Alternatives
Products that do what OpenCode Senses, An insanely fast and highly accurate vision plugin does
The vision plugin for OpenCode that truly understands images. Inspect, read, and reason about any screenshot or picture with deeper understanding than any other plugin — fully local, private, and free. Normally, it takes 300ms to analyse one image on my laptop, which is pretty fast for a local vision model. I use moondream2 as my vision model, you can set your custom model like moondream3.1 if you have a good GPU (for comparison I have currently have an RTX 3050). It works cross-platform. Just follow the README. If you like my work, you leave me a tip as an act for supporting open source!!…
- 1MA
I've been working on training this small vision language model for the last month - excited to release the first prototype today! It is based on SigLIP (image encoder), Phi-1.5 (text model) and trained using the LLaVa-1.5 training dataset. It runs reasonably fast on CPU with ~8GB of RAM in full 32-bit precision. There's plenty of room to speed it up and reduce memory consumption by quantizing the model. I posted a video of it running on my M2 Macbook Air (on CPU not MPS, so performance should be comparable on other hardware) on Twitter to demonstrate inference speed:…
2023 · github.com
- 2
- 3
- 4
- 5
- 6
- 7
- 8AT
A 3.16M-parameter INT4 transformer running entirely in the on-chip memory of a Xilinx Kria KV260. Zero DRAM in the token loop, 59,965 tok/s on the fabric, bit-exact. Chat with it live.
27d ago · mikeayles.com
- 9DC
2020 · github.com
- 10
I built a specialized package of DeepSeek V4 Flash 0731 (originally 284B total parameters, 13B active), preserving reasoning, tool calling and coding capabilities: https://huggingface.co/steadfastgaze/DeepSeek-V4-Flash-0731-... I let it write a minimal C compiler targeting ARM64, then test the result with Fibonacci and FizzBuzz programs, and it succeeded in less than 1 hour, with the full recording at: https://youtu.be/XiwSilmV8B0 You can run it on Silicon Macs with my engine https://github.com/steadfastgaze/MoEspresso, while one of the…
21d ago · huggingface.co
- 11NF
2020 · github.com
- 12G4
When new Large Multimodal Models (LMMs) are released, there is excitement as we explore new capabilities. What can a model do? What can't a model do? What strange behaviors does the model exhibit? With that said, such analyses are frozen in time. At a hackathon toward the end of last year, the Roboflow team made a tool that runs the same set of tests with the GPT-4 with Vision API every day. This allows people to see how the model performs over time as updates are made. The last seven days of results are displayed on a web page; the rest of the data is archived in GitHub. We started the site…
2024 · gptcheckup.com
- 13IM
Hey guys, I made a VS Code extension, within which you can use the Mixtral 8x7B AI model for free. Mixtral 8x7B is a new AI model from the Mistral family, which outperforms GPT-3 in many benchmarks, a fact that I have personally confirmed in daily coding tasks, where Mistral 8x7B was the clear winner. You can use all the AI features, such as AI Lens with custom instructions and similar. I'm pretty sure some of features will be useful to you. I'd appreciate both, positive and negative feedback!
2023 · marketplace.visualstudio.com
- 14OS
Hi everyone! Here is an open source implementation of a decently performant server hosting zero-shot image models (CLIP for image classification, OWL-ViT-ST for object detection), with an extra algorithm to allow users to give the models feedback when they make mistakes! We built a company off this flavor of tech two years ago and have clients who are currently using our commercial API. We are now moving on to other projects but want to make sure our clients still have access to the approaches that they've grown to rely on, so we're open sourcing a simple implementation that they'll be able…
2024 · github.com
- 15
- 16IA
I'm giving away some Promo Codes here as well, just as a thank you to the HN community. Would love your feedback.
2012 · itunes.apple.com
- 17IC
Hi HN, I am Anubhav from RamanLabs. We have been developing end to end Computer-vision modules to make it easy for developers, hobbyists to integrate such functionality into their applications with minimal amount of code. All modules are developed to run real-time on consumer-grade CPUs[0]. For now we are releasing only Python-language SDK. Demos are provided to allow users to test performance on desired data-distribution. Framework powering these modules in completely written in Nim language, which under the hood wraps some Operation's implementation provided by libraries like…
2022 · ramanlabs.in
- 18AA
Hi guys, For a few months now I've been working on a web GUI to build, visualise, train and share deep neural models. It's currently reaching a state where opening it for Beta release make sense. Currently the tool support: - Fully connected and Convolutional architecture - Cloud and local, saving / loading of models - Edit / delete layers - Visualise Convolutional layers filters - Freeze / Unfreeze layers - More datasets: Fashion MNIST, QuickDraw(10 and 30) The editor can be found here: https://aifiddle.io. Your feedback, ideas, suggestions are greatly useful, so…
2019
- 19OE
2020 · picsellia.com
- 20IE
Hey HN, when building ML systems for industrial AI, we have learned that data inspection is critical during the ML development process. We are also big fans of the Hugging Face ecosystem. That is why we built an integration to our data exploration tool Spotlight that allows you to interactively explore Hugging Face datasets with one line of code. Spotlight lets you leverage model results such as predictions and embeddings to gain a deeper understanding in data segments and model failure modes. Currently, many many NLP, CV, Audio and multimodal datasets are supported both locally and on the…
2023 · huggingface.co
- 21RG
I wanted to know how fast a 26B mixture-of-experts model could run on a desktop CPU with no GPU. Got ~40 tok/s single-stream (lossless) and ~124 batched. The surprising part was the byte budget: for this model you compress the output head (32% of per-token bytes), not the experts (16%). The writeup has the bandwidth roofline and the dead-ends; the repo has the reproducible recipe. Happy to answer questions. Repo: https://github.com/arun-prasath2005/gemma4-cpu-moe
Jun 2026 · apeg.dev
- 22M
Dear HN, this is Alex, cofounder of Moonvision, an Austrian based computer vision company. We started in 2017 tracking grilled chicken at the Oktoberfest Munich [1] and transitioned into automating visual inspections tasks. Our web tools are used by quality assurance experts to manage training data and create custom models without an external workforce. For such tasks and experts, the effort to label data is often prohibitive. Therefore, we built tools that work with low amounts of initial data. To train a new pipeline we cover the following 6 steps: - Video gathering - Object mining -…
2019
- 23
- 24IO
About three months ago, ipplex, a technology startup I work with released a real-time Money Reader app for Blind users that has been recognized by major publications and blogs, and has a 5 star rating in the app store. You can see a quick in office demo of it here: http://www.youtube.com/watch?v=lvfDnGMPrkI I wasn't active on HN then, but I thought the community may enjoy seeing some very early real world applications of real time object recognition. We are working on bringing this to all kinds of objects as well as landmarks, and incorporating some really interesting things to make this…
2011
Ranked by how close each launch is in meaning, then by votes. Refine with a description →