For the Reality Composer Pro Assistant that generates 3D objects and materials: what's the commercial-use and licensing status of generated assets in shipped apps, and what data underpins the model? Alternatively, am I able to upload an original image and use that for 3D generation?

Good Morning! Following the RCP 3 lightmap workflow: I've added Lightmap components to my entities and hit Bake, but I get "Lightmap bake failed: no lightmappable entities found — enable Process for Lightmaps in an asset's Geometry Transform Settings." I can't locate that flag anywhere in the GUI, and my scene objects are prototype instances. Could you walk through the complete end-to-end setup for baking lighting: where the Process for Lightmaps flag actually lives (on the instance or the source asset?), whether lightmap UVs must be authored or are auto-generated, and how the Lightmap component relates to that eligibility flag?

Can the new cloth sim be driven on a skinned character mesh — a cape pinned to the shoulders following skeletal animation — and does it run at interactive rates on visionOS, or is it aimed at non-real-time/hero content? Can a sim be cached/baked for deterministic playback?

The new GaussianSplatComponent: what's the supported ingestion path — standard .ply splats, .spz, or a conversion step inside RCP? And can a splat coexist in a scene with mesh geometry and depth-sort/occlude correctly against it, or are splats a separate pass with no depth interaction with meshes?

Hello from WWDC26! After installing visionOS27, USDZ models that viewed properly now exhibit strange anomalies, especially around UV seams. See attached image. Thx!

For Vision Pro's tiled GPU, how does MeshInstancesComponent compare to manually merging meshes for draw-call reduction? Does it collapse draw calls similarly while still allowing per-instance transform and material variation? Deciding whether to re-architect a heavy interior scene around it instead of hand-merging in Maya.

RCP 3's Animation Graph covers state machines and blending of imported clips. As an animator, is there now any in-editor support for authoring or editing animation curves and keyframes directly — a graph editor or dope sheet — or must all keyframe animation still be authored in a DCC (Maya/Blender) and imported as clips?

RCP 3 adds a lot of artist-facing surface: lightmaps, Animation Graph, Script Graph. Are step-by-step, artist-oriented tutorials planned beyond the API reference docs? A guided onboarding path would help 3D artists adopt these features much faster.

On visionOS the user's viewpoint isn't directly movable, so we currently invert world movement to simulate locomotion — translating the scene root rather than the camera. With RCP 3 / RealityKit this year, is there a supported way to define or animate a starting viewpoint — a "player start" transform — for an immersive scene, or is world-relative transform still the only sanctioned approach?

When I iterate geometry in Maya/Blender after assigning components, prototype overrides, and lightmaps in RCP 3, does re-importing the updated USD preserve those bindings, or do they need reauthoring on each import? What's the recommended round-trip for art that's still changing?

I guess this is not an actual video Group Lab. sigh Would love to see a dedicated Reality Composer Pro 3 session - even for those of use actual Vision Pro devs that didn't get the lucky golden ticket to the Apple Park event. You need to make these interactions available to us in person during WWDC week. That all being said... How do I go about baking lighting in RCP3? I cannot find anything in the documentation. Thanks!

Hello! Back from last week's amazing visit to Cupertino for the Game Dev session and diving back into Vision Pro experimentation. I've exported a simple geometry nodes with animation test from Blender for use in RCP, with intended output to Vision Pro. I've attached a few screenshots showing the node setup and how it animates over time. I select the Cube mesh and export as .usdc with animation. In the finder via quick look, I can actually see it working! If I try exporting as .usdz, however, i'm not seeing any animation in the finder preview. Next, I import the .usdc file to RCP and add an Animation Library component to the cube mesh, but am not seeing any animation selectable, even though I see animation playing back in preview. Next, I import the .usdc into Maya (via proper USD Stage pipeline - i'm learning to be USD compliant for authoring!) to verify if the animation is working, and it does. What step(s) am I missing to get this working in Reality Composer Pro? My goal is to experiment with animating these geometry node instances - along with color animation if possible - over to Vision Pro for full scale, immersive presentation. Of particular note, I am not a programmer, so I am trying my best to brute force this the only way I currently know possible, by keyframe animation and importing through Reality Composer Pro. I realize that, ideally, I should be learning how to leverage the code portion so I can start programatically controlling my 3d entities (with animation), but need more hand holding and real-world examples to help me get there. Thx!

