Rodin Gen-2.5

https://mcp.app.layer.ai/mcp

execute_forge({
  "base_model_id": "rodin-gen-2-5",
  "prompt": "A wooden treasure chest with iron bands, game-ready",
  "batch_size": 1
})

# Start the generation — returns an inference id straight away.
curl -X POST https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/base-models/hyper3d-rodin-gen-2-5/inferences \
  -H "Authorization: Bearer $LAYER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": "A wooden treasure chest with iron bands, game-ready"
      }'

# Poll until status is "complete" — the response then carries the asset URLs.
curl https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/inferences/$INFERENCE_ID \
  -H "Authorization: Bearer $LAYER_TOKEN"

prompt

string

Describe what to generate, or the change to make.

quality

enumdefault HIGH5 options

Higher levels render more detail, and can take longer and cost more.

seed

integer

The starting point for the model's randomness. The same seed and settings give the same result.

face_limit

integerdefault 500000500–2000000

The maximum number of faces in the output mesh.

quad_mesh

boolean

Build the mesh from four-sided faces, which are easier to edit and rig than triangles.

include_textures

booleandefault true

Paint colour onto the mesh. Off returns bare geometry.

pbr_materials

booleandefault false

Add metalness, roughness and normal maps so the model reacts to light in a game engine.

pose_mode

enumdefault NONENONE, T_POSE

The pose a character is built in. An A-pose or T-pose is easier to rig.

guidance_file_init_image

file[]

The image the 3D model is built from

prompt_language

string

The language the prompt is written in, so it reaches the model as you meant it.