Added Feb 5, 2026
Cloud-based serverless GPU platform providing unified API access to over 600 generative AI models across multiple modalities including image generation, video generation, audio synthesis, 3D creation,...
Why: Largest collection of generative AI models accessible via unified API, making it the most comprehensive platform for multi-modal AI development.
Added Feb 5, 2026
Generates high-quality 3D models from text descriptions, images, or sketches using Tencent's Hunyuan 3D engine
Why: Tencent's comprehensive 3D generation engine with support for multiple input types and professional output formats, making it ideal for production workflows.
Added Feb 5, 2026
Generates 3D meshes from text prompts or images using AI-powered reconstruction
Why: Meshy AI provides the fastest professional speed-to-3D workflow, enabling artists to iterate from a simple text prompt or 2D image to a usable, textured mesh in under a minute. Its high-quality PBR texture generation and clean topology make it the most efficient tool for game developers and 3D prototypers looking to bypass manual modeling bottlenecks.
Added May 25, 2026
Tripo v3
Why: Tripo v3.1 refines one of the fastest production-ready 3D generators. It is a practical choice for game developers, product designers, and AR/VR creators who need usable assets quickly.
Added May 27, 2026
Rodin Gen-2, also referred to as Rodin 2
Why: Rodin Gen-2 offers a focused image-to-3D pipeline that is easy to use for artists and developers. It is a solid option when you have a 2D concept and need a 3D starting point quickly.
New this month
Added Jul 7, 2026
TRELLIS 2 is an open-source image-to-3D generation model from Microsoft Research, released in 2026
Why: TRELLIS 2 is a valuable open research model for image-to-3D. It is ideal for academics, indie developers, and anyone who wants to run 3D generation locally or build on top of open weights.
New this month
Added Jul 7, 2026
NVIDIA Cosmos 3 is an open physical-AI omnimodel released around May 31 to June 1, 2026
Why: Cosmos 3 is a major open contribution to physical AI. By simulating realistic worlds, it can accelerate training for robots and self-driving cars while reducing the need for dangerous or costly real-world trials.
Added Feb 5, 2026
Microsoft TRELLIS generates high-quality 3D models from text prompts or reference images using a unified Structured LATent (SLAT) representation
Why: Microsoft's state-of-the-art 3D generation model with best-in-class quality for both text-to-3D and image-to-3D workflows. Open-source availability and NVIDIA integration make it ideal for professional 3D asset creation.
Added Feb 5, 2026
Turns 2D concept art into 3D models optimized for game asset pipelines
Why: Good when you want 2D concept → 3D asset workflows with game engine optimization and production-ready outputs.
Added Feb 5, 2026
Generates 3D assets from text prompts optimized for product visualization and catalog-style assets
Why: Worth considering for product-style 3D asset generation with clean outputs optimized for commercial use.
Added Feb 5, 2026
Offers creator tools across video and 3D generation including Dream Machine for video, Genie for 3D capture, and other creative AI products
Why: Strong creative studio brand; useful to track for video + 3D workflows with multiple integrated creative tools.
Added Feb 5, 2026
Helps design 3D scenes and assets in a browser-based workflow with real-time rendering and collaboration
Why: Great for interactive 3D design + rapid iteration with browser-based workflow and real-time collaboration features.
Added Feb 5, 2026
Generates 3D objects from text prompts or images using OpenAI's Shap-E model, a conditional generative model for 3D assets
Why: OpenAI's open-source 3D generation model with comprehensive documentation and active community, representing state-of-the-art conditional 3D asset generation from text and images.
Added Feb 5, 2026
Generates 3D point clouds from text prompts using OpenAI's Point-E model, a fast and efficient approach to 3D generation
Why: OpenAI's efficient point cloud generation model offering fast inference times, complementing Shap-E for workflows prioritizing speed over mesh quality in early-stage 3D concept exploration.
Added Feb 5, 2026
Generates high-quality 3D NeRF (Neural Radiance Field) representations from text prompts using score distillation sampling, a technique that leverages pre-trained 2D diffusion models for 3D generation
Why: Pioneering NeRF-based text-to-3D generation using score distillation, representing a significant advancement in 3D content creation from text without requiring 3D training datasets.
Added Feb 5, 2026
Generates high-quality 3D meshes with textures from images or text using NVIDIA's Get3D model, a generative model that produces detailed 3D triangular meshes with high-resolution textures
Why: NVIDIA's state-of-the-art 3D mesh generation model producing high-quality textured meshes with proper topology, ideal for production workflows requiring game-ready 3D assets.
Added Feb 5, 2026
Generates 3D models from single images using Zero-1-to-3, a model that learns to generate novel views of objects from a single input image
Why: State-of-the-art view-consistent image-to-3D generation model with strong geometric understanding, enabling high-quality 3D reconstruction from single images.
Added Feb 5, 2026
Generates 3D models from single images using Instant3D, a fast and efficient approach to image-to-3D conversion
Why: Fast and efficient image-to-3D generation model offering rapid 3D mesh creation from single images, ideal for workflows prioritizing speed and iteration.
Added Jan 1, 2026
Hymotion 1
Why: Tencent's cutting-edge open-source text-to-3D motion model with production-ready output and extensive motion category support.
Added Feb 5, 2026
Tripo AI v3 generates high-fidelity 3D meshes with clean topology and PBR textures in seconds
Why: The fastest path to 3D. Its v3 engine produces meshes that are actually usable in production pipelines without massive manual cleanup.
Added Feb 5, 2026
Genie is Luma's specialized 3D generation engine
Why: The 'Midjourney' of 3D. It prioritizes aesthetic quality and texture detail, making it the best for visual-first 3D projects.
Added Feb 5, 2026
Meshy v3 is the fastest text-to-3D and image-to-3D engine, producing high-topology meshes with PBR textures
Why: The bridge between AI and Game Engines. It generates usable, textured meshes that can be dropped directly into Unity or Unreal without manual cleanup.
Added Feb 5, 2026
SAM3D v2 leverages Meta's latest Segment Anything technology to reconstruct 3D geometry from single or multiple images with extreme precision
Why: The most precise open-source 3D reconstruction tool. Its boundary awareness makes it unbeatable for complex object modeling.
Added May 3, 2026
Meshy 6 continues Meshy's focus on fast, usable 3D assets with emphasis on multi-image conditioning—feed several views or references so the model better infers shape, materials, and proportions for ga...
Why: Teams outgrew 'cool sculpt from one photo' and need consistent assets from multiple references—Meshy 6 is explicitly positioned for that workflow.