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 4

Oct 20Tue61–79
  1. GamesBeat50

    Ludo.ai launches Ludo CLI, bringing game asset generation to the developer terminal

    Ludo.ai has released Ludo CLI, letting developers use its game asset generation tools directly from the command line without opening a browser. The tool can generate sprite sheets, animations, textures, 3D models, videos, sound effects, music, and voice, saving results straight to the project directory. It supports scripted batch generation and cost previews, and coding agents such as Claude Code can also call it. The CLI is available to Pro and Studio plan users and can be installed via npm or npx.

    Why it matters: Generating assets from the command line, and letting coding agents like Claude Code call them, makes this worth a look for teams that want to build asset production into automated pipelines.

  2. arXiv Game AI44

    InfiniDream: Open-ended photorealistic 3D worlds through procedural generation

    InfiniDream proposes a VLM-driven framework for open-ended procedural 3D world generation that creates novel photorealistic assets without relying on preset factories and APIs. Evaluated on 100 object and 20 scene generation tasks, it shows improvements on four perceptual metrics. The framework also combines semantic scene planning with deterministic frustum-guided grid placement to build large-scale 3D worlds with procedural population and animation.

    Why it matters: Existing VLM-guided procedural methods are mostly limited by preset factories and APIs; this paper tries to open up asset types and can be read alongside comparable methods.

Oct 19Mon
  1. Viggle AI35

    Viggle AI releases JST-2, a physics-native world foundation model

    Viggle AI has released JST-2, a full-stack physics-native world foundation model. According to the announcement, its entire model stack is built in 3D rather than in pixel or video space. The company says it can generate 3D scenes within seconds, scale them in real time, and create characters with built-in motion using the same general architecture.

    Why it matters: Unlike most world models that learn in pixel or video space, it builds its entire model stack directly in 3D, making it a useful reference for comparing different technical approaches.

  2. QbitAI57

    VAST open-sources EdenLive real-time world model, over 24 FPS at 720P on a single consumer GPU

    VAST has open-sourced EdenLive, a real-time world model that generates frames live under any reference input and art style and keeps running continuously. According to VAST, on a single Nvidia RTX 5090 at 720P, its 5B model exceeds 24 FPS, with end-to-end latency in the hundreds of milliseconds. EdenLive handles only visual rendering, while world state and interaction rules are still maintained by the upstream interaction system. Model weights, inference code and a technical report are now available.

    Why it matters: The article explains the design split between real-time rendering and state maintenance, and gives speed and latency figures on consumer GPUs, helping readers judge its usable range in game prototyping.

Oct 16Fri
  1. Tripo37

    LidaMidorin open-sources AI agent workflow for VTuber 3D character creation

    Tripo reposts LidaMidorin's open-source skill library for VTuber 3D modeling. The cited workflow uses Tripo P2.0 to generate each part, then combines the parts, rigging, IK/FK, and shader adjustments in Blender. The quoting account suggests about 5,000 to 10,000 quads per part and says the full production takes about two weeks.

    Why it matters: The cited production steps cover part generation, rigging, IK/FK, and jiggle physics adjustments, and the polygon count suggestions can be compared with your own VTuber asset pipeline.

Oct 15Thu
  1. Tripo41

    Tripo P2.0 powers the 3D asset pipeline for a solo fishing game

    Tripo's official account reposted a solo game workflow in which all 3D models, including palm trees, rocks, docks, boats, a cabin, and characters, were generated with Tripo P2.0, which it says powered the entire asset pipeline. According to the original post, the developer used Claude Opus 5.5 through MCP to connect to Blender for model setup and for animating the characters, fishing rods, and boats, then imported the assets into Unity 6 to build the forest, rivers, beach, and dock. The developer ran the game after each step and added walking, fishing, bait selection, and a day-night cycle one by one.

    Why it matters: The workflow breaks 3D model generation, Blender processing and animation, and world building in Unity 6 into clearly defined steps, offering a reference for indie asset pipelines.

