Resources

AI models for 3D pipelines

A directory of 214 AI models from 54 makers, covering 3D generation, 3D processing, image, language, and audio. Each entry gives the model's name, who makes it, and what it does.

Models
214
Makers
54
Model types
5

Hydrilla runs one of these models: BlueFox, Hydrilla's 3D model. Every other entry is a reference to the wider field, listed so a studio can see what exists around each stage of a 3D pipeline. A listing implies no partnership, endorsement, or availability in Hydrilla.

The directory covers the model types that feed a 3D asset pipeline. Video models are out of scope.

214 models

3D generation models

3D generation models turn a text prompt or an image into a mesh. They differ most in what arrives with the geometry: UVs, PBR texture maps, separate parts, and clean topology.

  • Hydrilla AI

    1 model

    Runs in Hydrilla

    BlueFox, Hydrilla's 3D model, returns a mesh split into parts, UV-unwrapped, with PBR maps, from a typed prompt or an uploaded image.

    • BlueFox 1Text or image to 3D
    About BlueFox
  • Tripo

    7 models

    Text, image, and sketch to 3D, with low-poly and part-based variants.

    • Tripo 3.5Text or image to 3D
    • Tripo 3.0Text or image to 3D
    • Tripo3D v3.1Text or image to 3D
    • Tripo P2Text or image to 3D
    • Tripo P1Text or image to 3D
    • Tripo Smart Low PolyLow-poly generation
    • Tripo Generate PartsPart-based generation
  • Meshy

    5 models

    Text and image to 3D, with a lighter tier and a topology-aware variant.

    • Meshy v7.1Text or image to 3D
    • Meshy v6Text or image to 3D
    • Meshy 6 LiteText or image to 3D
    • Meshy-T2.5 Smart TopologyTopology-aware generation
    • Meshy Figure PrototypeFigure generation
  • Tencent

    4 models

    The Hunyuan3D family, plus Pixal3D from Tencent ARC, which lifts pixel features into 3D for pixel-aligned geometry and PBR textures.

    • Hunyuan3D 3.1Text or image to 3D
    • Hunyuan3D 3.0 LowPolyLow-poly generation
    • Hunyuan3D RapidText or image to 3D
    • Pixal3DImage to 3D
  • Microsoft

    1 model

    Open-weights checkpoints from Microsoft Research that teams host on their own GPUs.

    • TRELLIS 2Image to 3D
  • Hyper3D

    1 model

    Rodin, the 3D model from Hyper3D by Deemos.

    • Hyper3D Rodin 2.5Text or image to 3D
  • Hi3D

    2 models

    High-resolution image to 3D in two quality tiers.

    • Hi3D v3.0 QualityImage to 3D
    • Hi3D v3.0 MasterImage to 3D
  • Meta

    1 model

    3D reconstruction of objects from a single image.

    • SAM 3DImage to 3D reconstruction
  • DreamTech

    1 model

    • Direct3D-S2Image to 3D
  • A research model for accurate multi-view object reconstruction through generation.

    • ReconViaGen 0.5Multi-view reconstruction
  • Atlas

    2 models

    • Titan v1Text or image to 3D
    • 404—GENText or image to 3D

3D processing, texture, and rigging models

3D processing models work on a mesh that already exists: they retopologize it, unwrap UVs, paint textures, split it into parts, rig it, or animate it.

  • Meshy

    8 models

    • Meshy RemeshRetopology
    • Meshy UV UnwrapUV unwrap
    • Meshy Texture v7Texturing
    • Meshy Texture v6Texturing
    • Meshy N1 TextureTexturing
    • Meshy RiggingRigging
    • Meshy Text to MotionAnimation
    • Meshy Auto SplitPart splitting
  • Tripo

    7 models

    • Tripo Texture 3.5Texturing
    • Tripo Texture 3.0Texturing
    • Tripo RetopologyRetopology
    • Tripo Smart UVUV unwrap
    • Tripo Segmented PartsPart splitting
    • Tripo Mesh SegmentationSegmentation
    • Tripo Rigging v1.0 / v3.0Rigging
  • Tencent

    4 models

    • Hunyuan UV UnfoldUV unwrap
    • Hunyuan Smart TopologyRetopology
    • Hunyuan3D PartsPart splitting
    • Tencent 3D Texture EditTexture editing
  • Hyper3D

    1 model

    • Hyper3D BangPart splitting
  • Hi3D

    2 models

    • Hi3D SplitPart splitting
    • Hi3D v3.0 TextureTexturing
  • fal

    1 model

    Seamless, tiling PBR material sets from text or a starting image.

    • PATINA PBR MaterialsPBR materials
  • NVIDIA

    1 model

    A kinematic motion diffusion model controlled by text and keyframe constraints.

