---
title: Moss-Cute12-Klein-1.0
canonical_url: "https://www.modelscope.ai/models/zyyw1022/Moss-Cute12-Klein-1.0"
md_url: "https://www.modelscope.ai/models/zyyw1022/Moss-Cute12-Klein-1.0.md"
repository: zyyw1022/Moss-Cute12-Klein-1.0
last_updated: 2026-10-29
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - openmoss/MOSS-Image-SFT
base_model_relation: adapter
parameters: 466.0M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - safetensors
supports_inference: txt2img
downloads: 58
stars: 0
tags:
  - LoRA
  - text-to-image
---

# Moss-Cute12-Klein-1.0

> Moss-Cute12-Klein-1.0 - An open-source model by zyyw1022 on ModelScope. Moss-Cute12-Klein-1.0

zyyw1022/Moss-Cute12-Klein-1.0 is a 466.0M-parameter text-to-image-synthesis model on ModelScope. licensed under Apache License 2.0. derived from openmoss/MOSS-Image-SFT. and supports online inference (txt2img).

- **Repository**: zyyw1022/Moss-Cute12-Klein-1.0
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 466.0M
- **Base model**: openmoss/MOSS-Image-SFT
- **Online inference**: txt2img
- **Tags**: LoRA, text-to-image
- **Downloads**: 58
- **Stars**: 0
- **Last updated**: 2026-10-29

Source: https://www.modelscope.ai/models/zyyw1022/Moss-Cute12-Klein-1.0

---

# Moss-Cute12-Klein-1.0

## 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：[openmoss/MOSS-Image-SFT](https://modelscope.cn/models/openmoss/MOSS-Image-SFT)
* 训练代码：[DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* 训练数据量：35
* 总训练步数：6000
* 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.moss_image import MOSSImagePipeline, ModelConfig
import torch

pipe = MOSSImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
        ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="text_encoder/model*.safetensors"),
        ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", computation_dtype=torch.float32),
    ],
    tokenizer_config=ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="tokenizer/"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="zyyw1022/Moss-Cute12-Klein-1.0", origin_file_pattern="Moss-Cute12-Klein-1.0_c1-st6000.safetensors"))

prompt = "a cat"
image = pipe(prompt, height=1024, width=1024, seed=0, num_inference_steps=50, cfg_scale=3.0)
image.save("image.jpg")
```