The full gallery
Tech stack
60 projects
Generate infographics from text using AI with 17 visual styles and 20 layout templates.
SummaGraph — AI 信息图生成工具，粘贴任意形式的文本即可一键生成高质量信息图，内置 20 种视觉风格 × 20 种布局模板，支持系列模式一次生成多页风格连续的信息图，覆盖中英日韩等 9 种语言
Transform photos into artistic styles like Ghibli, Polaroid, Sketch, and Pixar.
Style Ai — 免费 GPT-4o 绘画工具，轻松将图片转成吉卜力、史努比、3D 盲盒等功能
Design visual art with lines and forms directly in your browser.
@josephflaherty · X
by @golnik is the best vibe-coded software project I've seen, both in its aesthetics and the difficulty of its accomplishment. You can see the finished output of his work here:
Browse Midjourney style reference codes to customize AI-generated images.
Midjourney 样式代码库 — SrefHunter 汇集各种社交媒体平台的 Midjourney 样式代码
Visual Ideas is a free toolkit for solo creators: build and export HTML emails, plan posts in a social calendar, and turn pages into branded LinkedIn carousels. No account required
@criss_design · X
🚗 Carviano — automotive storytelling 🐾 My Pet's Stories — pet memories 💼 Orkely — invoicing & proposals (Microsoft Store) ✉️ Visual Ideas — email builder
Balance images and logo clouds by visual weight using perceptual science — not bounding boxes. Free in your browser, no signup.
@MarkPraschan · X
Upload a photo to get AI critique on composition, lighting, and color, then generate visual references for your next shoot.
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。
Create AI-animated live wallpapers using visual flows or trendy style templates.
@suwakopro · X
一直想用ai做动态壁纸，试了半天各种方案感觉基本没有找到能做到无限完美循环的，无论是首尾帧还是试了试civitai上面的几个基于wan2.2的几个模型，感觉效果一般，最后找到这家： 不需要用这个网站上面卖的模型，可以直接用grok生成一段视频，grok生成动态桌面性价比特别好，还特别便宜，基本上免费的480p就够用了，用类似这样的提示词： 可循环，呼吸，胸部随着呼吸晃动，首尾循环，wallpaper engine，Static camera, Fixed camera, Locked-off shot, Tripod shot, No camera movement, Camera remains still. 你可以根据视频往里面加一些提示词增加动态。 制作前可以先剪辑一下，大概保证首尾帧之间留着1.5秒的动作，如果首尾帧不对，那么生成的结果可能会导致速度，节奏怪异。但是这个模型感觉还可以，你用grok生成的视频大部分都不需要剪就可以用了。然后可以用这里面的超分模型放大，或者自己找一个本地的超分模型也可以 我做了一个示例： 根据这个图： 可以看到循环的效果还是挺不错的，即使特意做了比较大的动态循环也基本看不出问题 只用充一个最低档，只用循环模型就够你把想要的图全部做成动态桌面了。 估计以后minimax h3会有人训练做这种无限循环的lora，效果应该会更好。
Try different beard styles and colors on your face with realistic virtual previews.
Beardstyle AI — 虚拟试戴胡子
Generate personalized fashion looks from your photos while preserving your identity.
@skyvizlabs · X
Discover the first AI fashion engine that preserves your REAL identity and face geometry. We just launched @TrendilyAI on @ProductHunt! 🎉 Try it live today: #buildinpublic #AI #FashionTech
Turn your PDF portfolio into an interactive online gallery with multiple viewing modes.
@il_deil · X
I’m building an interactive, ultra-minimalist portfolio platform strictly for architects & designers, because I tired of ads and clutter ruining portfolio on Issuu and same services. I made zero visual noise. Multiple viewing modes. Just your portfolio
Browser-based AI image editor and generator with infinite canvas, available as desktop and mobile apps.
visuali · HN
Like Claude Code for Images
