Skip to content

Fields

3D generation latest news

3D assets and scenes from text or images: meshes, materials, topology quality and whether they hold up in an engine.

79 picks52 in the last 30 days228 collected in all

Updated

Picks archive · Page 3

Nov 2Mon41–60
  1. Chuapp65

    Under AI pressure, Chengdu's art outsourcing industry is polarizing

    Starting in 2026, art outsourcing orders from domestic studios explicitly allow AI, and the terms contractors receive have become halved turnaround times and lower per-unit prices. In 2021 studios still banned AI outright; by 2025 the line was that even with AI, the work had to be hand-drawn again.

    Why it matters: Several Chengdu art outsourcing workers give concrete figures on quotes, turnaround times and rework, offering a way to check exactly which step of the art production chain AI saved time on and which step cost more.

Oct 31Sat
  1. Roblox DevForum Announcements71

    Roblox launches Scene Generation beta in Studio for editable scenes from images and prompts

    Roblox has launched a beta of Scene Generation in Studio, which can generate editable scenes made up of models, textures, and terrain from one or more images and a text prompt; a single generation usually takes 2-3 minutes.

    Why it matters: Roblox details Scene Generation's input methods, generation time, and iteration tips, which developers can use to judge whether it fits into their own level prototyping workflow.

  2. Unity Blog49

    Unity looks back at 2026 Industry releases and previews Q4 updates

    Unity recapped the 2026 release cadence for Unity Industry, with more than 15 releases shipped over the year. Unity 6.4, 6.5 and 6.6 are out, and Unity 6.7 LTS is planned for the fourth quarter.

    Why it matters: It walks through Unity Industry's releases quarter by quarter across the year along with the Q4 plans, making it easier to time upgrades to your own 3D data pipeline and team collaboration tools.

  3. Hyper3D Rodin56

    Hyper3D Rodin launches Agentic Mode for WorldGen

    Hyper3D by Deemos announced that WorldGen's Agentic Mode is live, generating a complete 3D scene mesh from a single image, including lighting, materials and individual object meshes, all editable. The author says every asset can be exported directly to DCC tools such as Blender with lighting preserved, for uses including game development, design and robotic Sim2Real. Try it at https://hyper3d.ai/workspace/rodin?feature=worldgen.

    Why it matters: The original post says WorldGen's Agentic Mode can turn a single image into a complete, editable 3D scene and export it to DCC tools such as Blender.

Oct 30Fri
  1. Roblox DevForum Announcements61

    Roblox Studio beta adds Prompt-to-Avatar for generating game characters from text

    Roblox Studio beta adds Prompt-to-Avatar, which generates 3D character models from text descriptions that are ready to use in Roblox. The process involves describing the character and iterating on 2D concept images before generating the model, typically taking 3 to 6 minutes. Options include built-in clothing, dynamic heads, and R15 or Advanced R15 rigs. The beta does not generate accessories, even if they appear in the concept images; the full release will add support.

    Why it matters: This item offers a structured prompt format and explains options such as built-in clothing, dynamic heads, and R15 rigging, making it useful for developers evaluating whether AI-generated characters can fit into their Studio workflow.

  2. 80 Level40

    Giant robot in cathedral ruins: a 3D production breakdown

    Korean environment artist Jueon Kim breaks down the production of his work Silent Ruins, a scene centered on a cathedral and a giant robot that has crashed into it. The article details how to create damaged structures in Unreal Engine using Fracture Mode, Anchor Fields, Bomb Fields, and the Chaos Cache Manager.

    Why it matters: The author explains how Chaos fracturing, five model workflows, and UV division of labor are handled, a useful reference for comparing against your own art pipeline.

Oct 29Thu
  1. Tripo37

    Tripo launches Agentic Canvas beta, with agents chaining 3D asset workflows

    Tripo has launched a beta of Agentic Canvas, where users describe what they need in conversation and an agent plans and runs workflows from description to 3D asset. The beta is currently open to MAX and Team users, with other users to be added gradually. The canvas supports batch processing and reusable workflows, and assets can be inspected, cleaned up, rigged, and edited through AI 3D Lab.

    Why it matters: For art pipelines that often switch between several 3D tools, it brings generation, batch processing, and asset cleanup onto one canvas, making it a useful reference for organizing workflows.

Oct 28Wed
  1. Meshy38

    Meshy uses Hermes Agent to generate 5 game-ready 3D assets from one prompt and build a top-down dungeon game

    Meshy showed Hermes Agent calling Meshy end to end from a single prompt to generate five game-ready 3D assets, namely a sword hero, two skull lantern ghosts, a jar, a chest, and a torch, and to rig and animate the hero. The whole process took 6 minutes, and all five assets went into a top-down dungeon game, consuming 191 credits in total.

    Why it matters: The reported runtime and 191-credit consumption of this end-to-end run make it possible to estimate the actual cost and efficiency of using an agent to generate game assets in bulk.

  2. Meshy34

    Meshy's Blender MCP offers two options: your own API key or a Premium plan

    Meshy offers two ways to use it with Blender: your own Meshy API key, which requires the Pro plan or higher, or MCP for Blender in Blender Premium, which needs no Meshy key. The author shows in the quoted content how, within the same chat, the agent builds, lights and renders a sci-fi hangar around the model. Full steps are in the official tutorial.

    Why it matters: The article distinguishes two ways to connect to Blender: an API key that requires the Pro plan or higher, or the key-free Premium MCP. Readers can choose the path that suits them.

  3. Meshy43

    MCP for Blender now supports generating 3D models with your own Meshy key

    MeshyAI says MCP for Blender now lets users connect their own Meshy key. When a user asks an agent to generate a model, it goes directly into the Blender scene. The company says the models come with textures and stand on the ground at true scale. The integration was built into MCP for Blender by @sidahuj.

