Photo to geometry maps
Upload one perspective photo to produce two geometry-map images from a shared MoGe-2 estimate. For a first run, upload your image, keep the defaults, and run the Pipe. The first image shows OpenGL normals and the second shows DirectX normals, with inference detail set to 9, automatic camera field of view, and invalid-region filtering enabled.
Workflow details
Workflow details
Runtime profile
- Publisher
- Sweet Tea Automation
- Status
- Listed
- Version
- Checking published version…
- Updated
- Oct 25, 2026
Hover nodes for Pipe controls
Core
Primary Pipe surface
Source image
LoadImage
First geometry map
MoGeRender
Second geometry map
MoGeRender
Extended
Additional surfaced controls
Geometry estimation
MoGeInference
Input resizing
ComfySwitchNode
What you need
Hardware and download-size estimates are not available yet.
Outputs
- First geometry map · image
- Second geometry map · image
Requirements
Models
1moge_2_vitl_normal_fp16.safetensors
File unverifiedCheckpoint · Hugging Face · Comfy-Org/MoGe
Node packs
1Node pack · GitHub · tea-time-labs/sweet-tea-nodes
Sources
1 source
Sources
1 source