For those who don’t know the tool: D5 Render from Dimension 5 is a realtime rendering engine used across architecture, design, and visualisation pipelines. It connects with 3ds Max, Blender, Cinema 4D, Revit, Rhino, SketchUp, ArchiCAD, and Vectorworks via direct sync plugins.

Oceans, clouds, and skies

Version 3.0 introduces two major environment tools: an Ocean object for animated water surfaces and a Volumetric Clouds system with multiple presets such as cumulus and cirrus. The ocean object allows control of wave scale, wind speed, and interaction near shorelines.

Volumetric clouds integrate with improved fog and light scattering options for more natural outdoor illumination. Enhancements to the existing Geo Sky model provide finer control over sky intensity and sun balance, improving consistency between time-of-day setups.

Rendering and material control

A new True Displacement option replaces parallax mapping with physically accurate surface relief. The trade-off is a higher render cost, but it yields more convincing depth in materials such as stone or concrete. Additional material updates include CMYK texture support and a toggle for HDRI resolution, allowing lighter scene loads when full 16K environment maps are unnecessary. Users can now also set a custom viewport background colour, aiding previs or presentation renders that do not require a full environment.

AI generation expands inside D5

Dimension 5 continues its exploration of integrated AI tools. The new Image-to-3D feature creates simple 3D models from one to three reference photos, processed directly inside D5. In the AI Agent suite, Scene Match allows textual adjustment of scene elements, while Asset Recommendation searches the asset library based on descriptive keywords or reference images. At press time, these AI tools remain early implementations, and output quality varies depending on subject complexity.

Experiments with Gaussian splats

D5 Render 3.0 introduces experimental import of Gaussian splats, a point-based 3D representation format derived from neural rendering research. The implementation is explicitly labelled experimental, and Dimension 5 advises users to expect incomplete material or lighting behaviour.

Workflow refinements and licensing

Navigation within scenes has been overhauled with a free-camera mode and refined controls. Several features previously restricted to Teams subscribers, such as Caesium geographic data and XR Tours, are now available in the Pro tier. The procedural city generator is also promoted from Teams to Pro.

D5 Render continues to be offered in three tiers: a Community edition that remains free, plus paid Pro and Teams subscriptions.

D5 Lite: a lightweight sibling

Alongside the main update, Dimension 5 announced D5 Lite, a compact edition designed for early-stage design work, initially integrated with SketchUp. D5 Lite runs in two modes: Real-Time Rendering for viewport previews and AI Generation for cloud-based image synthesis from screenshots. Future versions of D5 Lite are planned for 3ds Max, Revit, and Rhino, though no release schedule has been released.

Compatibility and system support

D5 Render 3.0 supports Windows 10 and later. The recommended GPU baseline is an NVIDIA GeForce GTX 1060, AMD Radeon RX 6400 XT, or Intel Arc A3 series. Integration plugins remain available for all major DCC and CAD tools. As with any major rendering update, users are advised to test D5 Render 3.0 and its AI features on non-critical projects before integrating them into live production.

The post Ocean, clouds, and splats: D5 Render 3.0 sets sail first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

Beeble has released Beeble Camera, a free iOS app that uses Apple’s LiDAR and ARKit frameworks to track iPhone movement in real time while recording. The app anchors captured footage to real-world space and uploads it directly to the Beeble Web platform for AI processing. According to the developer, uploaded shots are processed into camera-tracked, rotoscoped and relightable VFX passes. These passes can then be composited in Beeble Studio, the online Beeble Editor, or exported into Blender and Unreal or using a dedicated plugin, or any other DCC through a straight export.

Setup and Shooting

After installing Beeble Camera from the App Store, users must scan their environment with the iPhone to allow ARKit to detect surfaces. A floor grid can be tapped to set the origin point for tracking. The app also allows insertion of reference geometry by placing a .usdz file into the scene. This can be scaled, rotated and moved as needed. Once the environment is prepared, recordings capture both video and camera metadata. For improved results, Beeble recommends using a gimbal, ensuring a clean lens (D’uh), and shooting under even lighting conditions.

Uploading and Processing

Recorded clips are uploaded from the phone to Beeble Web, where AI routines create roto masks and relightable passes. These are automatically aligned with tracked 3D data from the shoot. The same 3D reference model used on-set can be converted to .glb and imported into the Beeble Editor, where metadata ensures accurate placement in the composite. Alternatively, Blender users can bring in the footage via the Beeble add-on, which carries over the camera-tracking data.