    Why it matters: It notes that generated models come with textures and stand on the ground at true scale, which may interest artists and developers who want generated assets to flow directly into their Blender workflow.

  4. Hyper3D Rodin45

    Hyper3D Rodin's WorldGen coming soon with Agentic Mode

    Hyper3D announced that WorldGen will soon add Agentic Mode, which generates a complete 3D scene mesh from a single image. The output includes lighting, materials, and separate object meshes, all of which can be edited and refined. The original post says it is aimed at uses such as game development, design, and robotics Sim2Real.

    Why it matters: Single image to editable 3D scene with lighting and materials, useful for studying 3D asset production workflows

Oct 24Sat
Oct 22Thu
  1. arXiv Game AI45

    AnyGameRenderer proposes entity-consistent generative rendering across games and an entity-level benchmark

    AnyGameRenderer is a video-to-video generative renderer that turns prototype footage such as gray-box and colored-geometry scenes produced by AI agents into high-quality visuals with characters, motion detail, and effects, while keeping the layout, camera, and each entity's position and timing unchanged.

    Why it matters: The paper presents a method for turning gray-box prototype videos into high-quality visuals, along with an entity-level benchmark and quantitative comparisons, making it possible to judge whether generative rendering preserves entity correspondences.

  2. Tripo41

    Tripo Studio reworks rigging and animation features

    Tripo Studio has reworked its rigging and animation features for motion that can be used directly in games. The new version supports full-body and hand skeleton rigging and provides five skeleton presets ready for use in engines. Text to Motion generates 1–10 second animations from prompts, and up to five motion segments can be combined. Characters can be auto-rigged, animated, and exported without re-mapping.

    Why it matters: Covers the full workflow from rigging and motion generation to export, making it worth evaluating whether it can replace the existing manual animation step.

  3. Meshy38

    Meshy is now available in Hermes

    Meshy is now available in Hermes Agent as an official plugin. Users can have Hermes generate 3D models through Meshy's MCP server, such as a treasure chest model for Godot or a printable model converted from a photo of a cup. Hermes Desktop renders models in chat and plays rigged character animations inline, and its gallery saves each model with its prompt. In messaging apps, results arrive as short preview videos.

    Why it matters: The original post explains that Meshy connects to Hermes Agent through an MCP server, letting users generate and preview 3D models directly in conversation. It is useful for developers who want to bring 3D generation into agent workflows.

Oct 21Wed
  1. Tripo38

    Eden-Live now officially available on @reactorworld.

    Tripo's real-time generative rendering tool Eden-Live is now officially available on the Reactor platform, with a live online demo to try. According to a quoted post, it can repaint 3D scenes or prototypes into interactive worlds, change styles in real time using reference images and text, and allow prompts to be edited during runtime.

    Why it matters: Eden-Live offers an online demo on the Reactor platform, useful for developers interested in real-time visual repainting and scene stylization who want to evaluate integration options.

  2. Viggle AI49

    Viggle AI releases JST-2, unifying 3D character, motion and scene generation

    Viggle AI has released JST-2, a world foundation model that is now live in its API. Developers can get started at https://viggle.ai/developers. The company says JST-2 builds its full model stack in 3D space rather than pixel or video space, generating 3D scenes within seconds and expanding them in real time. The same general architecture can also generate 3D characters with built-in motion.

    Why it matters: Unlike most world models that learn in pixel or video space, JST-2 builds its entire model stack directly in 3D space, and its API is now open.

Oct 20Tue
  1. QbitAI53

    Meshy launches Meshy Edit, enabling local 3D model edits from a one-sentence description

    Meshy releases Meshy Edit, a local editing feature in which users box-select a region of a model and describe the change in one sentence, generating a new model in about a minute while the unselected parts stay unchanged. The feature is open to all registered users, costs 20 credits per edit, and supports high-precision models generated with Meshy 6 and Meshy 7.1. Every edit generates a new model and keeps the original; the new model can be edited further, downloaded, or sent straight to slicing software for 3D printing.

    Why it matters: It lays out the edit flow — box-select a region, describe the change in one sentence — and the price of 20 credits per edit, so 3D creators can judge whether it saves them the time of manually revising a model.

  2. arXiv Game AI35

    World2HOSI uses a multi-expert harness to generate long-horizon human-object-scene interaction data

    World2HOSI is a multi-expert harness framework that generates continuous human-object-scene interaction (HOSI) data from 3DGS scenes and natural language instructions. The paper reports that it achieves the best task completion and interaction quality on the evaluated HOSI tasks, and produces more diverse data. The method reduces physical artifacts through persistent scene state, bounded residual optimization, and contact-driven physics simulation.

    Why it matters: The paper orchestrates existing expert models within a unified scene state, offering a transferable idea for generating long-horizon interactions where training data is scarce.

  3. GameLook56

    Can AI models operating Blender for 3D modeling threaten Tripo and Meshy?

    The article argues that GPT-6 Astra can operate Blender through interfaces such as Blender MCP to complete 3D modeling, scene building, and animation, increasing the competitive pressure on dedicated 3D generation tools. It cites a hospital corridor scene built from scratch by Astra in about 45 minutes. On OpenAI's BenchCAD test, Astra scored 95.9%, while GPT-5.6 Sol and Claude Fable 5.1 scored 83.3% and 84.3%, respectively.

    Why it matters: The article compares the division of labor between general-purpose models operating Blender and specialized 3D tools such as Tripo and Meshy, making it useful for judging the competitive position of 3D generation tools.