---
title: ZIB-FTHLX-v1
canonical_url: "https://www.modelscope.ai/models/Neeshck/ZIB-FTHLX-v1"
md_url: "https://www.modelscope.ai/models/Neeshck/ZIB-FTHLX-v1.md"
repository: Neeshck/ZIB-FTHLX-v1
last_updated: 2026-06-06
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Tongyi-MAI/Z-Image
base_model_relation: adapter
parameters: 793.8M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - safetensors
frameworks:
  - pytorch
supports_inference: txt2img
downloads: 314
stars: 0
tags:
  - LoRA
---

# ZIB-FTHLX-v1

> ZIB-FTHLX-v1 - An open-source model by Neeshck on ModelScope. 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。

Neeshck/ZIB-FTHLX-v1 is a 793.8M-parameter text-to-image-synthesis model on ModelScope. licensed under Apache License 2.0. derived from Tongyi-MAI/Z-Image. and supports online inference (txt2img).

- **Repository**: Neeshck/ZIB-FTHLX-v1
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 793.8M
- **Base model**: Tongyi-MAI/Z-Image
- **Online inference**: txt2img
- **Tags**: LoRA
- **Downloads**: 314
- **Stars**: 0
- **Last updated**: 2026-06-06

Source: https://www.modelscope.ai/models/Neeshck/ZIB-FTHLX-v1

---

# FTHLX

## 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](https://modelscope.cn/models/Tongyi-MAI/Z-Image)
* 训练代码：[DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* 训练数据量：39
* 总训练步数：10000
* 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", origin_file_pattern="transformer/*.safetensors"),
        ModelConfig(model_id="Tongyi-MAI/Z-Image", origin_file_pattern="text_encoder/*.safetensors"),
        ModelConfig(model_id="Tongyi-MAI/Z-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
    ],
    tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image", origin_file_pattern="tokenizer/"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="Neeshck/ZIB-FTHLX-v1", origin_file_pattern="ZIB-FTHLX-v1_c1-st10000.safetensors"))
prompt = "a cat"
image = pipe(prompt=prompt, num_inference_steps=50, cfg_scale=4)
image.save("image.jpg")
```