Availability

Beeble Camera is available now as a free download on the iOS App Store. Processing and compositing features require a Beeble Web account.

What’s Next from Beeble

Beeble CEO Hoon Kim has confirmed plans for a local version of the platform in future updates. He discusses this roadmap and accessibility of AI-based relighting in our Digital Production interview, so read on over there :)

We have to talk about Switchlight 2.0

The post iPhone for Tracking: Beeble Camera enables Free “Virtual Production” first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

Masterpiece X has launched WorldEngen, a desktop AI scene editor that promises to compress weeks of 3D scene building into a handful of hours. According to the company, the software can cut the average scene creation time from around 148 hours to just 3, a claimed 50x acceleration.

WorldEngen is positioned as the “first AI assistant for 3D worldbuilding.” Instead of scattering asset generation across multiple disconnected tools, it acts as a central hub for AI models and assistants, tied directly into established workflows in Blender, Unreal Engine, and Unity.

Why WorldEngen exists

Masterpiece X frames its tool as a response to what many studios already experience: too many disconnected AI experiments and plugins, scattered across multiple browser tabs and applications. The company describes a “digital desktop littered with half-finished assets” and “creative vision lost in the chaos of disconnected tech demos.”

The problem is not the lack of AI models: there are plenty generating characters, props, textures, and concept art. The issue, according to Masterpiece X, is the absence of a unified, production-ready environment where AI assets can be directed, combined, and finalised into a coherent 3D scene.

Features on paper

WorldEngen introduces the concept of specialised AI “agents” that can be directed like team members. The workflow begins with layout and scene agents generating a greybox: a rough environment built from primitives that defines scale, composition, and spatial relationships.

From there, concept art agents help establish a consistent visual direction through a Style Guide, ensuring assets share the same look and feel. Once approved, an Image Kit Agent extracts objects from concept art and prepares them for 3D generation. Other agents refine, restyle, or edit images. Finally, a Scene Agent exports assets and layouts directly into Blender or Unreal Engine for further work.

A notable inclusion is the AI Video Agent, which can automatically render pre-vis clips based on the scene. This function is aimed at pitches, internal reviews, and fundraising decks.

Technical architecture

WorldEngen runs as a desktop editor, but its AI computations are performed in the cloud. The company stresses that users keep their files local, which avoids the need for high-end GPUs on the client side. This architecture could make it accessible to smaller studios or freelance artists, though it does raise questions about bandwidth requirements, file handling, and long-term reliability.

Real-time iteration is another selling point. Masterpiece X claims that layouts and asset updates can be adjusted instantly without repeated exporting or rebuilding. If this proves true in practice, it could cut down on one of the more frustrating bottlenecks in scene assembly.

Availability and access

WorldEngen is currently available only via Early Access, open to select studios and production teams. Interested professionals must apply through the official site. No general release date or pricing information is yet available.

The sceptical view

At present, all reported speed gains and cost savings come directly from Masterpiece X or its quoted design partners. No independent benchmarks or third-party tests have been published. Claims of compressing 148 hours of work into three remain unverified. As such, actual performance in production conditions is unknown.

Another open question is stylistic consistency. While WorldEngen introduces style guides and workflow control, the common criticism of AI models generating inconsistent or unusable results has not been conclusively addressed. Until production artists test it at scale, the reliability of its outputs remains uncertain.

Context in the industry

WorldEngen enters an increasingly crowded space of AI tools promising to “revolutionise” 3D workflows. Artists are already experimenting with pipelines that combine Midjourney, Stable Diffusion, Runway, and various asset-generation APIs. What Masterpiece X offers is consolidation: a single editor designed to unify these processes, with direct export into DCCs, which is easier to use than ComfyUI.

This makes the tool potentially appealing for studios exhausted by scattered pipelines. But as always, consolidation comes with trade-offs: lock-in to one ecosystem, reliance on proprietary AI agents, and dependence on cloud connectivity.

Test before you trust

Studios considering Early Access should evaluate WorldEngen with controlled pilot projects before integrating it into production-critical workflows. As with all new AI-driven tools, actual usability and reliability will only be clear once artists put it through the rigours of real-world deadlines.

Masterpiece X WorldEngen

The post WorldEngen promises AI-built 3D scenes in hours, not weeks first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

Autodesk has overhauled its Flow Studio subscription model, adding new tiers, lowering prices, and making notable feature changes. The browser-based, cloud-rendered platform, formerly known as Wonder Studio, is aimed at AI-assisted character replacement and animation.

