Mystic / README.md
pranavajay's picture
Update README.md
ca61727 verified
---
tags:
- text-to-image
- stable-diffusion
- diffusers
- image-generation
- flux
- safetensors
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
base_model: black-forest-labs/FLUX.1-dev
library_name: diffusers
---
# Mystic AI
<div align="center">
<img src="https://enhanceai.s3.amazonaws.com/976a976a-38e2-47d0-89fe-ace1f0e10483_1.png" width="600"/>
</div>
**Mystic AI** is a cutting-edge image generation model that focuses on creating high-quality, aesthetically pleasing images with minimal effort. Designed to perform efficiently, Mystic AI can generate stunning visuals in as few as 8 to 16 inference steps, making it a powerful tool for creative professionals and enthusiasts alike.
## Features
- **High Quality Output:** Mystic AI produces images with exceptional detail and realism, comparable to leading models like MidJourney.
- **Efficient Inference:** Capable of generating high-quality images with fewer steps, reducing computational load while maintaining excellent results.
- **Versatile Applications:** Ideal for a range of creative projects, including fashion photography, portrait art, and more.
## Installation
To use Mystic AI, you'll need to install the `diffusers` library and load the model. Here's how you can get started:
```bash
pip install diffusers
pip install torch --extra-index-url https://download.pytorch.org/whl/cu118
```
## Usage
Below is a sample Python script to generate an image using Mystic AI:
```python
import torch
from diffusers import FluxPipeline
# Load the model
pipe = FluxPipeline.from_pretrained("enhanceateam/mystic", torch_dtype=torch.float16)
pipe.to("cuda")
# Define your prompt
prompt = (
"close up portrait, Amidst the interplay of light and shadows in a photography studio, "
"a soft spotlight traces the contours of a face, highlighting a figure clad in a sleek "
"black turtleneck. The garment, hugging the skin with subtle luxury, complements the "
"Caucasian model's understated makeup, embodying minimalist elegance. Behind, a pale gray "
"backdrop extends, its fine texture shimmering subtly in the dim light, artfully balancing "
"the composition and focusing attention on the subject. In a palette of black, gray, and skin "
"tones, simplicity intertwines with profundity, as every detail whispers untold stories."
)
# Generate the image
image = pipe(prompt,
num_inference_steps=16,
guidance_scale=7.5,
width=768, height=1024,
).images[0]
# Save the image
image.save("mystic_example.png")
```
## Online Service
Mystic AI is available for use via an online service:
- **Enhance Playground:** Explore and generate images directly in your browser with the Mystic Run playground at [enhanceai.art/playground/v2](https://enhanceai.art/playground/v2).
## API Service
If you prefer to integrate Mystic AI into your own applications, you can access it via our API:
- **ModelsLabAPI Service:** Visit [https://modelslab.com/models/mystic](https://modelslab.com/models/mystic) to get started with the Mystic API, allowing you to generate images programmatically.
## Comparison with FLUX
Mystic AI is often compared to FLUX.1-dev for its high-quality outputs. Below are examples that demonstrate the differences in image generation under similar settings.
<div align="center">
<img src="https://i.imgur.com/GlGXtDJ.jpeg" width="800"/>
<img src="https://i.imgur.com/8OblxyN.jpeg" width="800"/>
<img src="https://i.imgur.com/S8nkwEs.jpeg" width="800"/>
<img src="https://i.imgur.com/0KAGeeB.jpeg" width="800"/>
</div>
## Conclusion
Mystic AI is an efficient and versatile image generation model, perfect for creators looking for high-quality results with minimal computational resources. Whether you're a professional or an enthusiast, Mystic AI can help you achieve your creative vision with ease.
## License
This project is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md). All generated images are non-commercial.