---
title: LiudefXB_ZIMAGE_TURBO_FP8
canonical_url: "https://www.modelscope.ai/models/moonawm/LiudefXB_ZIMAGE_TURBO_FP8"
md_url: "https://www.modelscope.ai/models/moonawm/LiudefXB_ZIMAGE_TURBO_FP8.md"
repository: moonawm/LiudefXB_ZIMAGE_TURBO_FP8
last_updated: 2026-10-19
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Qwen/Qwen-Image-2.1
base_model_relation: adapter
parameters: 880.8M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - safetensors
supports_inference: img2img
downloads: 134
stars: 0
tags:
  - LoRA
  - text-to-image
---

# LiudefXB_ZIMAGE_TURBO_FP8

> LiudefXB_ZIMAGE_TURBO_FP8 - An open-source model by moonawm on ModelScope. This model is trained using the Civision/model training environment and computing resources provided by ModelScope.

moonawm/LiudefXB_ZIMAGE_TURBO_FP8 is a 880.8M-parameter text-to-image-synthesis model on ModelScope. licensed under Apache License 2.0. derived from Qwen/Qwen-Image-2.1. and supports online inference (img2img).

- **Repository**: moonawm/LiudefXB_ZIMAGE_TURBO_FP8
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 880.8M
- **Base model**: Qwen/Qwen-Image-2.1
- **Online inference**: img2img
- **Tags**: LoRA, text-to-image
- **Downloads**: 134
- **Stars**: 0
- **Last updated**: 2026-10-19

Source: https://www.modelscope.ai/models/moonawm/LiudefXB_ZIMAGE_TURBO_FP8

---

# 

## Model Introduction

This model is trained using the [Civision/model training](https://modelscope.ai/civision/modelTraining) environment and computing resources provided by ModelScope.

* Model Type: LoRA
* Base Model: [Qwen/Qwen-Image-2.1](https://modelscope.ai/models/Qwen/Qwen-Image-2.1)
* Training Code: [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* Data amount：12
* Total training steps：7000
* License: Apache-2.0

## Inference Code

Install [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio):

```bash
pip install diffsynth
```

Inference:

```python
from diffsynth.pipelines.qwen_image_21 import QwenImage21Pipeline, ModelConfig
import torch

pipe = QwenImage21Pipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="Qwen/Qwen-Image-2.1", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
        ModelConfig(model_id="Qwen/Qwen-Image-2.1", origin_file_pattern="text_encoder/model*.safetensors"),
        ModelConfig(model_id="Qwen/Qwen-Image-2.1", origin_file_pattern="vae/diffusion_pytorch_model*.safetensors"),
    ],
    processor_config=ModelConfig(model_id="Qwen/Qwen-Image-2.1", origin_file_pattern="processor/"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="moonawm/LiudefXB_ZIMAGE_TURBO_FP8", origin_file_pattern="LiudefXB_ZIMAGE_TURBO_FP8_c2-st7000.safetensors"))

prompt = "a cat"
image = pipe(prompt, seed=0, num_inference_steps=50)
image.save("image.png")
```