Oct 14Wed
  1. Naavik64

    AI decompilation fuels viral game mash-ups, challenging source code protection and distribution models

    AI tools let amateur developers decompile commercial games and combine characters and mechanics. Mash-up videos on X have drawn millions of views, with one Minecraft-to-Elden Ring clip reaching 23.3M views. The article outlines three paths: pass-through mods, mechanic porting, and full decompilation and rewrite. It notes that decompilation itself is not illegal, but the legal boundaries for distributing rebuilt versions remain unclear. The author argues that as copying gets easier, long-term advantage may shift toward strong IP and distribution.

    Why it matters: The article breaks AI decompilation into three paths (pass-through mods, mechanic porting, and full rewrites), helping readers gauge its practical impact on source code protection and copyright.

Oct 13Tue
  1. QbitAI38

    ByteDance world model debuts live at 2026 Wonderful Night, generating and freely exploring 3D scenes from a single sentence

    At the tech segment of Douyin Group's 2026 Wonderful Night, ByteDance showed its self-developed world model, which can generate a 3D scene from a single sentence and supports free exploration, real-time interaction, object generation and editing, and cross-scene connectivity. The model has not been officially released yet, and the live demo was presented by Tim of Yingshi Jufeng.

    Why it matters: Using ByteDance's world model live demo as an entry point, this compares the differing approaches of OpenAI, DeepMind and Nvidia to spatial modeling and physical AI training.

Oct 12Mon
  1. Tripo44

    Tripo spotlights community open-source kit Charakuru, which generates VRM characters from a single illustration on Tripo P2.0

    In its Community Builds series, Tripo highlights Charakuru, an open-source character modeling kit built by community partner Nano (@Dstudio_ai) and powered by Tripo P2.0.

    Why it matters: Tripo has officially laid out the full workflow of the community open-source kit Charakuru, so readers can judge how workable single-image-to-VRM character generation is.

  2. Meshy45

    How to build a game with Claude Opus 5.5, Blender, Unreal Engine, and Meshy

    The official Meshy account reposted a walkthrough for building a game with Claude Opus 5.5, Blender, Unreal Engine, and Meshy. Following @rewind02's steps, Blender is connected through an MCP plugin and Meshy through MCP plus an API key, with Opus orchestrating the three tools inside a single conversation: Meshy generates props and characters, Blender handles cleanup, placement, and materials, and Unreal handles lighting, physics, and the game itself. The walkthrough says a full first build takes about 4 hours and uses roughly 19% of the weekly Max plan quota, and recommends getting the first level right first, since later levels go much faster once the assets already exist.

    Why it matters: The post lays out clearly how 3D generation, cleanup, and engine setup are split across different tools, and gives the time and quota cost of the first build.

Oct 10Sat
  1. Tripo44

    Tripo P2.0 adds quad mesh generation, polycount variants, and local Mesh Edit

    Tripo P2.0 update supports cleaner quad mesh generation, polycount variants, and local Mesh Edit. Smart UV automatically handles seam placement and UV unwrapping, while Remove Lighting generates cleaner base colors for easier adaptation to different engines' lighting setups. Rigging offers a more complete humanoid skeleton and engine-ready presets, and Text to Motion has been added for fast animation generation, with the entry point at https://studio.tripo3d.ai.

    Why it matters: P2.0 puts quad mesh generation, polycount variants, and local Mesh Edit into a single workflow and provides engine-ready rigging presets, making it easy for artists to adjust assets to project needs.

Oct 8Thu
  1. Tripo37

    How to build a level blockout kit in minutes with Tripo P2.0

    Tripo demonstrated a three-step workflow for building a level blockout kit with Tripo P2.0: first generate a complete environment with P2.0, then import it into Blender and run Separate → By Loose Parts to split it into individual parts. The company says the output is native quad topology that can be used directly in production, and work that originally took hours can be done in minutes.

