Alternatives
Products that do what Soot, a tool for visualizing and searching sets of images does
Hey everyone, I’m excited to share a project I’ve been working on: a tool for visualizing and searching massive sets of images. To demonstrate its capabilities, I decided to upload the 5000 best Magic: The Gathering cards into it. Here’s what you can do with it: Advanced Search: Find images based on any criteria you desire Image tagging and metadata: Cluster your images based on attributes Interactive Filters: Narrow down your search with various filters and categories Generative Content: Based on your content, generate similar images with Dall-E 3 Check it out and let me know what you…
- 1
- 2IT
I've been teaching LLMs to play Magic: The Gathering recently, via MCP tools hooked up to the open-source XMage codebase. It's still pretty buggy and I think there's significant room for existing models to get better at it via tooling improvements, but it pretty much works today. The ratings for expensive frontier models are artificially low right now because I've been focusing on cheaper models until I work out the bugs, so they don't have a lot of games in the system.
Feb 2026 · mage-bench.com
- 3HE
This is a personal project I've been working on for a long time now. I stumbled upon the color quantization problem while doing something related for work. I then found an interesting paper for which I could find no implementations online, and the thing went from "let's implement this paper" to getting pretty obsessed with the whole thing. It's at an early, eaaaarly stage. There's a lot of work to be done, and it's a memory hog, but generally speaking works quite well, and the output is for the most part very high quality, so I'm happy to share it as beta.
2025 · github.com
- 4
- 5IM
I was fascinated by this [0] and this video [1]. After many struggles, I finally built this app that traces images using circles similar to what these videos had shown. The most challenging part (to me) is to find a way to convert images to vector lines. I had tried Potrace, but its output is not suitable for my use case: too many small elements share the same border. Potrace's goal is to represent the original image faithfully using vector lines. But I want to trace the image edges. After searching and trying some Potrace alternatives in vain, I finally found my keyword. Surprisingly (to…
2022 · phqb.github.io
- 6FC
Hi HN! I've found this visualization tool immensely helpful over the years for getting an intuition for how an LLM "sees" some piece of text, and with a bit of elbow grease decided to move all compute to client side so I could make it publicly available. I've found it particularly useful for - Understanding exactly how repetition and patterns affect a small LM's ability to predict correctly - Understanding different tokenization patterns and how it affects model output - Getting a general sense of how "hard" different prediction tasks are for GPT-style models Known problems (that I probably…
2023 · perplexity.vercel.app
- 7ST
Creating high-quality scientific figures can be time-consuming and challenging, even though sketching ideas on paper is relatively easy. Furthermore, recreating existing figures that are not stored in formats preserving semantic information is equally complex. To tackle this problem, we introduce DeTikZify, a novel multimodal language model that automatically synthesizes scientific figures as semantics-preserving TikZ graphics programs based on sketches and existing figures. We also introduce a Monte Carlo Tree Search-based inference algorithm that enables DeTikZify to iteratively refine its…
2024 · github.com
- 8IM
2022 · generrated.com
- 9PT
Hello Hacker News! I’ve been having some fun recently and I wanted to share with you. My idea was to feed ChatGPT an image and ask for a caption, feed that back to DallE, then call this in a loop, and observe how the image that was generated changed over time. Similar to playing the game “telephone”. The results were really intriguing, so I built something that you can play with. Note this is best on a desktop (streamlit is optimized for a large screen), but if you’re on mobile you’ll want to expand the sidebar to start — it’s the carrot on top. My initial intention was for you to be able to…
2023 · share.streamlit.io
- 10
- 11MU
Hi Hackernews! Mage is the incredibly simple and fun platform with over 50+ top, custom Text-to-Image AI models as well as Text-to-GIF for all to create with their imagination, unlimited & unfiltered. Start with fast and unlimited Stable Diffusion for free! The first Mage link posted ever was here on HackerNews back in September with the promise of Free, Fast, & Unfiltered Stable Diffusion. Turns out, avoiding the h*ll of pip installs and CUDA errors while enjoying this incredible tech was (and is) a popular idea! Since then, we've grown into an incredible community, with a lively Discord…
2023 · mage.space
- 12IF
So, after many years of kicking about little apps and not putting the full effort in, I decided to bite the bullet and get on with it. Very much inspired by patio11 and Bingo Card Creator, I present Griddol (http://www.griddol.com) a tool to create and play word searches. Intended mainly for teachers, but encouraging those who like a word search too. This been churning around in my head for over a year in various forms, and I used the concept to help learn CoffeeScript, CouchDB and node.js, so even if the product itself is a failure, the learning process has been valuable. I'll be the first…
2011
- 13WV
Hi, I wanted to share with You our project (https://comparere.io). We have built a website for comparing graphics and designs. The concept is simple, you have to just drag'n drop two designs you are having trouble to pick from. The idea has emarged when we stumbled across many different facebook groups for graphic designers, where they used to sometimes ask the community for help to decide which design is better. I had similar problem too. Hopefully this tool will help graphic/ux designers build/create projects that will appeal to more audiences. We are looking forward to…
2019
- 14IB
Hi HN, I'm excited to share a project I've built: PixelateImage.org. Instead of being a traditional image editor, this is an *AI-powered tool that generates pixel art directly from your text prompts.* If you've ever wanted to create unique pixel art characters, scenes, or assets for games, art projects, or just for fun, but perhaps lacked the specific artistic skills or time, this might be for you. My goal was to make generating retro-style or modern pixel art more accessible. You can type in a description (e.g., "a brave knight in a dark forest," "a futuristic cityscape at night," "a cute…
2025 · pixelateimage.org
- 15AG
I found myself collecting a ton of different styles to explore and get inspiration for other photos so I built this to share the collection with others. The site was also completely coded using ChatGPT.
