Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.comfy.org/llms.txt

Use this file to discover all available pages before exploring further.

TripoSplat is an open-source model that generates 3D Gaussian splat representations directly from a single 2D image. It was developed by VAST-AI and released under an open-source license. Unlike traditional 3D reconstruction methods that require multiple views or generate meshes as the primary output, TripoSplat creates Gaussian splat representations — a rendering technique where thousands of colored 3D Gaussians are placed in space to represent a scene. This approach enables fast, high-quality rendering with controllable density and budget. TripoSplat workflow
Make sure your ComfyUI is updated.Workflows in this guide can be found in the Workflow Templates. If you can’t find them in the template, your ComfyUI may be outdated. (Desktop version’s update will delay sometime)If nodes are missing when loading a workflow, possible reasons:
  1. You are not using the latest ComfyUI version (Nightly version)
  2. Some nodes failed to import at startup

Download Workflow

Download JSON or search “TripoSplat” in Template Library

​
How it works

TripoSplat uses a feed-forward architecture that takes a single RGB image and directly predicts a set of 3D Gaussian primitives. The pipeline involves:
  1. Image encoding — the input image is processed by a vision encoder (DINOv2)
  2. Triplane generation — features are decoded into a triplane representation
  3. Gaussian prediction — the triplane is sampled to produce Gaussian parameters (position, scale, rotation, opacity, color)
  4. Rendering — Gaussians are rendered from arbitrary viewpoints using differentiable splatting

Learn about Subgraph

This workflow uses a Subgraph node for modular processing. Check out the Subgraph documentation to learn how to customize and extend the workflow.

​
Workflow node guide

​
LoadImage

  • Loads your input image (PNG/JPG)
  • Sample image: white-hotel-on-rocky-island.png (available in Template Library)

​
TripoSplat (subgraph)

The main subgraph node processes the image and generates the 3D Gaussian splat. Exposed parameters:
ParameterDefaultDescription
switch—Enable/disable the subgraph
num_gaussians—Number of Gaussian primitives to generate (controls quality/performance)
seed—Random seed for reproducibility
unet_name—TripoSplat diffusion model checkpoint
clip_name—CLIP vision encoder model
vae_name—VAE for encoding/decoding (2 entries: one for the main VAE, one for the encoder)
bg_removal_name—Background removal model

​
CreateCameraInfo

  • Defines the camera orbit for rendering the result
  • Parameters: orbit type, angle, distance, field of view, etc.
  • Default: orbit at 35° elevation, 30 distance, 2.5 zoom

​
RenderSplat

  • Renders the Gaussian splat into a 2D image from the defined camera angle
  • Parameters: output resolution (default 1024×1024), image quality settings

​
SplatToMesh

  • Converts the Gaussian splat to a mesh (optional)
  • Parameters: mesh density, smoothing, simplification

​
SaveGLB

  • Saves the result as a GLB 3D file

​
SaveVideo

  • Saves a video of the rendered 3D scene

​
SplatToFile3D

  • Exports the Gaussian splat in SPZ format

​
CreateVideo

  • Creates a video from rendered frames

​
Steps to run

  1. Load an image — use the LoadImage node to load a single 2D image
  2. Run the TripoSplat subgraph — the model will generate a Gaussian splat representation
  3. Choose output format — export as GLB, SPZ, video, or render to mesh
  4. View results — use the created 3D file or rendered preview

​
Output options

NodeFormatUse case
SaveGLB.glbStandard 3D file format, importable into 3D software
SplatToFile3D.spzCompressed Gaussian splat format for efficient storage
RenderSplat2D imageQuick preview of the result from any angle
SplatToMeshMeshConvert to traditional mesh for further editing

​
Model downloads

Download the TripoSplat model and required files. Place them in the corresponding models/ subdirectories.

TripoSplat diffusion

triposplat_fp16.safetensors — TripoSplat diffusion model checkpoint

TripoSplat VAE decoder

triposplat_vae_decoder_fp16.safetensors — VAE decoder

Flux2 VAE

flux2-vae.safetensors — Flux.2 VAE for latent encoding

DINOv2 CLIP

dino_v3_vit_h.safetensors — CLIP vision encoder (DINOv2)

BiRefNet bg removal

birefnet.safetensors — Background removal model for preprocessing

​
Model storage location

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 diffusion_models/
│   │      └── triposplat_fp16.safetensors
│   ├── 📂 vae/
│   │      ├── triposplat_vae_decoder_fp16.safetensors
│   │      └── flux2-vae.safetensors
│   ├── 📂 clip_vision/
│   │      └── dino_v3_vit_h.safetensors
│   └── 📂 background_removal/
│          └── birefnet.safetensors