Beeble AI has announced version 3.0 of its model SwitchLight, described as “the best Video-to-PBR model in the world”. The tool converts video footage into physically based rendering (PBR) passes suitable for VFX and relighting workflows.

Key improvements

According to Beeble’s official release, the model is now a true video model: it processes multiple frames simultaneously rather than treating each frame individually and applying a post-deflicker step. This approach is said to produce smoother, more stable temporal results in moving footage.

Beeble also claims that SwitchLight 3.0 has been trained on a dataset ten times larger than that of the previous version. The company states this broader dataset captures a wider range of lighting conditions, materials, and environments, yielding more realistic results.

The desktop application, Beeble Studio, now supports 4 K resolution input, 16-bit EXR output, and local GPU processing for video up to one hour in length. The cloud-based version has been upgraded to SwitchLight 3.0 as well, with no price increase for existing users.

The release further highlights improved preservation of fine surface detail, such as facial wrinkles, hair strands, and fabric texture. The update also claims to correct several artefacts present in earlier versions, including the green-tinted normals sometimes seen on top of subjects’ heads.

Workflow and platform details

Beeble confirms that all footage processed through its cloud application now uses the new model automatically, without additional user input. For the local version, Beeble Studio, the software downloads and activates the updated model upon launch. No changes to pricing or subscription structure are mentioned.

What is not yet clear or independently verified

Beeble’s claims of “the best Video-to-PBR model” and “unmatched quality” remain vendor statements; no third-party benchmarks or peer-reviewed tests have been published. Hardware specifications for the local GPU workflow, including minimum VRAM and platform compatibility beyond Windows, are not detailed in the announcement. However, as with any new AI-driven tool, studios should conduct thorough in-pipeline testing before adoption. Verification under real-world production conditions remains essential to ensure consistency and compatibility with existing workflows.

The post Beeble launches SwitchLight 3.0 first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

DP: Let’s kick things off with a bit of background: What actually set you and your crew on the path to AI relighting? 

Hoon Kim: Four other technologists and I founded Beeble as a selfie relighting app after seeing a gap in the market for AI-powered lighting tools. It received a great reception and went viral, but the real Eureka moment happened next. We found that VFX artists would hugely benefit from a similar tool that relights video instead of still imagery. We knew it would solve many time and budget issues, while enabling professionals to fix lighting in post, without having to reshoot. 

DP: With Switchlight 2.0 being released versus 1.0: What’s the “wow, that’s new!” factor? 

Hoon Kim: Switchlight 1.0 already had a huge level of detail in terms of PBR map generation, but this update brings it up a notch. It boosts the quality of our normal, basecolor, metallic, roughness, and specular passes, thanks to training on 13 times more data. We’ve now also extended these maps to background objects and environments, as well as the central video subject. 

DP: For anyone curious to jump in: How does the pricing and licensing for Switchlight 2.0 work?

Hoon Kim: All our pricing is credit-based, giving you a set amount of content to process each month. The Starter plan is free and allows you to run 15-second video passes, ideal for testing the software. For ongoing use, the Creator plan is $19/month and the Professional plan is $75/month, with discounted rates available on annual subscriptions. All pricing details are available on our site.

DP: If you think about Switchlight landing on the desk of a busy VFX artist or colorist: Where does it shine? 

Hoon Kim: Put simply, it delivers the level of quality a VFX artist would expect. Additionally, they receive AOV passes almost instantly, a significant shift from the traditional, manual CG rendering process, making it ideal for quick fixes.

DP: Deflickering temporal noise is a game-changer for a lot of us! Can you give us a peek into how your new approach works, especially for fast-paced or multi-source lighting?

Hoon Kim: SwitchLight 2.0 operates on an image-based model, utilising PBR maps that mitigate temporal noise deflickering. Our next update, SwitchLight 3.0, takes things further: a native video model that removes the need for special deflickering. More details coming soon!

DP: Speaking of standards: What’s your support like for things like ACES, Rec. 709, P3, and other pro color spaces? Are you outputting true 16-bit or 32-bit float EXRs, so no one’s losing data along the way?

Hoon Kim: Our AI is trained on the Rec. 709 colour space, which is the recommended format for best results. That said, you can still apply the generated PBR maps to your original ACES footage without losing any detail.

DP: What kind of shots or material have you seen Switchlight absolutely nail and where does it still sweat? 

Hoon Kim: SwitchLight 2.0 is built to handle footage from any camera, whatever the quality, lighting, or style. Of course, high-definition, steady shots with flat lighting will always give you the greatest control.