    Why it matters: It lays out a three-step workflow from generating an environment to splitting it into separate parts in Blender, and this workflow can be transferred to your own level blockout work.

  2. Tripo36

    Tripo launches P2.0 Official in Tripo Studio

    Tripo's official account announced that P2.0 Official is now live in Tripo Studio, inviting users to try it out in its generation workspace. The entry point given in the post is https://studio.tripo3d.ai/workspace/generate?tab=smart_mesh&utm_source=twitter&utm_medium=social&utm_campaign=game-ready-pipeline&utm_content=p2-official.

  3. GamesBeat44

    University of Chicago researcher Rana Hanocka launches 3D generation platform Thrixel and releases agent workflow Build World

    Thrixel, founded by University of Chicago computer science assistant professor Rana Hanocka, launched a 3D generation platform whose part-based generation architecture gives assets individually named parts and logical hierarchies, so AI agents can recognize, assemble, and animate them directly in game engines.

    Why it matters: The platform breaks 3D assets into individually named parts, letting agents call and animate them directly in the engine, offering a structured approach for bringing assets into AI workflows.

Oct 7Wed
  1. GamesBeat58

    Google and Unity partner to launch Playground and Unity Spark for no-code 3D game generation with natural language

    Google and Unity announced a strategic partnership, launching the no-code game generation platform Google Playground and Unity Spark built on the Unity engine, letting users generate and customize playable 3D games with natural language prompts.

    Why it matters: The partnership connects no-code generation with the Unity engine runtime, offering a way to gauge what in-browser 3D game creation can currently achieve.

Oct 6Tue
  1. Hyper3D Rodin41

    Hyper3D's ACT can generate skeletons, skinning, and text-driven motion, merging rigging and motion into one pipeline

    Hyper3D's ACT can generate skeletons, skinning, and text-driven motion, with rigging and motion generation merged into a single unified pipeline. This note comes from the 5th post in its tweet series and includes a link to the ACM paper https://dl.acm.org/doi/abs/10.1145/3811392.

    Why it matters: The original post states that ACT merges rigging and motion generation into a single unified pipeline, which shows how the skeleton and skinning of a 3D asset can be produced together.

Oct 4Sun
  1. arXiv Game AI39

    Code2Games: enabling coding agents to generate playable game worlds from natural language

    Wei Wu proposes Code2Games, an agent framework that lets coding agents build structured game worlds on top of a Blender world generated from the same game intent. The framework coordinates scene analysis, gameplay planning, constrained game world generation and engine customization through shared scene and gameplay representations, and when adapting to Unreal Engine 5 uses compilation diagnostics, runtime feedback and playtest results for execution-guided refactoring.

    Why it matters: The paper coordinates the generation stages with shared scene and gameplay representations and compares generation quality on a benchmark containing ten fixed game prompts, making it easy to measure against existing approaches.

Sep 30Wed
  1. Youxituoluo43

    Vidu S2 Powers AI Streamer Ziying's Mid-Autumn Broadcast, Drawing Over 300,000 Viewers

    During the Mid-Autumn Festival, Zaomeng Ciyuan's AI streamer Ziying took on a time-limited broadcast challenge in her live room; the real-time interaction model behind her is Vidu S2, released not long before, and the room drew as many as 20,000 viewers at one point. Ziying has no fixed script: viewers can request songs, vote on her look and send gifts, and she has to change outfits and perform while interacting, then pick up where she left off after being interrupted. The author also tested Vidu S2's Avatar and Editing: uploading a real person's photo or an anime image and adding some settings creates a digital human, and switching on the camera allows real-time outfit changes, art style changes and background swaps while filming.

    Why it matters: Using a livestream hosted by an AI streamer with no fixed script as a case study, it tests Vidu S2's real-time interaction and outfit-switching abilities, and discusses how they could be applied to game NPCs.