Orion 2 creates a realistic virtual try-on in a single turn!

Given an image of a dress and a model, it detects the person and garment in parallel, crops each, generates the composite, and asks a vision-LLM whether the fit looks natural. Four distinct visual operations composed as a single program, with every intermediate artifact inspectable.

Orion 2 supports image processing via OpenCV!

This quick walkthrough demonstrates several processing examples, including combining object detection with Canny edge detection.

We're headed to @Databricks Data + AI Summit 2026 in San Francisco!

Excited to connect with builders, researchers, and teams pushing the boundaries of agentic intelligence. If you're building frontier agents with multi-modal, unstructured data, check out @vlmrun's new visual agent Orion 2 that we launched last week.

If you're around Moscone Center June 15–18, drop a comment below and let's grab a coffee!

#DataAISummit #DAIS2026 #Databricks #AI #VisionLanguageModels #SanFrancisco

Our new visual agent Orion 2 can perform segmentation to 3D reconstruction in one chat thread!

See our robotics demo chat link in the comments 👇

The AI agent skills conversation focuses mainly on text. But for many tasks, words fall short. We need visual skills: providing images and videos as context, not just text.

It's one thing to describe to a robot how to fold a t-shirt. It's another to show it a video.

At VLM Run, that's what we're building: visual agents that understand visual data and act on it.

What if visual AI agents could help give feedback on exercise?

@jeremyparkphd recently reviewed Orion visual AI agent for providing deadlift feedback. He raises the question: what if visual intelligence could be made accessible for applications in exercise, all through a chat interface?

Read the Substack blog here: https://jeremyparkphd.substack.com/p/visual-agents-for-fitness-how-orion