2025 · imagestyles.ai
- 16IM
Recently there were some changes to the Twitter algorithm and one of the most important ones was boosting video content even more in the feed, which got me thinking: "Why shouldn't we benefit from the algo changes and get a boost every time we are sharing some visuals?" So I spent the weekend building a tool that: - Turns your images into videos - Has 30 beautiful animated gradients that we can pick from - Is completely FREE I'd love to know your thoughts about it!
2023 · clippulse.com
- 17DR
Hi HN! The children in my family love to draw and are beginning to explore digital drawing tools, but they've been somewhat discouraged by the complexity of popular software like GIMP, Photoshop, etc. I was motivated to create a tool that encouraged their artistic creativity and also piqued their technical curiosity. With the release of SDXL-Turbo in late Nov 2023, it became feasible to perform text-guided image to image generation in real-time on a consumer grade GPU. Inspired by this progress and my little cousins' artwork, I put together a web app that integrates an interactive canvas &…
2024 · github.com
- 18II
2015 · demo.algolia.com
- 19UI
Hey everyone! I am excited to share updates on four of my & my teams' open-source projects that take large-scale search systems to the next level: USearch, UForm, UCall, and StringZilla. These projects are designed to work seamlessly together, end-to-end—covering everything from indexing and AI to storage and networking. And yeah, they're optimized for x86 AVX2/512 and Arm NEON/SVE hardware. USearch [1]: Think of it as Meta FAISS on steroids. It's now quicker, supports clustering of any granularity, and offers multi-index lookups. Plus, it's got more native bindings than probably…
2023 · usearch-images.com
- 20CG
I've been building https://cardcast.gg, a web app for playing paper Magic: The Gathering remotely. You point a webcam at your play area and it identifies cards as you put them down. It's an alternative to Spelltable that I built for my friend group to play weekly with. The main technical difference is detection. Spelltable uses perceptual hashing; cardcast uses modern ViT backbones so it's much faster and more accurate. If you import a decklist from Moxfield, Archidekt, or MTGGoldfish, the search narrows to that deck's card pool, greatly reducing false-positives. What I have so…
Apr 2026 · cardcast.gg
- 21IM
It works by using open AIs new gpt-image API, image processing algorithms and some prompt engineering. Still has some limitations, but can already generate ready to use assets.
2025 · pixel-gen.ai
- 22IJ
Hey everyone, I'm excited to share a brand new side project I just finished building: phototopixel.art. It's a simple web tool that automatically converts any photo you upload into pixel art. I've always been a fan of the aesthetic of pixel art, but manually creating it is a tedious process. After trying out some existing tools and not being fully satisfied with the results, I decided to build my own. My goal was to create a fast and easy-to-use solution that consistently produces great-looking pixel art. Behind the Scenes The core of the tool uses a combination of color quantization and…
2025 · phototopixel.art
- 23BI
Hello HN, I built Bulk Image Generator because I was frustrated with how slow it is to iterate on visual assets. Tools like Midjourney are great for single images, but when you need 50+ variations of a product shot or a game asset based on a specific reference, the manual process is a pain. What it does: Upload one reference image and generate 100+ AI variations while maintaining style/structure. Batch background removal (because once you generate 100 images, you usually need to clean them up). Fast bulk download. Why I’m sharing it here: I’m looking for feedback on the consistency of…
Mar 2026 · bulkimagegenerator.app
- 24IB
I built a tool to roast landing pages with AI agents. I was gathering feedback from watching landing page roast videos, and figured out I could prompt LLMs to analyse a screenshot and roast based on the same criteria. It's not 100% accurate yet, but it has been really insightful when I've tested it on my own websites. Let me know what you think!
2024 · roastmylandingpage.io
Ranked by how close each launch is in meaning, then by votes. Refine with a description →