Pinned
Photon 1.3 is out!
It's now free and runs Moondream up to 70% faster. More images/sec, lower latency, on Mac, Windows & NVIDIA.
Good, fast, cheap: we picked all three!
moondream
230 posts
moondream
@moondreamai
Production vision AI that runs everywhere. Open models, fine-tuning, cloud, and fast inference for real-world deployment.
- Time to touch grass and use Moondream. Segmenting a dog is easy. But understanding which dog you mean is a different problem. Moondream does it from a prompt.
00:00 - moondream reposted
recently had the pleasure of presenting at the Frontier Research Club, hosted by @Stanford. Check out the recording for the TLDR on how we achieved SOTA segmentation
- Want to build an agent that can identify the lead swimmer in an Enhanced Games race clip? Existing models don't handle this well. A quick Moondream fine-tune solved it, segmenting the lead swimmer throughout the video.
00:00 - "Succulent chinese meal" isn't an object category. Yet Moondream knows exactly what you mean. Prompt: "croissant", "succulent chinese meal", "pizza", "beer", "check" Pixel-accurate grounding from naturel language. Fast, open vision AI.
00:00 - moondream reposted
00:00 - Replying to @moondreamaiBottom line: Photon 1.2.0 makes Moondream faster, easier to deploy, and available on more of the hardware you use. Production vision AI is moving from “cloud-only” to “run it where the work happens.”
- Replying to @moondreamaiJetson Thor support brings Moondream to robotics, inspection, kiosks, vehicles, cameras, and embedded vision products. Local VLM inference at the edge. More inference timings:
- Replying to @moondreamaiOn NVIDIA B200 (server), Photon reaches flagship performance numbers: ~23ms single-request latency for Moondream 2 ~30ms for Moondream 3 Visual reasoning at 30fps+ speeds.