DP: When you’ve got those nightmare shots with crushed blacks, low-res and ancient TV rips: Do you have any hacks? 

Hoon Kim: For that kind of challenging footage, it helps to upscale before running it through Beeble, and then apply a separate deflicker pass on top of the generated PBR maps. Tools like Nuke Copycat make that step straightforward and can dramatically improve the result.

DP: Any “dos and don’ts” from what you’ve seen in the wild?

Hoon Kim: AI upscaling is definitely a “do”, it could massively improve poor-quality footage and makes it easier for SwitchLight to generate accurate PBR maps. But avoid heavy denoising, which strips away detail the AI needs, and hold off on strong LUTs or oversharpening until after relighting, as they can distort the data and lead to unstable results.

DP: Is there a “Switchlight for Dummies” checklist for prepping shots? 

Hoon Kim: We actually put together an article on this! However, my main advice is simple: aim for even, level lighting when shooting. Beeble can handle almost any condition, but flat lighting gives you the most flexibility and control later in post.

DP: Alright, time for a technical deep dive! How does Switchlight 2.0 whip up those depth maps? 

Hoon Kim: At its core, it’s a neural net doing the heavy lifting. That’s about as far as I can go! You can more information via these links: https://beeble.ai/research/switchlight-2-0-is-here or the paper on the technology: SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting

DP: Under the hood, what kind of AI are we talking about? 

Hoon Kim: We are always improving the network architecture, so “monster hybrid” would probably be the most accurate description. However, the beauty lies in integrating the Cook-Torrance BRDF model, which enables the AI to learn how light bounces off a subject. Paired with physically based rendering, the system can generate a relit scene that looks physically convincing.

DP: The classic pain point: specularity. How does Switchlight tease out reflections and highlights? 

Hoon Kim: We’ve made specular maps flexible enough that you can dial them in however you like. Want more gloss, less sweat? Just tweak the strength directly in-platform, or plug the maps into a third-party shader like Blender or Unreal Engine for full control. You can even isolate high- or low-specularity regions, so you decide exactly how shiny or matte things should look.

DP: What about your reference data? 

Hoon Kim: All of our training data is created in-house using scans of real humans and objects. We train only on safe, clean, and fully licensed datasets, ensuring professionals can use our service with complete peace of mind. We do not use movies, films, or any third-party content that could raise copyright concerns..

DP: Platform time! So you’re solid on Windows, Red Hat, Ubuntu. Any dreams of a Mac version for the “Final Cut Victims”? 

Hoon Kim: Right now, SwitchLight 2.0 and the Beeble platform are web-based. With 3.0, we plan to introduce a local version, one that better aligns with the security and workflow standards of major post-production studios.

DP: For anyone building a new Switchlight workstation: What’s the minimum gear to get real-time, and what’s your dream setup? 

Hoon Kim: We’ve designed Beeble to be accessible to anyone, whether you’re a content creator on a laptop with phone footage or a studio running complex plates. At the entry level, all you really need is a laptop and some footage to upload; the platform handles the heavy lifting and generates the VFX passes for you. Bigger studios will naturally push higher-res material through, but it’s not a requirement. And for anyone wanting to get started right away, we’ve just released Beeble Camera: a free app that brings camera tracking to Beeble.

DP: Looking into the crystal ball: Where do you see Switchlight and AI relighting going, say, five or ten versions from now?

Hoon Kim: Looking ahead, our goal is to keep pushing the detail and fidelity of the PBR maps while advancing motion capture, camera tracking, and depth generation. Ultimately, we want to break footage down into its most detailed components so every frame can be reconstructed, relit, and reimagined with complete creative freedom.

DP: For the tech-heads and code nerds: Are there research papers or blog posts you’d absolutely recommend to get your head around the science powering Switchlight? 

Hoon Kim: Absolutely. Our paper is here for anyone to read. It provides a detailed overview of the methods behind SwitchLight, from self-supervised training to the physics-based models that underpin our approach. 

DP: What’s the most fun or jaw-dropping thing you’ve seen Switchlight do that made you stop and say: “Okay, that’s actually impossible—except now it isn’t”?

Hoon Kim: A standout for me was a father-and-son duo who made a fan film called Star Wars: Entrenched, with Beeble helping along the way. Navaz Dowling, who runs Bad Beetle Entertainment, taught his son the basics of VFX and brought in friends for costume design and relighting. The trailer’s already out, and the post-production community has responded really positively.

