---
title: hkk260927
canonical_url: "https://www.modelscope.cn/models/hh2357/hkk260927"
md_url: "https://www.modelscope.cn/models/hh2357/hkk260927.md"
repository: hh2357/hkk260927
chinese_name: hkk645987
last_updated: 2026-09-27
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - krea/Krea-2-Turbo
base_model_relation: adapter
parameters: 586.5M
tensor_type:
  - F16
library_name:
  - pytorch
  - lora
  - safetensors
supports_inference: txt2img
downloads: 22
stars: 0
tags:
  - LoRA
  - text-to-image
---

# hkk260927

> hkk260927 - hh2357 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。

hh2357/hkk260927 是 ModelScope 魔搭社区上的 586.5M 参数text-to-image-synthesis模型，采用 Apache License 2.0 许可，基于 krea/Krea-2-Turbo 构建，并支持在线推理（txt2img）。

- **Repository**: hh2357/hkk260927
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 586.5M
- **Base model**: krea/Krea-2-Turbo
- **Online inference**: txt2img
- **Tags**: LoRA, text-to-image
- **Downloads**: 22
- **Stars**: 0
- **Last updated**: 2026-09-27

Source: https://www.modelscope.cn/models/hh2357/hkk260927

---

# hkk645987

## 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：[krea/Krea-2-Turbo](https://modelscope.cn/models/krea/Krea-2-Turbo)
* 训练代码：[DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* 训练数据量：10
* 总训练步数：5000
* 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.krea2 import Krea2Pipeline, ModelConfig
import torch

pipe = Krea2Pipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="krea/Krea-2-Turbo", origin_file_pattern="turbo.safetensors"),
        ModelConfig(model_id="Qwen/Qwen3-VL-4B-Instruct", origin_file_pattern="*.safetensors"),
        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
    ],
    tokenizer_config=ModelConfig(model_id="Qwen/Qwen3-VL-4B-Instruct", origin_file_pattern=""),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="hh2357/hkk260927", origin_file_pattern="hkk260927_c1-st5000.safetensors"))
prompt = "a cat"
image = pipe(
    prompt, seed=0,
    num_inference_steps=8, cfg_scale=1, mu=1.15,
)
image.save("image.jpg")
```