README.md

---
base_model: runwayml/stable-diffusion-v1-5
license: creativeml-openrail-m
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
inference: true
---

# MeinaMix V11

[Original model page](https://civitai.com/models/7240?modelVersionId=119057)

<details>
  <summary>Examples</summary>

|                                 |                                 |                                 |                                 |
|---------------------------------|---------------------------------|---------------------------------|---------------------------------|
| ![](.hf/readme/examples/1.png)  | ![](.hf/readme/examples/2.png)  | ![](.hf/readme/examples/3.png)  | ![](.hf/readme/examples/4.png)  |
| ![](.hf/readme/examples/5.png)  | ![](.hf/readme/examples/6.png)  | ![](.hf/readme/examples/7.png)  | ![](.hf/readme/examples/8.png)  |
| ![](.hf/readme/examples/9.png)  | ![](.hf/readme/examples/10.png) | ![](.hf/readme/examples/11.png) | ![](.hf/readme/examples/12.png) |
| ![](.hf/readme/examples/13.png) | ![](.hf/readme/examples/14.png) | ![](.hf/readme/examples/15.png) | ![](.hf/readme/examples/16.png) |
| ![](.hf/readme/examples/17.png) | ![](.hf/readme/examples/18.png) | ![](.hf/readme/examples/19.png) | ![](.hf/readme/examples/20.png) |

-----------

</details>

**MeinaMix objective** is to be able to do good art with little prompting.
I have a [discord](https://discord.gg/F6yeQtEQ98) where you can share images, discuss prompt and ask for help. 
https://discord.gg/meinaverse

I also have a [ko-fi](https://ko-fi.com/meina) and [Patreon](https://www.patreon.com/MeinaMix) page where you can 
support me or buy me a coffee <3, it will be very much appreciated: 
https://ko-fi.com/meina and https://www.patreon.com/MeinaMix

MeinaMix and the other of Meinas will ALWAYS be FREE.

## How to use?

Negative: worst quality, low quality, zombie, sketch, interlocked fingers, comic\
CLIP Skip: 2\
Steps: 20 to 30 (if image has errors or artefacts use higher steps)\
CFG Scale: 4.0 to 11.0\
Size: 512x768, 512x1024 for portrait, 768x512, 1024x512, 1536x512 for landscape

## Use it with 🧨 diffusers

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

```python
import torch
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
  'kamillaova/MeinaMix',
  torch_dtype=torch.float16,  # or bfloat16 for Ampere+ GPUs
).to('cuda')

img = pipe(
  prompt='positive prompt',
  negative_prompt='negative prompt',

  guidance_scale=5.0,
  num_inference_steps=30,
  width=512, height=768,
).images[0]

img.save('image.png')
```