TripoSplat Image to Gaussian Splat ComfyUI Workflow Example

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

Portable or self deployed users
Desktop or Cloud users

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 If you can’t find them in the template, your ComfyUI may be outdated.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:

You are not using the latest ComfyUI version (Nightly version)
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:

Image encoding — the input image is processed by a vision encoder (DINOv2)
Triplane generation — features are decoded into a triplane representation
Gaussian prediction — the triplane is sampled to produce Gaussian parameters (position, scale, rotation, opacity, color)
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:

Parameter	Default	Description
`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

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

Output options

Node	Format	Use case
SaveGLB	`.glb`	Standard 3D file format, importable into 3D software
SplatToFile3D	`.spz`	Compressed Gaussian splat format for efficient storage
RenderSplat	2D image	Quick preview of the result from any angle
SplatToMesh	Mesh	Convert 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

Download Workflow

​How it works

Learn about Subgraph

​Workflow node guide

​LoadImage

​TripoSplat (subgraph)

​CreateCameraInfo

​RenderSplat

​SplatToMesh

​SaveGLB

​SaveVideo

​SplatToFile3D

​CreateVideo

​Steps to run

​Output options

​Model downloads