README.md

# Fox 1.2 Image Model

**Fox 1.2** is 100x more powerful than Fox 1.0 - based on FLUX.1-schnell (12B params, Apache 2.0).

## Model Details

- **Base:** FLUX.1-schnell (12 billion parameters)
- **License:** Apache 2.0 (commercially unrestricted)
- **Steps:** 1-4 (vs 35+ for older models)
- **Quality:** State-of-the-art

## Ollama Command

FLUX.1-schnell is a **diffusers/HuggingFace model**, not an Ollama model. 

### To use with Python:
```python
from diffusers import FluxPipeline
import torch

pipe = FluxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-schnell",
    torch_dtype=torch.bfloat16
)
pipe.to("cuda")

image = pipe(
    prompt="Your prompt here",
    num_inference_steps=4,
    guidance_scale=0.0,
).images[0]

image.save("output.png")
```

**First:** Accept license at https://huggingface.co/black-forest-labs/FLUX.1-schnell

## Quick API Call:
```bash
curl -X POST "http://127.0.0.1:7860/generate" \
  -d "prompt=A majestic fox in a forest at sunset"
```

## Comparison

| Feature | Fox 1.0 | Fox 1.2 |
|---------|---------|---------|
| Parameters | ~1B | 12B |
| Steps | 35+ | 1-4 |
| Quality | Good | State-of-the-art |

## License

Apache 2.0 - Commercial use permitted.