An AI-first visual editor using GPT-4o's GPT-image-1 model
Hey HN! We’ve been experimenting with integrating multimodal models directly into creative workflows, and ended up building an AI-first image editor using OpenAI’s new `gpt-image-1` (from GPT-4o) inside our SDK. Instead of prompting in ChatGPT and pasting outputs into a design tool, this lets you generate, edit, and remix images all in one canvas. This allows for really interesting new workflows, like quickly mixing multiple images, or creating visual prompts by using annotations and reference on the canvas. Some key details: - Built with our plugin system in CE.SDK (CreativeEditor SDK) -…
In plain words
An AI-first visual editor that integrates OpenAI's GPT-4o image model directly into a creative canvas. Users can generate, edit, and remix images in one workspace rather than switching between ChatGPT and design tools. Built on the CE.SDK plugin system, it supports any multimodal model API and allows users to bring their own keys. The editor enables workflows like mixing multiple images and creating visual prompts through canvas annotations and references.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN! We’ve been experimenting with integrating multimodal models directly into creative workflows, and ended up building an AI-first image editor using OpenAI’s new `gpt-image-1` (from GPT-4o) inside our SDK. Instead of prompting in ChatGPT and pasting outputs into a design tool, this lets you generate, edit, and remix images all in one canvas. This allows for really interesting new workflows, like quickly mixing multiple images, or creating visual prompts by using annotations and reference on the canvas. Some key details: - Built with our plugin system in CE.SDK (CreativeEditor SDK) - Works with any multi modal model/API, not just OpenAI - You can bring your own API key, or extend it however you like - Focused on real-world workflows, not just concept generation We put together a live demo and wrote a bit more on why we built it. Would love feedback or to hear how others are thinking about AI in creative tools. If you have questions or ideas, let us know!
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 · 26d ago · cactuscompute.com
Launched alongside, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
