Kinjal Das
Kinjal Das is Head of Visual Intelligence at Vinc. She writes the blog's Research posts on AI in film and VFX.
Articles

Alpha Gen Chooses the Subject for You. How to Test That Before a Shot Depends on It
A zero-prompt matte model is only as useful as its choice of subject. This article goes through what Lightricks has published about LTX Alpha Gen, shows what happened when we ran it through our own matting benchmark, and sets out a short protocol for testing it on your own plates before you schedule work around it.

Teaching a Video Model Camera, Not Content: How We Built a Cinematic Training Set
If a video model's training data doesn't separate camera movement from content, it can render the scene and ignore the shot. This article describes the dataset we built around camera movement, with its numbers, and says plainly what it has not yet been measured on.

What an AI Shot Really Costs, and Why Credits Are the Wrong Unit
Price AI film work by the cost of a shot the client accepts, not by the credits it takes to render one. This article puts three public figures from November 2026 side by side and shows that each one points the same way: generation is a small, visible line item, and judgement, revision and review are where the money goes.

Time to Finished Shot, Not Time to First Image: Measuring Gen AI at Shot 200
A shot that's quick to generate can still be slow to finish. This article draws on two November 2026 production accounts, CJ 4DPLEX's ScreenX case study and BOT VFX's work on Young Washington, and proposes four measures that tell you more about a schedule than time to first image does.

What Makes a Gen AI Tool Comp-Ready? A Checklist from Three Production Tools
A gen AI tool is ready for comp when its output lands back in the script with alpha, frame range and colour intact, and when the artist holding the notes can still adjust it late in the schedule. This article draws a checklist from three tools that shipped or were described in November 2026.

What a Studio Means by "AI Strategy" in 2026: Provenance, Hosting and Pipeline Fit
The studio gate on gen AI has moved from "ban or allow" to "show us your strategy". In practice, a strategy means you can say how each model was trained, where it runs, and how an artist stays in control on a long-form shot.

Measured 3D on Set: What On-Camera LiDAR and Native Splats Change for ML in Comp
Much of the ML that comp artists get excited about, such as depth estimation, relighting and matte extraction, is guessing 3D from 2D. Two November 2026 releases record or hold real 3D instead: Leica's MANTIS rig and Blender 5.3's native Gaussian splats.