README.md

---
library_name: diffusers
---

This pipeline is intended for debugging or testing. It is saved from [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) with smaller size and randomly initialized parameters.

## Example Usage
```python
import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained("tlwu/tiny-random-flux", torch_dtype=torch.bfloat16)
prompt = "a tree with blue leaves"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=3.5,
    num_inference_steps=50,
    max_sequence_length=512,
    generator=torch.Generator("cpu").manual_seed(0)
).images[0]

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