Hi HN,I built PaperBanana to help researchers create professional scientific figures and diagrams using AI.It turns text descriptions or rough sketches into publication-ready illustrations, including system architectures, flowcharts, and schematics.I’d love to hear your feedback on the output quality and what scientific styles you’d like to see added.
Hey HN! I built MuseVideo, an AI video generation platform that gives you access to multiple state-of-the-art models in one place. What it does: - Text-to-video and image-to-video generation - Supports Sora 2, Sora 2 Pro, Veo 3.1, Wan 2.5, and more - Text-to-image with Nano Banana, Seedream, and Z-Image - Pay-per-use credits system (no forced subscriptions) Why I built this: ...
Hi HN! I built Nano Banana 2, a SaaS platform for AI-powered image using Google's Gemini 2.5 Flash. You can try it for free.Would love your feedback!
Hi HN, I built DreamOmni to turn text prompts into brand-ready visuals for small marketing teams and indie founders. Describe what you need and get several polished options in seconds. Core features: - Brand kits to lock fonts and colors - Batch generation for campaign assets - Version history and quick exports I’d love feedback on usability and pricing. Thanks for...
AI-powered photo to drawing converter. Try it free with Google login - 2 conversions included. Built with Next.js 15 + Gemini 2.5 Flash.
Our platform offers dual video creation modes: text-to-video AI that generates cinematic content from your descriptions, and image-to-video that animates static images into dynamic
footage. Perfect for marketers, content creators, educators, and businesses seeking high-quality video content without expensive production costs or technical expertise.
With support for multiple aspect ratios (landscape, portrait, square), up to 8-second video generation, lip-sync capabilities, and commercial usage rights, Wan2-5.com delivers
studio-quality results optimized for social media, marketing campaigns, presentations, and creative projects. Join 10,000+ users already revolutionizing their video production workflow
with AI-powered creativity.The fact that you're daily driving this speaks volumes about its usability despite being a "toy" project. A few questions: - How's the learning curve for someone coming from Vim/Neovim? - The org-mode-like feature sounds intriguing - can you elaborate on what Ctrl-C Ctrl-C does? - Any plans to add plugin support, or are you keeping it intentionally minimal?
The Helix color theme borrowing is smart - no need to reinvent good design choices.
I can see this being particularly valuable for: - Debugging weird SSL/TLS handshake issues - Analyzing API response timing problems - Understanding network-level failures that don't show up in application logs
The reusable configs feature is especially clever - manually crafting tshark filters every time is such a pain. How complex can these configs get? Can you chain multiple filters together?