创意工具3 days ago
AI Pixel Art Generator & Editor for Game Assets | Sprite Fusion
用AI生成专业像素艺术精灵和图标，在浏览器中编辑和导出。
Open source
hugodpz · Product Hunt
AI Pixel Art Generator The professional AI pixel art generator for game developers
完整作品展
技术栈
60 projects
用AI生成专业像素艺术精灵和图标，在浏览器中编辑和导出。
hugodpz · Product Hunt
AI Pixel Art Generator The professional AI pixel art generator for game developers
AI平台，提问、生成图像、语音交互，辅助更好的决策。
@Akinzoooo · X
通过ImagesArt.ai从文本描述生成专业图像，支持多个AI模型。
ImagesArt.ai — 生成完美的AI艺术提示词。使用这个工具为Flux、Midjourney和Stable Diffusion模型生成并优化图像提示词。
创建AI角色、与其聊天并生成图像。
@Bubioai · X
Content creation made easy. Bring cinematic image + video generation into your workflow with Skill. Install it in Claude Code, Codex, Cursor, Gemini, etc. Connect the API key, and create from natural-language prompts, without leaving your flow. Download the skill and start building.
用AI生成定制乐高设计和小人偶，支持文本、照片和动画。
Brick Center — 如果您是一位乐高爱好者，热衷与创造各种乐高形象，BrickCenter 可以将您的创意，自动生成乐高设计图。AI 乐高生成器可以将你的文字转换成定制的乐高套装。轻松地从照片创建你自己的小人偶，如果您觉得乐高头像很酷，也可以将您的自拍图片，生成乐高头像。还可以来网站浏览由爱好者精心制作的独一无二的乐高作品 - [更多介绍](https://www.bilibili.co
用 Google Gemini 生成和编辑 AI 图像
Nano Banana AI — 基于市面上最强的 AI 图像编辑模型 Nano Banana 开发的图片编辑器，用嘴改图、保持角色一致性、控制细节、图片融合
AI 60 秒内生成品牌化提案、发票和专业文档 PDF。
@AadyaAI · X
Aadya AI turns a client conversation into a branded, ready-to-send proposal or invoice PDF in 60 seconds — no templates, no formatting, no chasing.
Make Manga：用 AI 将故事转化为漫画和视频。
MakeManga — AI 生成漫画，支持 Nano Banana 和 Seedream 4.0 模型，只需提供故事，剩下的分镜和角色生成等都交给 AI
开源 AI 画布工具，可在浏览器中生成 UI 原型、文章封面、Logo、贴纸和社交媒体配图。
MuseUI — 开源的纯浏览器运行的 AI 画布式图片工作台，可生成 UI 原型、文章封面、信息图、Logo、贴纸、社交媒体配图
StoryIntoVideo：将故事转化为有AI角色和旁白的短视频
StoryIntoVideo — AI 故事转视频 | 小说一键生成短剧视频
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