    • Kimodo Text to MotionAnimation
  • Atlas

    2 models

    • Atlas RemeshRetopology
    • Atlas 1 RiggingRigging

Image models

Image models generate and edit pictures from a prompt. In a 3D pipeline they produce the concept art and the reference image that image-to-3D starts from, and they upscale, cut out, and vectorize source art.

  • The Nano Banana line, also listed under its Gemini image names.

    • Nano Banana 2.1Generate, edit
    • Nano Banana 2Generate, edit
    • Nano Banana 2 LiteGenerate, edit
    • Nano Banana ProGenerate, edit
    • Gemini 3 Pro ImageGenerate, edit
    • Gemini 3.1 Flash ImageGenerate, edit
    • Gemini 3.1 Flash Lite ImageGenerate, edit
    • Gemini 3 Pro UpscaleUpscale
    • Gemini 3.1 Flash UpscaleUpscale
  • OpenAI

    5 models

    GPT Image, with a fast Flare tier and a precision Sunburst tier.

    • GPT Image 2.6 FlareGenerate, edit
    • GPT Image 2.6 SunburstGenerate, edit
    • GPT Image 2.5 FlareGenerate, edit
    • GPT Image 2.5 SunburstGenerate, edit
    • GPT Image 2Generate, edit
  • The FLUX family, from hosted flagship tiers to small open-weights models.

    • FLUX 3 ImageGenerate, edit
    • FLUX 3 Image KleinGenerate, edit
    • FLUX.2 MaxGenerate, edit
    • FLUX.2 ProGenerate, edit
    • FLUX.2 FlexGenerate, edit
    • FLUX.2 Klein 4BGenerate
    • FLUX.1 DevGenerate
    • FLUX.1 SchnellGenerate
  • Alibaba

    9 models

    Qwen Image for generation and editing, with strong text rendering, plus the fast Z-Image Turbo.

    • Qwen Image 3Generate, edit
    • Qwen Image 3 ProGenerate, edit
    • Qwen Image 2.1 ProGenerate, edit
    • Qwen Image 2.1 TurboGenerate, edit
    • Qwen Image 2 ProGenerate, edit
    • Qwen-ImageGenerate, open weights
    • Qwen Image LayeredLayered output
    • Qwen Camera ControlCamera edit
    • Z-Image TurboGenerate
  • ByteDance

    9 models

    Seedream for generation and editing, plus upscaling, inpainting, and depth estimation models.

    • Seedream 5.5Generate, edit
    • Seedream 5.0 ProGenerate, edit
    • Seedream 5.0 LiteGenerate, edit
    • Seedream 5.0 FlashGenerate, edit
    • Seedream 4.5Generate, edit
    • SeedVR2 UpscalerUpscale
    • OneRewardInpainting
    • Depth Anything V3Depth estimation
    • Depth Anything V2Depth estimation
  • Recraft

    12 models

    Design-first models with brand colours as an input and real SVG output in the vector variants.

    • Recraft V4.1Generate
    • Recraft V4.1 ProGenerate
    • Recraft V4.1 FlashGenerate
    • Recraft V4.1 UtilityGenerate
    • Recraft V4.1 Utility ProGenerate
    • Recraft V4Generate
    • Recraft V4 ProGenerate
    • Recraft V4 VectorVector
    • Recraft V3Generate, edit
    • Recraft Text to VectorVector
    • Recraft VectorizeVectorize
    • Recraft UpscaleUpscale
  • Ideogram

    6 models

    Built for design and typography, with region editing and SVG output.

    • Ideogram 4.5Generate, edit
    • Ideogram 4.5 Precise EditRegion edit
    • Ideogram 4.0Generate
    • Ideogram VectorVector
    • Ideogram VectorizeVectorize
    • Ideogram Remove BackgroundBackground removal
  • Krea

    5 models

    • Krea 3Generate, edit
    • Krea 2 LargeGenerate
    • Krea 2 MediumGenerate
    • Krea 2 Medium TurboGenerate
    • Krea 2 TurboGenerate
  • xAI

    2 models

    • Grok Imagine 2.0Generate, edit
    • Grok ImagineGenerate
  • Bria

    4 models

    Image models trained on licensed data.

    • Bria FIBO 2.0Generate, edit
    • Bria FIBO 1.5Generate
    • Bria RMBG 2.0Background removal
    • Bria Guided Remove BackgroundBackground removal
  • Microsoft

    2 models

    • MAI-Image-2.5Generate
    • MAI-Image-2.5 ProGenerate, edit
  • Kuaishou

    2 models

    The image models from the Kling line.

