge bases. It pairs a block-based editor and Git Sync with AI tooling that answers reader questions, flags stale content, and keeps docs accurate for both people and AI agents.



对新手友好的 AI 绘画生成器,支持姿态控制

Readdy is an AI website builder that generates complete, production-ready websites from plain-language prompts, uploaded screenshots, Figma frames, or a reference URL. It adds hosting, a built-in backend, forms, SEO tools, and code export so one platform can build and run the whole site.
Readdy is an AI website builder that generates complete, production-ready websites from plain-language prompts, uploaded screenshots, Figma frames, or a reference URL. It adds hosting, a built-in backend, forms, SEO tools, and code export so one platform can build and run the whole site.
