3D

Linus Ekenstam says PLY recalculates material estimates using kerf, edge trimming and stock lengths. He reports slowdowns above roughly 300 parts and describes planned rendering optimizations.

PJ Accetturo says the $29,575 budget for a film made in 10 days went to labor, with AI filmmakers costing roughly $1,000 a day. Production mixed 3D-guided Seedance shots with prompt-only outputs.

PJ Accetturo reports making an AI film for $29,575 in 10 days. He shared a Claude skill, Dreamina prompts and a Claude-run Blender workflow used by a team without prior Blender experience.

Danny Limanseta shared a playable desktop-browser parcel delivery game built mainly with Sonnet in Three.js. His development posts explain the model choice and discuss trailer revisions and a shader issue in the rainy, Hong Kong-inspired project.

Linus Ekenstam demonstrated a browser-based skate-park designer that generates construction plans, cut lists and bills of materials. It also estimates store-linked prices and exports printable scale models.

Amir Mushich released a GitHub skill and installation guide that uses GPT-6 Astra or Claude Opus 5.5 to turn real-estate photos into walkable 3D spaces. The workflow targets Unreal Engine scene creation.

Higgsfield released Claude Opus 5.5 skills for arranging editable Blender scenes, sorting footage, cleaning shots, compositing scene changes, and directing TouchDesigner. The release also adds a Vectorize skill that converts raster illustrations into layered outputs.

Higgsfield described using Blender to test timing and camera moves for difficult shots before generation. Its pipeline combines hand-drawn storyboards, character sheets, Blender blockouts, Claude prompting, and Seedance 2.5.

Creators prompted Claude Opus 5.5 to build 3D scenes in code, score individual visual elements, and revise them iteratively. Reported outputs include a Three.js ship scene and an explorable Atlantis world built in about two hours.

Meta's VR glasses move compute and battery to a wired pocket module, bringing headset weight to about 100 grams. Reports cite a 5K micro-OLED display and spring 2027 availability.

Higgsfield says Claude Opus 5.5 built a 3D arcade shooter through its workflow. Separate demos rebuild a building from one photo in Blender, then simulate its collapse.

Amir Mushich reports using GPT-6 Astra and Unreal Engine 5.8 to turn 20 real-estate listing photos and map panoramas into an interactive property walkthrough. He says Blender tests did not work well for the project.

Higgsfield demos show Claude Opus 5.5 converting paintings, drawings, character sheets, floor plans, and photos into editable Blender-style scenes. One demo also builds a browser app for placing photo-derived furniture in an interior.

A creator’s tool uploads video and exposes frames through volumetric playback, time slices, opacity controls, synchronized playback, and 360-degree orbit export.

Tutorials show Astra workflows moving from DiffUI concepts or wireframes into Codex and three.js, with transparent layers, animation, and reusable 3D skills.

Atria Dawn Preview is presented as a research agent that validates results against tests, metrics, rendered files, file states, and citations. Its reported API has a 256K text context window and is text-only.

The workflow gives GPT-6 Astra authenticated MCP access to Hyper3D Rodin for planning and generating 3D assets. A related setup sends an image through Astra and Codex to create an editable 3D space rather than a static model.

A 166,700-neuron fly-brain simulation placed a guitar body and headstock while scale-length math constrained the neck. Related tests used the system to draw between 23 anchor points and turn neural spikes into a 643-note performance.

A creator used Blender to block scenes, cameras, framing, and timing before generating finished shots with GPT-6 Astra and Seedance 2.5. The project used seven image references, four previs clips, and extensive editing and splicing.

A creator says GPT-6 Astra recreated a studio as a Blender scene from five photos and three panoramas in 11 minutes. The model and web viewer were published for inspection, while a separate demo showed a similar office.

Higgsfield shared GPT-6 Astra projects including an interactive fly brain, beehive, pollen-flight simulation, and fruit-fly rhythm game. The demos let viewers inspect systems and alter conditions rather than only watch rendered output.

Higgsfield demoed GPT-6 Astra turning visual references and plans into editable Blender models, including nail art, an AirPods case, a Mies house, and Space Shuttle Discovery. The shuttle demo contains 192 assemblies.

Higgsfield demoed GPT-6 Astra creating interactive 3D experiences including a wardrobe, room planner, Tokyo rail tracker, and hand-tracked story theatre. A Spline robot demo adds collision detection and pose correction to its walking solver.

Higgsfield demos Astra-built interactive models for a beating heart, ant colony, building systems, and music scores. Other examples include an Ancient Egypt classroom lesson, a virtual-city disaster test, and a 3D product website.

Creators have shared browser games, Godot projects, simulations, and a released tower-defense game made or finished with GPT-6 Astra. Reported workflows combine Astra with Blender, Three.js, Fable, Godot, and imported 3D assets.

