---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- image-generation
- flux
- safetensors
widget:
- text: mkym this is made of wool, close up of a gundam robot
  output:
    url: images/398201ddb32398edd6d4af2fe7e1d7d7c30eabe6c7bf06d287b2746e.jpg
- text: mkym this is made of wool, burger
  output:
    url: images/3637c2d5aa282569a9849f4f38ac9c194cd16a86f9e9b3b0f66aef5e.jpg
- text: mkym this is made of wool, sports car
  output:
    url: images/5e8cb733ef5e9a3ca1a2e709911438a6afb3f5f1329107442f4d1898.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: mkym this is made of wool
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
library_name: diffusers
---
# FLUX.1-dev-LoRA-MiaoKa-Yarn-World

This is a LoRA (MiaoKa-Yarn-World) trained on FLUX.1-dev by [MIAOKA](https://www.shakker.ai/userpage/2f1c20f5b5ce44d0a9d15d9ecf721d55/publish) for creating wool yarn art. It is capable of producing intricate and realistic woolen textures and patterns while maintaining high performance.

<div class="container">
  <img src="./poster.jpg" width="1024"/>
</div>

## Showcases
<Gallery />


## Trigger words

You should use `mkym this is made of wool` to trigger the image generation. The recommended scale is `0.8` to `1.0` in diffusers.


## Inference

```python
import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("Shakker-Labs/FLUX.1-dev-LoRA-MiaoKa-Yarn-World", weight_name="FLUX-dev-lora-MiaoKa-Yarn-World.safetensors")
pipe.fuse_lora(lora_scale=1.0)
pipe.to("cuda")

prompt = "mkym this is made of wool, sports car"

image = pipe(prompt, 
             num_inference_steps=24, 
             guidance_scale=3.5,
            ).images[0]
image.save(f"example.png")
```

## Online Inference

You can also download this model at [Shakker AI](https://www.shakker.ai/modelinfo/bde5721eb17a457c85cc2fffefc0a390?from=feed), where we provide an online interface to generate images.


## Acknowledgements
This model is trained by our copyrighted users [MIAOKA](https://www.shakker.ai/userpage/2f1c20f5b5ce44d0a9d15d9ecf721d55/publish). We release this model under permissions. The model follows [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).