README.md

metadata

license: apache-2.0
language:
  - en
  - zh
tags:
  - text-to-image
  - diffusers
  - lora
  - flux
base_model:
  - Tongyi-MAI/Z-Image-Turbo
  - ostris/Z-Image-De-Turbo
library_name: diffusers
pipeline_tag: text-to-image

Z-Image-De-Turbo

📦 This repo is mirrored from ostris/Z-Image-De-Turbo, with complete Diffusers format files added.

This is a pre-de-distilled version of Tongyi-MAI/Z-Image-Turbo, optimized for LoRA training.

📌 Why This Model?

Z-Image-Turbo is a distilled model. Training LoRA directly on it results in blurry, low-quality outputs.

Two solutions exist:

1. Use Training Adapter: Load zimage_turbo_training_adapter during training
2. Use Pre-de-distilled Model (this repo): The training adapter is pre-merged, ready for direct training

✅ Advantages

• Ready to use: No need to load additional training adapters
• Diffusers format: Complete directory structure, compatible with various training tools
• Inference: Recommended 25 steps, guidance_scale 3.0

📝 Credits

• Original pre-de-distilled model: ostris/Z-Image-De-Turbo
• Base model: Tongyi-MAI/Z-Image-Turbo
• Training adapter: ostris/zimage_turbo_training_adapter