---
title: B-74
canonical_url: "https://www.modelscope.cn/models/Z18132644/B-74"
md_url: "https://www.modelscope.cn/models/Z18132644/B-74.md"
repository: Z18132644/B-74
chinese_name: B-74
last_updated: 2026-06-05
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - HiDream-ai/HiDream-O1-Image
base_model_relation: adapter
parameters: 102.7M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - safetensors
frameworks:
  - pytorch
supports_inference: txt2img
downloads: 61
stars: 0
tags:
  - LoRA
---

# B-74

> B-74 - Z18132644 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。

Z18132644/B-74 是 ModelScope 魔搭社区上的 102.7M 参数text-to-image-synthesis模型，采用 Apache License 2.0 许可，基于 HiDream-ai/HiDream-O1-Image 构建，并支持在线推理（txt2img）。

- **Repository**: Z18132644/B-74
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 102.7M
- **Base model**: HiDream-ai/HiDream-O1-Image
- **Online inference**: txt2img
- **Tags**: LoRA
- **Downloads**: 61
- **Stars**: 0
- **Last updated**: 2026-06-05

Source: https://www.modelscope.cn/models/Z18132644/B-74

---

# B-74

## 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：[HiDream-ai/HiDream-O1-Image](https://modelscope.cn/models/HiDream-ai/HiDream-O1-Image)
* 训练代码：[DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* 训练数据量：35
* 总训练步数：2000
* 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.hidream_o1_image import HiDreamO1ImagePipeline, ModelConfig
import torch

pipe = HiDreamO1ImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="HiDream-ai/HiDream-O1-Image", origin_file_pattern="*.safetensors"),
    ],
    processor_config=ModelConfig(model_id="HiDream-ai/HiDream-O1-Image"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="Z18132644/B-74", origin_file_pattern="B-74_c1-st2000.safetensors"))
prompt = "a cat"
image = pipe(prompt=prompt, num_inference_steps=30, cfg_scale=4)
image.save("image.jpg")
```