    • Kling Image O3Generate, edit
    • Kling Image v3Generate, edit
  • MiniMax

    2 models

    • MiniMax H3 ImageGenerate, edit
    • MiniMax H3 Image HighspeedGenerate, edit
  • Tencent

    1 model

    • Hunyuan Image 3.0 InstructGenerate, edit
  • Baidu

    2 models

    • ERNIE ImageGenerate
    • ERNIE TurboGenerate
  • Meta

    1 model

    • Muse ImageGenerate, edit
  • Luma AI

    1 model

    • Luma Uni-1Generate, edit
  • HiDream.ai

    2 models

    Open-weight image models.

    • HiDream-I1 FullGenerate
    • HiDream-O1Generate, edit
  • Topaz Labs

    2 models

    • Topaz Precision Image UpscaleUpscale
    • Topaz Image UpscaleUpscale
  • Quiver

    2 models

    • Quiver Arrow 1.1Vector
    • Quiver Arrow 1.1 MaxVector
  • OpenMOSS

    1 model

    An open model for text and layout that plans the layout before it draws.

    • MOSS-ImageGenerate
  • ImagineArt

    1 model

    • ImagineArt 1.5 ProGenerate
  • Pruna AI

    1 model

    • P-ImageGenerate
  • Hi3D

    1 model

    • Hitem3D ReliefRelief from an image
  • Pixelcut

    1 model

    • Pixelcut Background RemoverBackground removal
  • Smoretalk

    1 model

    • Rembg EnhanceBackground removal
  • Feyn

    1 model

    • FeyNoBGBackground removal
  • Visioncortex

    1 model

    • Image2SVGVectorize

Language models

Language models read, reason, and write text and code. In a 3D pipeline they write and expand prompts, plan asset lists, and run the AI agents that call generation tools.

  • OpenAI

    7 models

    • GPT-6 AstraLanguage
    • GPT-6 SolLanguage
    • GPT-6 LunaLanguage
    • GPT-6.1 SolLanguage
    • GPT-6.1 TerraLanguage
    • GPT-OSS 120BLanguage, open weights
    • GPT-OSS 20BLanguage, open weights
    • Gemini 4 ArgonLanguage
    • Gemini 3.8 FlashLanguage
    • Gemini 3.5 Flash LiteLanguage
    • Gemini 3.1 Pro PreviewLanguage
    • Gemini 3.1 FlashLanguage
    • Gemini 3.1 Flash LiteLanguage
    • Gemini 3 ProLanguage
  • Anthropic

    6 models

    • Claude Fable 5.2Language
    • Claude Opus 5.5Language
    • Claude Sonnet 5.5Language
    • Claude Haiku 5.5Language
    • Claude Fable 5.1Language
    • Claude Haiku 4.5Language
  • xAI

    2 models

    • Grok 4.7Language
    • Grok Build 0.1Language, coding
  • ByteDance

    3 models

    • Seed 2.1 TurboLanguage
    • Seed 2.0 LiteLanguage
    • Seed 2.0 MiniLanguage
  • DeepSeek

    2 models

    • DeepSeek V4 ProLanguage
    • DeepSeek V4.1 FlashLanguage
  • Z.ai

    1 model

    • GLM 5.3 FlashLanguage

Audio and voice models

Audio models generate speech, music, and sound effects, and transcribe recordings. They give voices to characters and sound to the scenes a 3D team builds.

  • ElevenLabs

    9 models

    • Eleven v4Text to speech
    • Eleven v4 TurboText to speech
    • Eleven v3Text to speech
    • Eleven Flash v2.5Text to speech
    • ElevenLabs Music v2Music
    • ElevenLabs Music v2.5 ExtendMusic
    • ElevenLabs SFX v2Sound effects
    • ElevenLabs Scribe v2Transcription
    • ElevenLabs Voice ChangerVoice conversion
    • Lyria 3.5Music
    • Lyria 3 ClipMusic
    • Gemini 3.8 Flash TTSText to speech
    • Gemini 3.8 Flash-Lite TTSText to speech
    • Gemini 3.1 Flash TTSText to speech
    • Gemini 3.5 TranscribeTranscription
  • MiniMax

    4 models

    • MiniMax Speech 2.8 HDText to speech
    • MiniMax Speech 02Text to speech
    • MiniMax Music 3Music
    • MiniMax Music CoverMusic
  • ByteDance

    3 models

    • Seed TTS 2.0Text to speech
    • Seed Audio 1.0Audio generation
    • Seed ASR 2.0 FlashTranscription
  • HeyGen

    2 models

    • HeyGen VoiceText to speech
    • HeyGen Voice TurboText to speech
  • Sonilo

    2 models

    • Sonilo MusicMusic
    • Sonilo Sound EffectsSound effects
    • Stable Audio 3Music and audio
  • xAI

