---
title: openjourney
canonical_url: "https://www.modelscope.cn/models/dienstag/openjourney"
md_url: "https://www.modelscope.cn/models/dienstag/openjourney.md"
repository: dienstag/openjourney
last_updated: 2023-03-28
license: creativeml-openrail-m
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
parameters: 2.6B
tensor_type:
  - F32
  - F16
  - I64
library_name:
  - lora
  - safetensors
  - diffusers
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 2609
stars: 6
tags:
  - stable-diffusion
  - text-to-image
---

# openjourney

> openjourney - dienstag 在 ModelScope 开源的模型。Openjourney is an open source Stable Diffusion fine tuned model on Midjourney images, by PromptHero

dienstag/openjourney 是 ModelScope 魔搭社区上的 2.6B 参数text-to-image-synthesis模型，采用 creativeml-openrail-m 许可。

- **Repository**: dienstag/openjourney
- **License**: creativeml-openrail-m
- **Tasks**: text-to-image-synthesis
- **Parameters**: 2.6B
- **Tags**: stable-diffusion, text-to-image
- **Downloads**: 2609
- **Stars**: 6
- **Last updated**: 2023-03-28

Source: https://www.modelscope.cn/models/dienstag/openjourney

---

# Openjourney is an open source Stable Diffusion fine tuned model on Midjourney images, by [PromptHero](https://prompthero.com/poolsuite-diffusion-prompts?utm_source=huggingface&utm_medium=referral)

Include **'mdjrny-v4 style'** in prompt. Here you'll find hundreds of [Openjourney prompts](https://prompthero.com/openjourney-prompts?utm_source=huggingface&utm_medium=referral)

# Openjourney Links
- [Lora version](https://huggingface.co/prompthero/openjourney-lora)
- [Openjourney v2](https://huggingface.co/prompthero/openjourney-v2)

# Want to learn AI art generation?:
- [Crash course in AI art generation](https://prompthero.com/academy/prompt-engineering-course?utm_source=huggingface&utm_medium=referral)
- [Learn to fine-tune Stable Diffusion for photorealism](https://prompthero.com/academy/dreambooth-stable-diffusion-train-fine-tune-course?utm_source=huggingface&utm_medium=referral)

# Use it for free:
[![Open In Spaces](https://camo.githubusercontent.com/00380c35e60d6b04be65d3d94a58332be5cc93779f630bcdfc18ab9a3a7d3388/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f25463025394625413425393725323048756767696e67253230466163652d5370616365732d626c7565)](https://huggingface.co/spaces/akhaliq/midjourney-v4-diffusion)

### Stable Diffusion v1.5 vs Openjourney 
(Same parameters, just added "mdjrny-v4 style" at the beginning):
<img src="https://s3.amazonaws.com/moonup/production/uploads/1667904587642-63265d019f9d19bfd4f45031.png" width="100%"/>
<img src="https://s3.amazonaws.com/moonup/production/uploads/1667904587623-63265d019f9d19bfd4f45031.png" width="100%"/>
<img src="https://s3.amazonaws.com/moonup/production/uploads/1667904587609-63265d019f9d19bfd4f45031.png" width="100%"/>
<img src="https://s3.amazonaws.com/moonup/production/uploads/1667904587646-63265d019f9d19bfd4f45031.png" width="100%"/>

### 🧨 Diffusers

This model can be used just like any other Stable Diffusion model. For more information,
please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).

You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or [FLAX/JAX]().


#### 代码范例
```python
from modelscope.models import Model

from modelscope.pipelines import pipeline

from modelscope.utils.constant import Tasks

import cv2

if __name__ == '__main__':
    pipe = pipeline(task=Tasks.text_to_image_synthesis, 
                model='dienstag/openjourney',
                model_revision='v1.0.0')
    prompt = 'retro serie of different cars with different colors and shapes, mdjrny-v4 style'
    output = pipe({'text': prompt})
    cv2.imwrite('result.png', output['output_imgs'][0])
```