---
title: Qwen-Image-woodcarving-dailyuse-1b48
canonical_url: "https://www.modelscope.cn/models/diffsynth-i2L-gallery/Qwen-Image-woodcarving-dailyuse-1b48"
md_url: "https://www.modelscope.cn/models/diffsynth-i2L-gallery/Qwen-Image-woodcarving-dailyuse-1b48.md"
repository: diffsynth-i2L-gallery/Qwen-Image-woodcarving-dailyuse-1b48
chinese_name: "木雕、日用品"
last_updated: 2026-04-21
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - "MusePublic/Qwen-image@v1"
base_model_relation: adapter
parameters: 59.0M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - safetensors
supports_inference: txt2img
downloads: 7
stars: 0
tags:
  - LoRA
  - text-to-image
---

# Qwen-Image-woodcarving-dailyuse-1b48

> Qwen-Image-woodcarving-dailyuse-1b48 - diffsynth-i2L-gallery 在 ModelScope 开源的模型。本模型使用 Qwen-Image-i2L 从 1 张图像生成。

diffsynth-i2L-gallery/Qwen-Image-woodcarving-dailyuse-1b48 是 ModelScope 魔搭社区上的 59.0M 参数text-to-image-synthesis模型，采用 Apache License 2.0 许可，基于 MusePublic/Qwen-image@v1 构建，并支持在线推理（txt2img）。

- **Repository**: diffsynth-i2L-gallery/Qwen-Image-woodcarving-dailyuse-1b48
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 59.0M
- **Base model**: MusePublic/Qwen-image@v1
- **Online inference**: txt2img
- **Tags**: LoRA, text-to-image
- **Downloads**: 7
- **Stars**: 0
- **Last updated**: 2026-04-21

Source: https://www.modelscope.cn/models/diffsynth-i2L-gallery/Qwen-Image-woodcarving-dailyuse-1b48

---

# 木雕、日用品

本模型使用 [**Qwen-Image-i2L**](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-i2L) 从 1 张图像生成。

## 安装

```bash
git clone https://github.com/modelscope/DiffSynth-Studio.git  
cd DiffSynth-Studio
pip install -e .
```

## 使用本模型

```python
from modelscope import snapshot_download
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
import torch

vram_config = {
    "offload_dtype": "disk",
    "offload_device": "disk",
    "onload_dtype": torch.bfloat16,
    "onload_device": "cpu",
    "preparing_dtype": torch.bfloat16,
    "preparing_device": "cuda",
    "computation_dtype": torch.bfloat16,
    "computation_device": "cuda",
}
pipe = QwenImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors", **vram_config),
        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", **vram_config),
        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", **vram_config),
    ],
    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
    vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
)
lora_path = snapshot_download(model_id="diffsynth-i2L-gallery/Qwen-Image-woodcarving-dailyuse-1b48")
pipe.load_lora(pipe.dit, f"{lora_path}/model.safetensors")
image = pipe("一把精雕细琢的木质梳子，表面刻有流畅叶脉纹饰与微小汉字印章，暖棕色木纹清晰，置于灰色渐变背景中，3D渲染写实风格", seed=0, height=1024, width=1024, num_inference_steps=50)
image.save("image.jpg")
```


## 相关链接
- i2L 模型：https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-i2L
- 代码仓库：https://github.com/modelscope/DiffSynth-Studio

## License

Apache-2.0