Hello again! So, I am trying my best to figure out how to get a simple, fully Immersive scene that is navigable via the PS5 controller to work on Vision Pro. I am even using ChatGPT (both externally AND in Xcode when it makes fix recommendations) however, I seem to be moving around in circles, having to constantly send error messages back to ChatGPT, then try the new "confirmed to work" fixed code, only to have more errors. I also have explicitly let the AI know that I'm using all the current betas, only to learn there has been lots of stuff deprecated (of course!). This is my initial query to ChatGPT: "How can I create a fully immersive VR experience for Apple Vision Pro, using a PS5 game controller to navigate the user via first person view through a 3d scene?" And then down the rabbit hole the past few days. Seriously, I thought AI was supposed to be helpful! LOL Per Xcode logs, I'm seeing thumbstick movement, but simply cannot get the camera to move. Is this even possible?! Is it a camera defined in Reality Composer Pro? Or, does it need to be defined outside. I'm trying to follow along with the AI, but it seems to go back and forth with different solutions. Here is the latest it's spitting out: __ Thanks for this super clear log — and you’re absolutely right: the gamepad input is working, CameraRoot is moving as expected… but your actual camera view is not changing. This strongly suggests the issue is that RealityKit is not using your custom camera (PerspectiveCameraComponent) for rendering the view. ⸻ 🔍 What’s happening Even though CameraRoot is moving (with correct logs), RealityKit will default to its own internal camera unless: 1. You explicitly assign your camera entity to be the one used, or 2. Your camera is the only one and RealityKit picks it up automatically. But in visionOS 2.0 / Xcode 26, there seems to be a bug or behavior change where RealityKit no longer auto-uses your custom PerspectiveCameraComponent in RealityView unless it’s: • properly set with content.camera, or • part of a .usda/Reality Composer camera hierarchy that’s already active. Unfortunately: 🟥 RealityView.camera = .entity(cameraRoot) ❌ Is no longer allowed (we confirmed this breaks with a type error) ⸻ ✅ The Reliable Workaround: Attach your camera to the Immersive scene itself Since we’re loading a .usda scene (Reality Composer Pro), here’s the most reliable path forward: ✔️ Option A: Embed your camera into the Reality Composer Pro scene 1. Open your Reality Composer Pro scene 2. Add a Camera entity directly in your Immersive.usda scene 3. Name it something like "PlayerCamera" 4. Position it at [0, 1.6, 0] 5. Leave it selected as the default camera Then in your Swift code: • Find the camera entity with .findEntity(named:) • Move that entity instead of creating a new one. ⸻ ✔️ Option B: Force RealityKit to use your custom camera (via transform parenting) Since direct camera assignment is unavailable, we can use a trick: Move the whole RealityView scene via a parent entity with a camera. But let’s go with Option A, since you’ve already got a Reality Composer Pro scene. __ Can any developer over there can make a suggestion on how to move forward? I JUST want to create a sandbox template so I can start exploring 3d scenes created in Maya and sent over to headset. I'll deal with animation next, but come on, why is this so difficult to get working? I'm not a programmer, but have been trying to wrap my head around Xcode and SwiftUI. This needs to be much simpler. Or, you need to provide us creatives with better sample templates and non programmer speak on how to set this up properly. Ideally, you HIRE us 3d professionals to work side by side with the programmers to help make these tools useable - especially Reality Composer Pro. Seriously, I am making a concerted effort to use the native tools, even though I would love to be porting Unreal Engine scenes over. If anyone can help point me in the right direction, coming from a 3D Creator/Animator/Modeler perspective, I, and my fellow peers in the XR/AR/VR community would greatly appreciate it. Thank you.

I’m having issues getting Collision Shapes working in Reality Composer on iPadOS, or with Reality Composer Pro via Xcode on macOS? I’ve posted a video recorded through my Vision Pro showing the issue. The project i’m working on is a Dice Rolling application. The dice don’t appear to be working set as Collision Shape=Automatic, which I assume takes into account the actual silhouette of the shape. https://youtu.be/upPtQY4QOAk?si=yyx6rbSSmVkLxBLg They also don’t rest on their face when they land. Anyone experience this type of behavior and found a solution? I’m currently doing this with Reality Composer, but most likely will also be wanting to get it to work properly in Reality Composer Pro as well. Thx!

Hello! I’ve got a USDZ export from Maya pipeline working with animation, and they load up nicely in the Vision Pro. I’ve been checking out the animated sample files in the Augmented Reality/Quick Loop sample page, specifically, the first three at the top of the page. I would like to know how they are created. I’m a 3d modeler and animator, not a programmer, so dipping my toe in RCP and Xcode/SwiftUI, but could used some informative tutorials for proper workflow. For example, in the Lunar Rover sample, there are lines emanating from the model, then text windows appear. Would I need to create all these extras inside Reality Composer Pro? I’d like to start creating immersive, narrative experiences (both in a volume, and fully immersive) but for prototyping, I want to learn the proper way to add this type of functionality. I think I remember seeing something to do with “schemas” involved. I’m assuming there might be some coding to setup in RCP for when items are selected, then an associated animation is triggered. Can anyone point me towards the relevant documentation to help me get started? Remember, I don’t code. ;) Here are my recent Vision Pro experimentations. https://youtube.com/playlist?list=PLCH753rZ9r6eqXxpIemaSlcyYxjFgR210&si=P_7AY2aL97Upm61i I’m also proficient with Unreal Engine, but getting content packaged and over to AVP is still not ready for prime time, so i’m exploring the native approach. Thanks for helping point me in the right direction!