You can deploy this model and start earning money today!

DamianBoborzi/
TRELLIS-image-large_MeshFleet_ft

Name: TRELLIS-image-large_MeshFleet_ft
Availability: InStock

DamianBoborzi/MeshFleet_TRELLIS

microsoft/TRELLIS-image-large

finetune

mit

Views

No views yet

TRELLIS Image-to-3D Finetuned Model

This is a finetuned version of the TRELLIS Image-to-3D generation model. It was finetuned using the MeshFleet dataset.

TRELLIS can generate high-quality 3D assets from single images, producing structured 3D representations including gaussian splatting, radiance fields, and meshes.

Model Description

This finetuned model contains all the necessary components for the TRELLIS Image-to-3D pipeline.

Usage

python

from trellis.pipelines import TrellisImageTo3DPipeline
from PIL import Image

# Load the pipeline
pipeline = TrellisImageTo3DPipeline.from_pretrained("path/to/this/model")
pipeline.cuda()

# Load input image
image = Image.open("path/to/your/image.jpg")

# Generate 3D assets
outputs = pipeline.run(image, seed=42)

# Access different 3D representations
gaussian_splatting = outputs['gaussian'][0]  # Gaussian splatting representation
radiance_field = outputs['radiance_field'][0]  # Radiance field representation
mesh = outputs['mesh'][0]  # Mesh representation

# Save outputs
gaussian_splatting.save("output_gs.ply")
radiance_field.save("output_rf.obj")
mesh.save("output_mesh.obj")

File Format

All model weights are stored in the same SafeTensors format (.safetensors) as the original weights. Configuration files (.json) contain model hyperparameters and architecture details.

Requirements

CUDA-capable GPU with >= 24GB VRAM recommended
TRELLIS library (see the official TRELLIS repository for installation instructions: https://github.com/microsoft/TRELLIS)

License

This model follows the same license as the original TRELLIS model.

DamianBoborzi/TRELLIS-image-large_MeshFleet_ft