Creators report using GPT-6 Astra, reference materials, and Blender to build editable 3D models. Reported results include an 11-minute studio model, a 3D-printable replacement part, and a cleaned RealityScan mesh.

Reported GPT-6 Astra projects include a Roblox dragon world, a prompt-responsive Minecraft screen, a first-person motion simulator, and several Three.js games. An Astra-made Mac and Windows game also added saved progress and revised controls.

Developers report publishing playable web and 3D games built with GPT-6 Astra. Reported projects include a four-level Pitfall clone and Blender/Godot builds; one tutorial covers four games made in about two hours.

Higgsfield says Astra converted a floor plan into scene code, a Blender location model, and a Cycles render. Separately, a creator says it made a to-scale cabin walkthrough from a 38-page PDF in about 10 minutes.

Intangible now lets creators draw and edit splines on scene geometry, attach objects, and animate progress along a route. Objects can orient to travel direction using the same spline system as roads and populators.

Users are publishing Fable 5.1 browser worlds including game clones, shader-driven scenes, a train yard, and a procedural Kyoto three.js site. One reported racing-game test cost $123.98 and used 1.2 million tokens, exceeding Fable 5.

Higgsfield says GPT-6 Astra reconstructed a floor plan in Blender, furnished and lit it, then ray-traced a walkthrough in Supercomputer. A separate company demo shows a playable FPS made with the approach, but the evidence comes from vendor demonstrations rather than independent tests.

Higgsfield's Blender plugin lets creators set camera paths, actor placement, and timing before generating AI-video takes. A phone can also serve as a virtual camera while Blender supplies the scene.

World Labs says Atlas generates consistent worlds from text, images, and camera paths. Creator demos show sparse photos or phone-video captures reconstructed for reframing from new viewpoints.

Spline says Hana V2 lets agents generate through MCP or its in-app tools. The release adds PBR GLB and GLTF import, SVG and PDF export, a WebGPU canvas, and improved vector editing.

Meng To released ThreeUI, an open-source library of procedural 3D landing-page components, icons, motion designs, and templates. Creators can copy its source or prompts into coding agents, while some extras remain paid.

Spline rebuilt its web-based 3D editor with Agent Mode and an MCP connection for its desktop app. V2 also adds a WebGPU engine, PBR and HDR workflows, and scripting for code-enabled scenes.

SpAItial is recruiting creative partners for a beta that turns simple iPhone recordings into consistent multi-room 3D worlds. The company describes the system as a generative world model.

Intangible connects to Claude Code, Claude Desktop, or ChatGPT through MCP so an agent can build scenes, compose cameras, and preview renders. The beta leaves creators to finish directing inside the scene.

Rainisto's workflow turns a screenplay into a rough Blender animation and uses it as Seedance video reference. The Blender timeline preserves planned cuts, lenses, and camera angles before generation.

Bilawal Sidhu demonstrates 2D moments reconstructed as 3D holograms and left at their original physical locations. One venue-scale spatial-memory project used more than 500 captures.

Danny Limanseta says Grok 4.6 produced most of a WebGPU horde shooter, including its UI, visual effects, and sound effects. Meshy generated and rigged the character models separately.

Meng To released the Kage landing page repo and reusable Three.js skills after building the 3D scrolling site with Claude Code, Opus 5, and image tools. He cites a 922 KB build and mobile fixes.

Meng To released code and prompts for a scrolling bookshelf demo refined through many Codex prompts. Karpathy separately used Claude Opus 5 to turn the opening of LOTR into a 5,500-line Three.js render.

Meng To used Opus 5 through Codex and Claude Code to rebuild Sakura Crossing as a single-file Three.js scene. Other demos show one-prompt Fallout-style RPGs and a Pool Rooms survival-horror level.

New Opus 5, Codex, and Fable demos showed agents creating 3D worlds, Blender assets, Godot ports, and one-shot games. Pushback focused on whether the clips become games worth playing.

Creators posted demos where Opus 5 built browser 3D games, Codex Sites produced a Three.js game, and Grok 4.5 helped redesign a Steam card game. Some workflows now pair video concepts with Claude Code, but the evidence is demo-based.

A demo roundup showed Grok 4.5 generating game engines, worlds, controllers, CAD objects, React projects, and voxel scenes. The clearest consequence was faster playable prototyping by a single operator.

Google DeepMind unveiled GenCeption, which turns video into depth, segmentation, camera rays, 3D keypoints, and prompt-steered scene representations. The thread links project and Hugging Face materials.

Demos from Gokay and Meng To used video, object-view, and image references to generate HTML, Three.js, or Blender scenes. The builds paired Sol or Claude Code with tools including Reve, HyperFrames, and Blender MCP.