
# 偶映-顾盼生辉-rh1-moss-sft

## 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：300
* 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.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="orangeHong/allin-gpsh-rh1-moss-sft", origin_file_pattern="allin-gpsh-rh1-moss-sft_c1-st10000.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")
```


orangeHong/allin-gpsh-rh1-moss-sft

allin-gpsh-rh1-moss-sft_c1-st8000.safetensors

c1-st8000

c1-st10000

c1-st9000

c1-st7000

c1-st6000

c1-st5000

c1-st4000

c1-st3000

c1-st2000

c1-st1000

Files with SHA256: 6503d33ec51216adfe449b27bdac333f649c65bfe31e00474bfd24352cab0125