DiTFuse: Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach (Official Weights)

This repository provides the official pretrained weights for DiTFuse. The project code is available on GitHub:

πŸ‘‰ GitHub: https://github.com/Henry-Lee-real/DiTFuse

DiTFuse supports multiple fusion tasksβ€”including infrared–visible fusion, multi-focus fusion, multi-exposure fusion, and instruction-driven controllable fusion / segmentationβ€”all within a single unified model.


πŸ“Œ Available Model Versions

πŸ”Ή V1 β€” Stronger Zero-Shot Generalization

  • Designed with better zero-shot fusion capability.
  • Performs robustly on unseen fusion scenarios.
  • Recommended if your use case emphasizes cross-dataset generalization.

πŸ”Ή V2 β€” Full Capability Version (Paper Model)

  • This is the main model used in the DiTFuse paper.

  • Provides the most comprehensive capabilities:

    • Full instruction-following control
    • Joint fusion + segmentation
    • Better fidelity and controllability
    • Stronger alignment with text prompts
  • Recommended for research reproduction, benchmarking, and controllable image fusion tasks.

Downloads last month
26
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support