Sim-Plates founder Alex Pearce has unveiled Sim-Plates.ai, an in-development AI plate-generation app that pairs the studio's existing CG driving-plate library with a guided five-step workflow for creating photoreal background plates for virtual production and VFX. Pearce shared the early look in a LinkedIn post describing the tool as still internal and gauging interest in a public release.
The hook: Sim-Plates is a CG-plate vendor moving into AI generation while keeping its own pre-rendered plates as the structural anchor. Composition, camera motion, perspective, geometry, and driving direction stay locked. Lighting, weather, atmosphere, texture, and "overall cinematic quality" become the variables.
The framing: Pearce positions Sim-Plates.ai as a companion to existing CG and live-captured plates, not a replacement. We previously covered how Sim-Plates supplies custom CG-rendered environments for car process shots on LED volumes, which is the workflow this new tool is meant to augment.
A guided five-workspace pipeline replaces the blank prompt box and the ComfyUI node graph
Pearce frames the design choice directly in the post: artists shape plates "using environment choices, source videos, style references, and AI generation controls instead of relying only on a blank prompt box or node spaghetti in the case of Comfyui." The interface is split into five sequential workspaces:
Environment picks the base location and auto-customizes the prompt plus animation references.
Settings sets camera animation type, speed, time of day, weather, and time period, all of which feed downstream prompts.
Style auto-generates a style prompt from the prior selections; users can import their own style image or pick a built-in one, with a reference image or video loaded by default.
Generate produces the video plate and auto-recommends a video model based on the inputs, though the user can swap to any supported model and edit the auto-generated prompt.
AI Upscale is the final pass, with multiple upscalers available and a recommended one preloaded.
Each step inherits choices from the previous one, so a "1950s London, overcast, dolly move" selection in the early workspaces propagates into the style prompt and model recommendation rather than asking the artist to retype it.
The production problem is shoot-day plate failures, not eliminating CG or live capture
The pitch is shaped around a specific pain point Pearce has hit on set. "What if the plate doesn't exist? You need London in the 1950s or New York in 2032," he writes. "We can create these with CG, but most productions don't have the time or budget for us to do it properly, and shooting practically? Forget it." He adds a second use case: when a production needs a specific plate on shoot day and "for whatever reason they don't have it," citing an instance where the internet was too slow to download a plate from the vendor and another where the vendor sent the wrong file.
Driving plates remain one of the more workflow-sensitive elements in virtual production. Our iPhone car-chase experiment walked through the practical pain points of capturing and sequencing driving footage, and the same sensitivities carry over once those plates land on an LED volume.
Sim-Plates' own seamless 12K-24K looping plates showed up in our NAB virtual projection preview as a category of asset that LED-volume operators are actively buying. Sim-Plates.ai targets the gap in between: when neither the prerendered library nor a live shoot covers what the production actually needs.
Pearce is explicit that the goal is augmentation. "The larger goal is not to replace CG Plates (Sim-Plates) or even live-captured plates," he writes. The AI generation step inherits the camera move and driving direction from a Sim-Plates source plate, then layers atmosphere and era on top.
Access is gated to expression-of-interest, with no public release date
Sim-Plates.ai is not publicly available. Pearce describes the tool as having been built "in stealth mode" as an internal tool for the company's own Gen-AI production work, with a stated future state where "anyone to generate their own plates, using our extensive library and procedural toolset under the hood." For now, the LinkedIn post functions as an interest-gauge: "Sim-Plates.ai began as a tool for our own workflow. We're now exploring whether it should become something more, let me know if you're interested in exploring this when we make it public!"
