Offline sketch to image geneartor in a whiteboard
I'm excited to share my indie product, https://drawing.pics In this post, I'll share all the technical details behind it. So, what exactly is DrawingPics? It's an image-to-image and sketch-to-image generator that runs in a whiteboard, allowing you to draw your draft directly on the canvas and easily generate the desired image. How does it work from a technical perspective? TLDR: Miniconda + Diffusers + Electron + Excalidraw One of the most important aspects of creating this tool was finding a stable diffusion locally inference solution. There are many solutions available, such as…
In plain words
DrawingPics is a sketch-to-image generator that runs locally in a whiteboard interface. Users draw their drafts directly on a canvas, and the tool generates images based on those sketches using offline image generation. Built with Electron and Excalidraw, it processes requests locally without requiring cloud services. The tool is designed for anyone who wants to quickly transform hand-drawn sketches into finished images while maintaining privacy and control over their work.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I'm excited to share my indie product, https://drawing.pics In this post, I'll share all the technical details behind it. So, what exactly is DrawingPics? It's an image-to-image and sketch-to-image generator that runs in a whiteboard, allowing you to draw your draft directly on the canvas and easily generate the desired image. How does it work from a technical perspective? TLDR: Miniconda + Diffusers + Electron + Excalidraw One of the most important aspects of creating this tool was finding a stable diffusion locally inference solution. There are many solutions available, such as https://github.com/leejet/stable-diffusion.cpp and https://github.com/apple/ml-stable-diffusion. I tested the C++ version, but the inference speed was very slow, and Metal GPU support still had issues (you can find relevant issues in their repo). Ultimately, I decided to use python to run it because PyTorch is mature and MPS support is well-established. And I chose Miniconda, because it can create a small, isolated Python environment to run the program. The AI model should run in the background so that we can continuously produce images while you draw. We need to find an RPC method to enable communication between the Python process and Electron's Node.js process. The easiest way is to run a Python HTTP server, but the memory usage is too high. We need a more lightweight solution, so I used xmlrpc for memory efficiency, although there might be better alternatives that I'm unaware of. The AI inference part is handled by diffusers, which is great, but I had to apply some custom patches to make it work in this situation. This can be a bit challenging if you're not familiar with Python. For the frontend, I initially used a low-level canvas library and tried to implement a drawing pad from scratch. However, it had too many details, so I chose a more mature option: Excalidraw. It's fantastic, with the only shortcoming being limited API support. Finally, I combined all these technologies in Electron, ensuring they work smoothly on both the main process and the renderer process. Ok, Is DrawingPics free to use? 80% of the project is free to use. I only charge a lifetime license for the effort I've put in, as I've spent 4 months on it and made numerous improvements based on user feedback. Currently, only Mac is supported. Windows support will be added later.
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
