Meshy 7

Meshy 7 — text, image or multi-image to 3D. Wire nothing for text-to-3D, one image for image-to-3D, two or more for multi-image reconstruction; the endpoint is picked automatically. Optional character rigging and animation.

Try Meshy 7 in the playground

Last updated View as MarkdownAgent setup

Meshy 7

Node type: 3d:meshy_v7
Category: 3d
Hidden in sidebar: yes (auto-selected by routing)

Description

Meshy 7 is Meshy's 3D generation model for text, image or multi-image to 3D. Wire nothing for text to 3D, one image for image to 3D, or two or more images for multi-image reconstruction; the node picks the mode automatically. Options include texturing, PBR, quad or triangle topology, a target polycount, and character rigging and animation, which return a rigged GLB or FBX with basic walk and run animations. Its node type is 3d:meshy_v7. Call it from code by running a saved workflow that contains it with POST /api/v1/workflows/{id}/run, or let an agent build and run it over the Wireflow MCP server. It costs about 192 credits per generation; turning texture off costs less, and Ultra Mode, rigging and animation cost more.

Pricing

  • Cost: ~192 credits per generation

Variant family

  • Family: meshy-v7
  • Is primary: yes
  • All variants: 3d:meshy_v7, 3d:meshy_v7_image, 3d:meshy_v7_multi_image

Canvas ports

These appear as port handles on the left side of the node.

ID Label Details
prompt Prompt TEXT (required) · multiline — What to model. Required for text-to-3D; ignored once an image is wired (the node routes to an image endpoint, which takes no prompt).
image1 Image 1 IMAGE — Wire one image for image-to-3D. Add more image inputs (2 or more) and Meshy reconstructs from the whole set — multi-image is a different endpoint and is selected automatically. Leave empty for text-to-3D.
texture_prompt Texture Prompt TEXT

These render as form fields in the right-side config panel when the node is selected.

ID Label Details
should_texture Texture BOOLEAN — Texture the mesh. Off returns untextured geometry and costs less. Applies on every route.
model_type Model Type TEXT · options: standard, lowpoly, smart-topology
ultra_mode Ultra Mode BOOLEAN — Highest-detail generation (costs more).
enable_prompt_expansion Enable Prompt Expansion BOOLEAN
topology Topology TEXT · options: quad, triangle
target_polycount Target Polycount NUMBER · 100…300000
symmetry_mode Symmetry Mode TEXT · options: off, auto, on
enable_pbr Enable PBR BOOLEAN
should_remesh Should Remesh BOOLEAN
pose_mode Pose Mode TEXT · options: a-pose, t-pose, ``
enable_rigging Enable Rigging BOOLEAN — Rig the character for animation (costs extra). Returns a rigged GLB/FBX plus basic walk and run animations.
rigging_height_meters Rigging Height Meters NUMBER
enable_animation Enable Animation BOOLEAN — Apply an animation action to the rigged mesh (costs extra).
animation_action_id Animation Action Id NUMBER

Outputs

ID Label Type
model_mesh 3D Model 3D
thumbnail Thumbnail IMAGE
animation_glb Animation GLB 3D
frame Render IMAGE

Auto-generated from the Wireflow node registry.

For AI agents: the full documentation index is at /llms.txt, and most docs pages are available as Markdown by adding .md to the URL.

© 2026 Wireflow. All rights reserved.