At the same time, we’re seeing larger post-production studios integrate Beeble into their pipelines. The work Boxel Studio did on Superman & Lois is a great example of this. With SwitchLight 3.0 introducing a local version, that side of adoption is only going to grow.

The post We have to talk about Switchlight 2.0 first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

Beeble’s SwitchLight 2.0 marks the company’s push to put AI-powered relighting into the hands of actual postproduction artists—and not just demo video influencers. The new release introduces physically based rendering (PBR) relighting, portrait and universal HDRI extraction, AI-based deflicker, a neural detail enhancer, and local processing for the security-conscious (or just the deeply skeptical). All these features target one goal: letting post artists relight filmed footage with actual, production-grade material and lighting data, without needing a full 3D scan or reshoot.

From Green Screen to Full PBR Passes—What’s New in 2.0?

SwitchLight 2.0 can generate a complete suite of PBR passes from video footage—including normals, depth, albedo, roughness, specular, and ambient occlusion. These can be exported as layered EXRs or video, suitable for use in Blender, Unreal Engine, or compositing apps like Nuke and After Effects. The updated system also brings improved halo handling, temporal stability, and smart anti-ghosting—so even when the footage is a bit rough, Beeplle claims to keep edges tight and details intact.

HDRI Extraction for Real-World Lighting

A major new feature is dual HDRI extraction. “Portrait HDRI” mode analyzes the lighting on a subject’s face, then generates an HDRI map of the environment—useful for relighting close-ups or matching CG light to live-action. “Universal HDRI” uses Beeble’s DiffusionLight technology to estimate lighting for entire scenes, not just heads. Both methods aim to shortcut the process of shooting reference balls or fiddling with 360-degree cameras (switchlight-studio.beeble.ai).

Neural Enhancers and Deflicker—But No Magic

Beeble incorporates AI-based deflicker to tame temporal noise, and a neural enhancer that tries to restore details like subsurface scattering and self-occlusion lost to compression or lighting limitations. That sounds like a marketing claim, but the neural enhancer’s job is to create passes that don’t look like synthetic plastic when relit. In practice, expect results to vary based on source quality. Still, these tools are designed to reduce the time artists spend cleaning up messy mattes and reconstructing details by hand.

The Workflow: From Upload to Export

The workflow starts in the Beeble Studio web app or desktop version: upload video (green screen or not), and the AI gets to work—extracting backgrounds, creating PBR passes, and providing a real-time interface for relighting. Within the Studio, users can swap HDRIs (from the built-in library or custom sources), add point lights, and preview the results with instant feedback.

Need a background? Text prompts can generate new AI backdrops on the fly, with the usual caveats of GenAi. When finished, export your full composite or individual passes in 4K+ for Blender, Unreal, Nuke, or straight to edit. A dedicated loader plugin lets Blender and Unreal Engine users import PBR assets with a click, skipping the usual roundtrip of manual pass matching.

Deployment: Web, Desktop, CLI—And Air-Gapped

Beeble offers both web and desktop versions. Local processing is the default; no uploads to the cloud unless you want them. Air-gapped studios get RLM licensing and command-line (CLI) batch processing on Windows or Linux—making it possible to integrate into automated pipelines or run batch jobs on render farms without an internet connection (switchlight-studio.beeble.ai).

Who Should Use SwitchLight 2.0?

SwitchLight is not for Instagram filter enthusiasts. Its core audience: VFX compositors, lighting artists, colorists, look-development supervisors, indie filmmakers, and virtual production teams who need to relight live-action or green-screen plates with credible, production-ready PBR data. It’s also a fit for small shops and individuals who want the flexibility of PBR relighting without a massive pipeline investment or multi-camera setup. In practical terms, anyone who wants to blend real and CG elements (or relight plates to match different CG environments) without access to a full 3D scan should consider trying it.

Caveats: No AI Is Infallible

AI’s strengths—speed and automation—don’t make SwitchLight immune to artifacts, lighting mismatches, or temporal hiccups. The more you push the relighting or try to extract passes from low-quality or compressed sources, the more likely you are to see oddities. Beeble CEO Hoon Kim specifically urges professionals to validate AI-generated passes and composites in their own postproduction pipelines before trusting the results for final delivery (vp-land.com). That’s not just sensible—it’s necessary for any artist who wants to keep their QC department onside.

Reminder:
Innovative relighting and AI pass generation tools like SwitchLight 2.0 are best tested thoroughly in your own pipeline before any real-world delivery. No exceptions.

beeble.ai

The post Beeble: AI relighting steps up to validate in your pipeline first appeared on DIGITAL PRODUCTION and was written by Bela Beier.