创意工具1 month ago
PicSpeak | AI Photo Critique and GPT Image 2 Visual References
上传照片获得 AI 对构图、光线、色彩的分析，生成视觉参考。
Open source
PicSpeak — 基于 AI 的摄影点评 Web 应用，上传一张照片，几秒钟内即可获得对构图、光线与色彩的专业分析，同时可以向社区展示你的优秀作品。
完整作品展
技术栈
60 projects
上传照片获得 AI 对构图、光线、色彩的分析，生成视觉参考。
PicSpeak — 基于 AI 的摄影点评 Web 应用，上传一张照片，几秒钟内即可获得对构图、光线与色彩的专业分析，同时可以向社区展示你的优秀作品。
用文本提示和参考图像创建和编辑AI图像。
FLUX 3 AI Image Generator — 多模型 AI 图片生成与编辑工作台，支持文字生图、参考图编辑、宽高比与多语言文字控制，并清晰标注模型可用状态
AI 图像编辑与生成工具，在浏览器和移动设备上编辑和扩展图像。
visuali · HN
Like Claude Code for Images
Flint是为AI代理设计的可视化语言,用于创建交互式数据可视化。
chenglong-hn · HN
Data visualizations are the bridge between user and data. But building AI agents that can generate visualizations reliably can be very tricky: - simple chart specs can be reliable, but generated charts are often of low quality due to reliance on system defaults; - complex chart specs with explicit details can produce good-looking charts, but they are verbose and agents can struggle with reliability We figured out it is a limitation on the language issue (not just AI capability thing) -- current visualization languages are a bit too low-level for AI agents, requiring them to explicitly make visual decisions that are supposed to be handled by a good compiler. Flint is a visualization intermediate language to address this issue, allow AI agents to solve this last-mile human-agent interaction problem. It provides a simple semantic-type based specification, and contains a layout optimization engine that can produce good-looking charts (filled with derived low-level details) from simple
Avnac 是一个开源设计工具，可在浏览器中创建图形。
@akinkunmi · X
He trash-talked me and my amazing project ( unprovoked while all his projects are vibe-coded slop. That's why I named him King of Slop.
从 Adobe Illustrator 导入 2D 路径，在 3D 中变换并以矢量格式导出。
@kamone · X
I built (vibe coded) my own geometry engine from scratch. It keeps path as path, and does the transformation and the silhouette splitting. You can see the code here. One single html file.
React 和 shadcn/ui components，用于在营销和登陆页面上创建 animated visual elements
@pixelcave_john · X
Hey Germán! I recently launched and a major update to Tailkit!
浏览精选 Midjourney sref 代码库，快速生成特定图像风格。
Midjourney Sref code 精选库 — 在 Midjourney 的 prompt 输入 `--sref xxx` ，可以固定生成某种特定风格的图片。这对很多人来说非常方便，不用写一堆效果词，只要记住几位数字就可以。但 `--sref xxx` 有大概 40 亿个，其中重复或者质量不佳的不在少数。因此做了一个网站把一些个人觉得不错的 sref code 收集起来并进行分类，方便新人或
从文本、图像或参考片段生成AI视频，支持动作控制。
VidLux AI — AI 视频生成与编辑平台，支持文生视频、图生视频、参考生视频和视频编辑
将屏幕录制转换为精美的PDF指南。
@vanmurten_eth · X
Guidesnap: turn any screen recording into a polished PDF guide.
使用 Seedream 5.0 Pro 生成和编辑 AI 图像，支持 2K 输出和参考图像。
imaginevid-ai · GitHub
Awesome-seedream-5-pro-prompts-and-skills About World's largest Seedream 5.0 Pro prompt library — 10,000+ curated prompts with preview images, 16 languages. Dreamina Seeream AI image generation. Free & open source.
科学引文网络与论文的交互式WebGL可视化。
@lushptr · X
I feel really guilty for vibe coding this but it looks cool even tho it is really inefficient and broken you can use it too now I'll desloppify it after exams I swear