Fuko Diffusion

Overview

This repository contains an optimised ONNX version of an SDXL-based model, prepared for efficient inference.

Modifications

  • LoRA ProomptEngineer/pe-funko-pop-diffusion-style has been merged into the base SDXL model
  • The two original text encoders have been merged into a single combined text encoder
  • UNet has been converted to FP16 precision for improved performance and reduced memory usage
  • VAE has been optimised for CUDA execution

Conversion

The model was exported to ONNX using the included export_to_onnx.py script. This script demonstrates the full conversion pipeline and can be used to reproduce or adapt the process.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for r0r-5chach/funko-diffusion