WaifuXL - SOTA image upscaling neural network that runs in the browser
WaifuXL is our state of the art super resolution model trained on ~1,200,000 anime style images from the Danbooru2021 dataset. You can run it straight from your browser, entirely client-side, at https://waifuxl.com. Using the Onnx Runtime, we stream the weights of our ML models directly onto your device to be executed locally in WebAssembly. Doing so allows us to provide this service solely through a static webpage, no backend for model execution needed. This has the added benefit of enabling the privacy of your images--your images are not, and never will be, sent to us. Our…
In plain words
WaifuXL is a neural network for image upscaling trained on 1.2 million anime-style images. It runs entirely in the browser using WebAssembly, with no server backend required, meaning images never leave the user's device. The tool is designed for anyone needing to enlarge anime or manga artwork, though it can also process real photographs. Users access it directly through a static webpage without installation.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
WaifuXL is our state of the art super resolution model trained on ~1,200,000 anime style images from the Danbooru2021 dataset. You can run it straight from your browser, entirely client-side, at https://waifuxl.com. Using the Onnx Runtime, we stream the weights of our ML models directly onto your device to be executed locally in WebAssembly. Doing so allows us to provide this service solely through a static webpage, no backend for model execution needed. This has the added benefit of enabling the privacy of your images--your images are not, and never will be, sent to us. Our original inspiration for this project was waifu2x (http://waifu2x.udp.jp). In general, our model will outperform those used on waifu2x by a significant margin, without the need for multiple models trained on various noise reduction levels. Note that while you _can_ upscale natural (real) images, the model was only trained on anime style drawings, so don’t expect good results. It does work quite well on non-anime graphic art, however. For more information, see our blog post at https://haydn.fgl.dev/posts/the-launch-of-waifuxl/
Does the same job
all alternatives →
- RARubbrband – A hosted ComfyUI alternative for image generation2024 · ▲61
Hey HN! My friends and I built a new platform for generating images. The app is easy to use for people who find ComfyUI hard to use, or just simply don’t have a GPU to use it on. For those not familiar, ComfyUI is a great tool for using open-source models like Stable Diffusion. It’s primarily great because it’s a node-based tool, which means you can chain together models, upscalers, prompting nodes, etc… which let you create images in the exact aesthetic you want. There’s also a vibrant dev community behind ComfyUI, which means that there are a ton of nodes and customizability. We’re users…
- STSynthesize TikZ Graphics Programs for Scientific Figures and Sketches2024 · github.com · ▲132
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…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2022
the whole month →
Peerlist▲1,052A professional network w/ robust work profiles at its core
Life & fun · 2022 · peerlist.io
- MA
Life & fun · 2022 · github.com
