---
title: vintedois-diffusion-v0-1
canonical_url: "https://www.modelscope.cn/models/dienstag/vintedois-diffusion-v0-1"
md_url: "https://www.modelscope.cn/models/dienstag/vintedois-diffusion-v0-1.md"
repository: dienstag/vintedois-diffusion-v0-1
last_updated: 2023-02-15
license: creativeml-openrail-m
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
library_name:
  - pytorch
frameworks:
  - pytorch
downloads: 212
stars: 6
tags:
  - "text2image generation"
  - "stablediffusion model"
  - "stable diffusion"
  - "文到图"
  - "文生图"
  - "生成"
  - "图片生成"
  - "生成图片"
  - "ai作画"
  - "作画ai"
  - "作画"
---

# vintedois-diffusion-v0-1

> vintedois-diffusion-v0-1 - dienstag 在 ModelScope 开源的模型。无需复杂繁长的prompt即可生成高质量图像

dienstag/vintedois-diffusion-v0-1 是 ModelScope 魔搭社区上的text-to-image-synthesis模型，采用 creativeml-openrail-m 许可。

- **Repository**: dienstag/vintedois-diffusion-v0-1
- **License**: creativeml-openrail-m
- **Tasks**: text-to-image-synthesis
- **Tags**: text2image generation, stablediffusion model, stable diffusion, 文到图, 文生图, 生成, 图片生成, 生成图片, ai作画, 作画ai, 作画
- **Downloads**: 212
- **Stars**: 6
- **Last updated**: 2023-02-15

Source: https://www.modelscope.cn/models/dienstag/vintedois-diffusion-v0-1

---

###  Vintedois (22h) Diffusion 由 [Predogl](https://twitter.com/Predogl) 和 [piEsposito](https://twitter.com/piesposi_to) 利用开源的模型权重、配置文件、prompts训练而来。

该模型在大量高质量图像上训练，只需要简单的prompt就可以生成优质的图像，而不需要大量的prompt调试。

如果生成图像质量不够好，你可以在prompt开头加入`estilovintedois`关键词。

**你可以商业上使用这个模型，但产生的后果我们不负责任。**


### Model card

模型由 [Stable Diffusion v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5)微调而来。由于改模型由两个独立开发者，构建，因此没能充分测试模型偏见。

利用`diffusers`进行模型finetune的示例见[Colab Notebook for Inference](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_inference.ipynb).

### 样例图像

![](joined.png)

### 使用方式
```python
from modelscope.utils.constant import Tasks
from modelscope.pipelines import pipeline
import cv2

pipe = pipeline(task=Tasks.text_to_image_synthesis, 
                model='dienstag/vintedois-diffusion-v0-1',
                model_revision='v0.1')

prompt = 'kneeling cat knight, portrait, finely detailed armor, intricate design, silver, silk, cinematic lighting, 4k'
output = pipe({'text': prompt})
cv2.imwrite('result.png', output['output_imgs'][0])
```

### 样例 prompts

- Prompt: photo of an old man in a jungle, looking at the camera
- CFG Scale: 7.5
- Scheduler: `diffusers.EulerAncestralDiscreteScheduler`
- Steps: 30
- Seed: 44
![](44-euler-a-photo%20of%20an%20old%20man%20in%20a%20jungle%2C%20looking%20at%C2%A0the%C2%A0camera.png)

- Prompt: kneeling cat knight, portrait, finely detailed armor, intricate design, silver, silk, cinematic lighting, 4k
- CFG Scale: 7.5
- Scheduler: `diffusers.EulerAncestralDiscreteScheduler`
- Steps: 50
- Seed: 44
![](44-euler-a-kneeling%20cat%20knight%2C%20portrait%2C%20finely%20detailed%20armor%2C%20intricate%20design%2C%20silver%2C%20silk%2C%20cinematic%20lighting%2C%204k.png)


- Prompt: a beautiful girl In front of the cabin, the country, by Artgerm Lau and Krenz Cushart，hyperdetailed, trending on artstation, trending on deviantart
- CFG Scale: 7.5
- Scheduler: `diffusers.EulerAncestralDiscreteScheduler`
- Steps: 50
- Seed: 44
![](44-euler-a-a%20beautiful%20girl%20In%20front%20of%20the%20cabin%2C%20the%20country%2C%20by%20Artgerm%20Lau%20and%20Krenz%20Cushart%EF%BC%8Chyperdetailed%2C%20trending%20on%20artstation%2C%20tre.png)

- Prompt: destroyed city
- CFG Scale: 7.5
- Scheduler: `diffusers.EulerAncestralDiscreteScheduler`
- Steps: 50
- Seed: 44
![](44-euler-a-destroyed%20city.png)

- Prompt: victorian city landscape
- CFG Scale: 7.5
- Scheduler: `diffusers.EulerAncestralDiscreteScheduler`
- Steps: 50
- Seed: 44
![](44-euler-a-victorian%20city%20landscape.png)

- Prompt: prehistoric native living room
- CFG Scale: 7.5
- Scheduler: `diffusers.EulerAncestralDiscreteScheduler`
- Steps: 50
- Seed: 44
![](44-euler-a-prehistoric%20native%20living%20room.png)

感谢Google Developer Expert计划为我们提供GCP信用拨款。