WaveSpeed.ai
Beranda/Jelajahi/3D Creation/hyper3d/rodin-v2/image-to-3d
image-to-3d

image-to-3d

Hyper3D Rodin v2

hyper3d/rodin-v2/image-to-3d

Hyper3D Rodin v2 turns a single image into production-ready 3D assets with clean topology, UVs and textures. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Input

Hint: You can drag and drop a file or click to upload

preview
Control the generation result to T/A Pose.
Used when processing the image.
Provided in the download list.

Idle

Permintaan Anda akan membutuhkan $0.3 per run.

Untuk $10 Anda dapat menjalankan model ini sekitar 33 kali.

ContohLihat semua

README

Hyper3D-Rodin-Gen-2 — Text / Image to 3D

Hyper3D-Rodin-Gen-2 is Hyper3D’s commercial 3D generation system that turns text prompts or 2D images into production-ready 3D assets with UVs and textures. It targets game art, film/TV, XR, product visualisation and even 3D printing workflows.

🔧 What it does

  • Text-to-3D & Image-to-3D in one model Enter a prompt, upload one or more images, or combine both. Multi-view images help reconstruct more accurate shapes.

  • Geometry + textures, ready for DCC / engines Outputs UV-unwrapped meshes plus PBR or shaded textures for use in Unity, Unreal, Blender, Maya, 3D printing pipelines, etc.

  • Topology & resolution control Choose between quad meshes (good for sculpting / rigging) or triangle meshes (game-ready), and pick an approximate polycount tier.

  • Geometric & pose control Optional bounding-box constraints and T/A-pose enforcement help keep characters and props within expected proportions and ready for rigging.

🧩 Parameters

1. Core inputs

  • prompt Natural-language description of the object (shape, style, material, usage).

  • images* One or more reference images (front / side / 3-view / concept art).

    • With only text → Text-to-3D
    • With images (and optional text) → Image-to-3D / guided Text-to-3D
  • material Rendering/material mode for textures:

    • PBR – Physically-based maps (albedo, normal, roughness, metallic, etc.).
    • Shaded – Baked / stylised look.
    • All – Export both PBR and shaded variants.

2. Quality & mesh settings

  • quality_and_mesh Controls mesh type and target polycount:

    • 4k_Quad, 8k_Quad, 18k_Quad, 50k_Quad → Quad-dominant topology at roughly 4k / 8k / 18k / 50k faces. Best for character work, sculpting, retopology and rigging.

    • 2K_Triangle, 20K_Triangle, 250K_Triangle, 500K_Triangle → Triangle meshes at increasing density. Good for game engines, previs, or high-detail props.

    Higher tiers give more detail but larger file sizes and longer generation time.

  • addons Optional enhancement packs. Currently:

    • HighPack – Increases mesh and texture fidelity (higher polycount / resolution) for final-quality assets.

3. Output format

  • geometry_file_format Choose which 3D file you want back:

    • glb – Compact, modern, web-friendly (recommended default).
    • fbx – Widely used for DCC and game engines.
    • obj – Simple geometry + MTL, highly compatible.
    • stl – For 3D printing workflows.
    • usdz – Apple-friendly AR format.

4. Advanced geometric control

  • bbox_condition A ControlNet-style bounding box that limits the maximum size of the generated model (width / height / depth). Useful when you need consistent scaling across a whole asset library.

  • TAPose When enabled, forces humanoid characters into a T-pose / A-pose for easier rigging and animation downstream.

  • use_original_alpha If your input image has transparency, this option lets the model respect the original alpha silhouette during generation (handy for cut-out product shots or stylised characters).

  • preview_render Adds a quick preview render (e.g., turntable / shaded view) to the download bundle so you can inspect the result without opening a DCC tool.

5. Randomness & reproducibility

  • seed Random seed for generation:

    • Leave empty / default → random each time.
    • Set to a fixed integer → reproduce the same model configuration (useful for iteration with small prompt tweaks).

🚀 Typical workflow

  1. Decide on input mode

    • For concepting: start with prompt only.
    • For fidelity: upload one or more reference images and optionally add a short prompt.
  2. Pick material & mesh quality

    • PBR + 8k_Quad or 18k_Quad for game/film characters.
    • PBR + 20K_Triangle for background props.
    • Add HighPack when you’re close to final asset quality.
  3. Set geometry_file_format to match your pipeline (e.g., glb for web, fbx for DCC, stl for printing).

  4. (Optional) Add bbox_condition, enable TAPose for characters, and toggle use_original_alpha if your reference image uses transparency.

  5. (Optional) Turn on preview_render to get a ready-to-view render in the output zip.

  6. Set a seed if you want to be able to regenerate or slightly tweak the same base model.

  7. Click Run — once the job finishes, download the mesh + textures bundle and import into your DCC, engine, or 3D-printing tool.

Price

  • Per genration cost $0.3.

💡 Tips

  • Use clean, centered references with good lighting for image-to-3D. Multi-view images greatly improve shape accuracy.
  • Start with medium polycount tiers (8k_Quad, 20K_Triangle) for fast iteration, then switch to higher tiers + HighPack for final export.
  • For rigged characters, combine TAPose + quad meshes and export as fbx or glb.
  • If scale consistency matters across a project, define a shared bbox_condition and reuse it for all related assets.

Mode 3D Models

  • tripo3d/v2.5/image-to-3d Tripo3D’s v2.5 image-to-3D model turns a single product or concept image into a textured, game-ready 3D asset for e-commerce, AR/VR and real-time engines.

  • tripo3d/v2.5/multiview-to-3d Tripo3D’s multi-view 3D reconstruction model uses several photos of the same object to generate higher-fidelity meshes and textures for digital twins and 3D catalogs.

  • hunyuan3d/v2.1 Tencent Hunyuan3D v2.1 (hosted by WaveSpeedAI) converts text prompts into detailed 3D models, ideal for stylised characters, props and environment assets in games and animation.

  • hunyuan3d-v2-multi-view Tencent Hunyuan3D v2 multi-view leverages multiple reference images to create accurate, textured 3D assets for digital humans, product visualization and virtual production workflows.