    1 model

    • Grok TTSText to speech
  • Alibaba

    1 model

    • Qwen Audio 3 TTSText to speech
  • Microsoft

    1 model

    • MAI-Voice 2.1Text to speech
  • Mistral AI

    1 model

    • Voxtral Mini TTS 3.0Text to speech
  • Fish Audio

    1 model

    • Fish Audio Drama 3Text to speech
  • Inworld

    1 model

    • Inworld Realtime TTS 2.0Text to speech
  • AssemblyAI

    1 model

    • AssemblyAI TTS 1Text to speech
  • hexgrad

    1 model

    • KokoroText to speech, open weights
  • Bilibili

    1 model

    • IndexTTS 2.0Text to speech
  • ACE Studio and StepFun

    1 model

    • ACE-StepMusic
  • Mirelo

    1 model

    • Mirelo SFX 2.0Sound effects
  • VEED

    1 model

    • VEED Clean AudioAudio cleanup
  • Kotoba Technologies

    1 model

    • Kotoba STTTranscription

How this directory is compiled

Names and makers come from each maker's public pages and from public model catalogs. We give no scores and no rankings, and the order within a section is not a recommendation.

Models are renamed, replaced, and retired often. Treat each maker's own site as the source of truth, and when you are choosing a 3D generator, test it on your own brief. The buying guide sets out a fair way to run that test.

Questions about AI models

Which AI model does Hydrilla use to generate 3D models?
Hydrilla runs BlueFox, Hydrilla's 3D model, built by Hydrilla AI. The current version is BlueFox 1. It turns a typed prompt or an uploaded image into a mesh split into parts, UV-unwrapped, with PBR maps.
Which AI models can generate a 3D model from text or an image?
3D generation models include BlueFox from Hydrilla AI, Tripo, Meshy, Hunyuan3D and Pixal3D from Tencent, TRELLIS from Microsoft, Rodin from Hyper3D, Hi3D, SAM 3D from Meta, and Direct3D-S2. They differ in whether the mesh arrives with UVs, PBR maps, separate parts, and clean topology.
Are the other models on this page available in Hydrilla?
No. BlueFox is the model that runs in Hydrilla. Every other model here is a reference listing with no partnership, endorsement, or availability implied. Confirm details on each maker's own site.
Which image model should I use to make a reference image for image to 3D?
Any image model that gives you one clear subject on a plain background, evenly lit, will do. Models with reliable editing help when you need to clean up a reference before you spend on 3D. Hydrilla's text-to-3D flow also makes a reference image for you to approve first.
Can a language model generate 3D assets in Hydrilla?
Yes, through an agent. Hydrilla's MCP server lets agents such as Claude Code, Cursor, and Codex generate models and send them into an open Blender, Maya, 3ds Max, Unity, Unreal, or Godot scene. Inside Hydrilla, Hydrilla Agent is the AI 3D agent that builds and changes your Blender scene in chat.
Why does this directory leave out video models?
It covers the model types that feed a 3D asset pipeline: 3D generation and processing, image, language, and audio. Video generation is outside that scope.
What is the difference between a 3D generation model and a 3D processing model?
A 3D generation model creates a new mesh from a text prompt or an image. A 3D processing model works on a mesh that already exists: it retopologizes, unwraps UVs, textures, splits the mesh into parts, rigs, or animates it.
Which AI models can texture, retopologize, or rig a 3D model?
Texturing models include Meshy Texture, Tripo Texture, and Hi3D Texture. Retopology models include Meshy Remesh, Tripo Retopology, and Hunyuan Smart Topology. Rigging models include Meshy Rigging and Tripo Rigging. PATINA from fal generates PBR materials, and Kimodo from NVIDIA generates motion.
Which AI image models are available today?
Image model families include Nano Banana from Google DeepMind, GPT Image from OpenAI, FLUX from Black Forest Labs, Qwen Image from Alibaba, Seedream from ByteDance, Recraft, Ideogram, Krea, Grok Imagine from xAI, and Bria FIBO. Most generate and edit; some specialize in vectors, upscaling, or background removal.
Which language models do AI agents use?
Agents run on language models such as GPT from OpenAI, Gemini from Google DeepMind, Claude from Anthropic, Grok from xAI, DeepSeek, and GLM from Z.ai. The agent picks the tools; the language model does the reasoning and writes the calls.
How current is this list?
The listings reflect November 2026. Model names and versions change quickly, so treat each maker's own site as the source of truth.

Generate your first 3D model with BlueFox

Start from a typed prompt or an uploaded image, check the result in the browser, and export it to the tools you already use.

Listings as of November 2026. Model names and logos belong to their owners and are shown for identification only. No affiliation or endorsement is implied.