The update introduces five subscription options:
Free: $0/month
Lite: $10/month
Standard: $45/month
Pro: $95/month
Enterprise: contact sales

Free means watermarks

The Free tier now allows 720p exports, 300 credits/month, 1 GB of storage, up to 100 MB uploads, three custom character uploads/month, and tracking for a single actor per project. Output is watermarked, making it suitable for testing or non-commercial uses.

Lite gets cheaper—and leaner

The Lite tier drops from roughly $20/month to $10/month. Credits fall to 2,100/month, maximum resolution is 1080p, storage is 5 GB, uploads are capped at 500 MB, custom character uploads are limited to six, and tracking is capped at two actors per project. Autodesk has removed Lite’s ability to export character passes, PNG image sequences, and USD scene files. Wonder Tools, used for tasks like camera tracking and clean-plate generation, are also no longer included.

Standard as the middle ground

The Standard tier costs $45/month, includes 6,000 credits/month, supports 4K exports, offers 20 GB of storage, a 500 MB upload limit, up to 15 custom character uploads, and tracking for three actors per project. It also omits character pass and PNG exports, and USD export capability is absent.

Pro drops into double digits

The Pro tier is now $95/month (down from $99.99), with 12,000 credits/month, 4K export, 80 GB storage, 2 GB upload limit, up to 50 custom characters, and four-actor tracking. All export formats and Wonder Tools are included. Pro is also now bundled in Autodesk’s Media & Entertainment Collection, alongside Maya, 3ds Max, Arnold, Golaem, Mudbox, MotionBuilder, ReCap Pro, and more.

Enterprise for scale

The Enterprise tier offers 48,000 credits/month, 4K export, 1 TB storage, 2 GB uploads, up to 50 custom characters, and tracking for up to seven actors. Pricing is available only via Autodesk sales.

Platform and pipeline notes

Flow Studio runs in Chrome or Safari; mobile browsers are not supported. All processing is cloud-based, using a credit system tied to project complexity and output settings. Export restrictions in Lite and Standard may affect USD-based or multi-pass compositing workflows. As always, studios should test any new subscription tier in a controlled environment before integrating it into production.

The post Flow Studio prices drop, tiers multiply, features shift first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

In a move that might make brand strategists giddy, Autodesk has rebranded Wonder Studio, the AI-infused platform for seamlessly inserting CG characters into video footage, as Autodesk Flow Studio. This rebranding officially integrates the service into Autodesk’s Flow cloud platform for media and entertainment. Despite the new moniker, users can rest easy knowing that the platform’s availability and pricing remain unchanged.

AI-Powered CG Integration

Launched in 2023 and acquired by Autodesk in 2024, Wonder Studio—now Autodesk Flow Studio—leverages artificial intelligence to automate the integration of CG characters into live-action footage. The platform tracks live actors, replaces them with CG counterparts, and matches lighting conditions, producing clean plates, alpha masks, camera tracks, and motion-capture data. For those who like their data portable, the platform supports exports to Blender, Maya, Unreal Engine, or in USD format for applications like 3ds Max, Houdini, or Unity.

Introducing ‘Wonder Tools’

In February 2025, the platform received an update introducing standalone services dubbed ‘Wonder Tools.’ These tools allow users to extract clean plates—backgrounds without actors—and obtain camera tracking data from footage. Notably, the Camera Track Wonder Tool can process footage sans actors, while the Clean Plate Wonder Tool is designed to remove human actors (up to four per shot) but doesn’t extend its vanishing act to animals or inanimate objects.

Pricing and Accessibility

Autodesk Flow Studio operates as a browser-based platform compatible with Chrome or Safari—sorry, mobile users, you’ll need to switch to a desktop. The platform offers two subscription tiers:

• Lite: Priced at $29.99/month or $299.88/year, this tier allows 1080p video exports and access to mocap data, clean plates, camera tracks, and 3D scenes.
• Pro: At $149.99/month or $1,499.88/year, subscribers can export at 4K resolution and receive additional features like roto masks.

Both plans operate on a credit system, with one second of video processing consuming 20 credits. Lite subscribers receive 3,000 credits/month, while Pro users enjoy 12,000 credits/month. citeturn0search0

As with any new tool, it’s advisable to evaluate Autodesk Flow Studio’s features in the context of your project’s specific requirements before full integration.

For a visual overview of the rebranding and new features, check out the video below:

The post Wonder Studio Rebrands: Now Flowing with Autodesk first appeared on DIGITAL PRODUCTION and was written by Bela Beier.