---
title: Qwen_Commercial_Food
canonical_url: "https://www.modelscope.ai/models/nescampos/Qwen_Commercial_Food"
md_url: "https://www.modelscope.ai/models/nescampos/Qwen_Commercial_Food.md"
repository: nescampos/Qwen_Commercial_Food
last_updated: 2026-02-10
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: 471.9M
tensor_type:
  - BF16
library_name:
  - lora
  - safetensors
  - pytorch
frameworks:
  - pytorch
supports_inference: txt2img
downloads: 35
stars: 0
tags:
  - LoRA
  - text-to-image
---

# Qwen_Commercial_Food

> Qwen_Commercial_Food - An open-source model by nescampos on ModelScope. QwenCommercialFood is a model created from Qwen-Image using LoRA You can access the model files in the "Files and versions" tab.

nescampos/Qwen_Commercial_Food is a 471.9M-parameter text-to-image-synthesis model on ModelScope. licensed under Apache License 2.0. derived from MusePublic/Qwen-image@v1. and supports online inference (txt2img).

- **Repository**: nescampos/Qwen_Commercial_Food
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 471.9M
- **Base model**: MusePublic/Qwen-image@v1
- **Online inference**: txt2img
- **Tags**: LoRA, text-to-image
- **Downloads**: 35
- **Stars**: 0
- **Last updated**: 2026-02-10

Source: https://www.modelscope.ai/models/nescampos/Qwen_Commercial_Food

---

### Qwen_Commercial_Food is a model created from Qwen-Image using LoRA
#### You can access the model files in the "Files and versions" tab.

#### Why adapt the model?
This model, based on Qwen-Image and adapted with LoRA, is focused on obtaining very high quality images of food dishes, which can be very useful for example in delivery apps (to show images of the products offered) and restaurants (instead of having to hire photographers for high-precision images), since these types of businesses may have constantly changing menus and taking photos all the time is not valuable.


#### How use it 

##### With ModelScope SDK

Download with ModelScope’s Python SDK
```bash
#Install ModelScope
pip install modelscope
```
```python
#Download with ModelScope’s Python SDK
from modelscope import snapshot_download
model_dir = snapshot_download('nescampos/Qwen_Commercial_Food')
```

##### Direct from API Inference

```python
import requests
import time
import json
from PIL import Image
from io import BytesIO

base_url = 'https://api-inference.modelscope.ai/'
api_key = "<MODELSCOPE_TOKEN>" # ModelScope Token

common_headers = {
    "Authorization": f"Bearer {api_key}",
    "Content-Type": "application/json",
}

response = requests.post(
    f"{base_url}v1/images/generations",
    headers={**common_headers, "X-ModelScope-Async-Mode": "true"},
    data=json.dumps({
        "model": "nescampos/Qwen_Commercial_Food", # ModelScope Model-Id, required
        "prompt": "A steaming hot vegetable soup in a rustic ceramic bowl, with a small glass of clear water and a bread basket filled with several slices of freshly baked bread. The soup is rich and colorful, with visible chunks of various vegetables such as carrots, potatoes, and green beans. The glass of water is placed next to the bowl, adding a refreshing touch. The bread basket, made of woven wicker, sits on the table, holding several slices of crusty, golden-brown bread. The table is set with a simple, clean white tablecloth, and the background is a cozy, warmly lit kitchen, enhancing the inviting and comforting atmosphere. The overall style is realistic, with attention to detail and a focus on the textures and colors of the food."
    }, ensure_ascii=False).encode('utf-8')
)

response.raise_for_status()
task_id = response.json()["task_id"]

while True:
    result = requests.get(
        f"{base_url}v1/tasks/{task_id}",
        headers={**common_headers, "X-ModelScope-Task-Type": "image_generation"},
    )
    result.raise_for_status()
    data = result.json()

    if data["task_status"] == "SUCCEED":
        image = Image.open(BytesIO(requests.get(data["output_images"][0]).content))
        image.save("result_image.jpg")
        break
    elif data["task_status"] == "FAILED":
        print("Image Generation Failed.")
        break

    time.sleep(5)
```


##### Download with Git clone
```
git clone https://www.modelscope.ai/nescampos/Qwen_Commercial_Food.git
```

<p style="color: lightgrey;">If you are a contributor to this model, we invite you to promptly update the model card content according to <a href="https://www.modelscope.ai/docs/contribute/model-integration" style="color: lightgrey; text-decoration: underline;">the model contribution documentation</a>.</p>