---
title: fbb4
canonical_url: "https://www.modelscope.cn/models/NICCCCCC/fbb4"
md_url: "https://www.modelscope.cn/models/NICCCCCC/fbb4.md"
repository: NICCCCCC/fbb4
chinese_name: fbb
last_updated: 2026-07-19
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Tongyi-MAI/Z-Image-Turbo
base_model_relation: adapter
parameters: 635.0M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - safetensors
frameworks:
  - pytorch
supports_inference: txt2img
downloads: 42
stars: 2
tags:
  - LoRA
  - text-to-image
---

# fbb4

> fbb4 - NICCCCCC 在 ModelScope 开源的模型。本模型依托魔搭社区（ModelScope）AIGC专区模型训练环境与算力完成训练。

NICCCCCC/fbb4 是 ModelScope 魔搭社区上的 635.0M 参数text-to-image-synthesis模型，采用 Apache License 2.0 许可，基于 Tongyi-MAI/Z-Image-Turbo 构建，并支持在线推理（txt2img）。

- **Repository**: NICCCCCC/fbb4
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 635.0M
- **Base model**: Tongyi-MAI/Z-Image-Turbo
- **Online inference**: txt2img
- **Tags**: LoRA, text-to-image
- **Downloads**: 42
- **Stars**: 2
- **Last updated**: 2026-07-19

Source: https://www.modelscope.cn/models/NICCCCCC/fbb4

---

# fbb

## 模型介绍

本模型依托魔搭社区（ModelScope）AIGC专区[模型训练](https://modelscope.cn/aigc/modelTraining)环境与算力完成训练。

* 模型类型：LoRA
* 基础模型：[Tongyi-MAI/Z-Image-Turbo](https://modelscope.cn/models/Tongyi-MAI/Z-Image-Turbo)
* 训练代码：[DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* 训练数据量：28
* 总训练步数：8000
* 开源协议：Apache-2.0

## 推理代码

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

```bash
pip install diffsynth
```

开始推理：

```python
from diffsynth.pipelines.z_image import ZImagePipeline, ModelConfig
import torch

pipe = ZImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="transformer/*.safetensors"),
        ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="text_encoder/*.safetensors"),
        ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
    ],
    tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="tokenizer/"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="NICCCCCC/fbb4", origin_file_pattern="fbb4_c1-st8000.safetensors"))
prompt = "a cat"
image = pipe(prompt=prompt, num_inference_steps=8, cfg_scale=1)
image.save("image.jpg")
```