SandBase is live — $1 in free credits on signupStart free ›
Start building
Use in agentMeshy models

Meshy modelsimage generation api

meshy/meshy-v6/multi-image-to-3d

Meshy V6 Multi Image To 3d by Meshy - convert 2D images into 3D models with AI. Generate textured 3D assets from single photos for games, AR/VR, e-commerce, and digital content creation.

Input

PNG, JPEG, WebP, or GIF · 20 MiB maximum each

1 to 4 images for 3D model creation. All images should depict the same object from different angles. Supports .jpg, .jpeg, .png formats, and AVIF/HEIF which will be automatically converted. If more than 4 images are provided, only the first 4 will be used.
Automatically rig the generated model as a humanoid character. Includes basic walking and running animations. Best results with humanoid characters that have clearly defined limbs.
Specify the topology of the generated model. Quad for smooth surfaces, Triangle for detailed geometry. Allowed values: quad, triangle.
Whether to generate textures. False provides mesh without textures for 5 credits, True adds texture generation for additional 10 credits.
Whether to enable the remesh phase. When false, returns triangular mesh ignoring topology and target_polycount.
Animation preset ID from Meshy's library (500+ presets). Only used when enable_animation is true. See https://docs.meshy.ai/en/api/animation-library for available action IDs.
Text prompt to guide the texturing process. Requires should_texture to be true.
100300000
Target number of polygons in the generated model Range: 100 to 300000.
Deprecated: use pose_mode instead. When true, generates a T-pose model.
Approximate height of the character in meters. Only used when enable_rigging is true.
Controls symmetry behavior during model generation. Allowed values: off, auto, on.

PNG, JPEG, WebP, or GIF · 20 MiB maximum

2D image to guide the texturing process. Requires should_texture to be true.
Apply an animation preset to the rigged model. Requires enable_rigging to be true.
Pose mode for the generated model. 'a-pose' generates an A-pose, 't-pose' generates a T-pose, empty string for no specific pose. Allowed values: a-pose, t-pose, .
Generate PBR Maps (metallic, roughness, normal) in addition to base color. Requires should_texture to be true.
Idle

Example output — click Run to generate your own

API README

Meshy 6 - Multi Image To 3D

Meshy 6 - Multi Image To 3D is a Meshy route built for multi-view image-to-3D reconstruction. It turns several complementary object views into a textured 3D asset whose geometry is constrained by multiple angles, giving creators a focused endpoint instead of forcing one generic workflow across materially different production tasks. The route belongs to a family known for production-oriented 3D creation, editable assets, and fast iteration, so it is best evaluated as a creative system for intentional shots and assets rather than as a one-click novelty generator.

Use this endpoint when the input contract and deliverable match that job exactly. Its documented controls include topology choices (quad, triangle); pose_mode choices (a-pose, t-pose, ); enable_pbr (Generate PBR Maps (metallic, roughness, normal) in addition to base color. Requires should_texture to be true); is_a_t_pose (Deprecated: use pose_mode instead. When true, generates a T-pose model). Together, these controls help teams plan predictable iterations, compare outputs under stable settings, and connect generation to game, product, visualization, and spatial-content pipelines without hiding the operational choices that shape the result.

Highlights

  • Meshy 6 - Multi Image To 3D: dedicated multi-view reconstruction. This exact route centers on multi-view reconstruction; it uses the schema-defined source fields to separate its job from neighboring endpoints in the same family.
  • images control. 1 to 4 images for 3D model creation. All images should depict the same object from different angles. Supports .jpg, .jpeg, .png formats, and AVIF/HEIF which will be automatically converted. If more than 4 images are provided, only the first 4 will be used; this setting provides a concrete lever for route-specific output planning.
  • topology control. options quad, triangle; use it to build controlled comparisons without changing the rest of the request.
  • pose_mode control. options a-pose, t-pose, ``; together with the other documented fields, it supports repeatable review of this model path.

Pricing

ConfigurationPrice
Standard request$0.800000

When to Use

ScenarioWhy this model fits
Create the exact route outputChoose it when you need multi-view image-to-3D reconstruction and already have several complementary object views.
Develop controlled variationsKeep the main brief fixed while changing one documented setting at a time to compare motion, framing, quality, or asset behavior.
Build repeatable batchesUse a consistent request shape for catalog, campaign, storyboard, game-asset, or social-content production.
Preserve source intentPrefer this route when the supplied reference material must remain the foundation of a textured 3D asset whose geometry is constrained by multiple angles.
Connect a media pipelineUse asynchronous results in an automated review, approval, post-production, or asset-management workflow.

Prompt Guide

Start with the desired result, then describe the source relationship, subject action, composition or camera behavior, lighting, style, and timing. For multi-view image-to-3D reconstruction, state what must remain stable as clearly as what should change. Use only fields exposed by the schema; the example below is structurally valid for this route.

{
  "images": [
    "https://static.sandbase.ai/examples/meshy/meshy-v6/multi-image-to-3d/input_images_0.png",
    "https://static.sandbase.ai/examples/meshy/meshy-v6/multi-image-to-3d/input_images_1.png",
    "https://static.sandbase.ai/examples/meshy/meshy-v6/multi-image-to-3d/input_images_2.png"
  ],
  "topology": "triangle",
  "pose_mode": "",
  "enable_pbr": false,
  "is_a_t_pose": false
}

Technical Specs

SpecificationValue
Model IDmeshy/meshy-v6/multi-image-to-3d
WorkflowMulti-view image-to-3d reconstruction
Required inputsNo fields marked required by schema
imagesarray
topologystring; options: quad, triangle
pose_modestring; options: a-pose, t-pose, ``
enable_pbrboolean
is_a_t_poseboolean
should_remeshboolean
symmetry_modestring; options: off, auto, on
enable_riggingboolean
should_textureboolean
texture_promptstring

Related Models

Related Models

meshy/meshy-v6Meshy V6 by Meshy - convert 2D images into 3D models with AI. Generate textured 3D assets from single photos for games, AR/VR, e-commerce, and digital content creation.meshy/meshy-v6/text-to-3dMeshy V6 is Meshy's text-to-3D AI model. Turn written descriptions into textured 3D objects with realistic geometry and materials.meshy/meshy-v6-preview/text-to-3dMeshy V6 Preview is Meshy's text-to-3D AI model. Turn written descriptions into textured 3D objects with realistic geometry and materials.meshy/meshy-v6-previewMeshy V6 Preview by Meshy - convert 2D images into 3D models with AI. Generate textured 3D assets from single photos for games, AR/VR, e-commerce, and digital content creation.meshy/meshy/v5/multi-image-to-3dMeshy V5 Multi Image To 3d by Meshy - convert 2D images into 3D models with AI. Generate textured 3D assets from single photos for games, AR/VR, e-commerce, and digital content creation.meshy/meshy/v5/remeshMeshy V5 Remesh by Meshy - advanced AI model for 3d-to-3d. Delivers high-quality results with fast inference, suitable for both creative and production workflows.meshy/meshy/v5/retextureMeshy V5 Retexture by Meshy - advanced AI model for 3d-to-3d. Delivers high-quality results with fast inference, suitable for both creative and production workflows.meshy/riggingRigging by Meshy - advanced AI model for 3d-to-3d. Delivers high-quality results with fast inference, suitable for both creative and production workflows.