---
title: Kontext-Style-Loras
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Kontext-Style-Loras"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Kontext-Style-Loras.md"
repository: AI-ModelScope/Kontext-Style-Loras
last_updated: 2025-07-26
pipeline_tag: image-to-image
tasks:
  - image-to-image
base_model:
  - black-forest-labs/FLUX.1-Kontext-dev
base_model_relation: finetune
parameters: 3.9B
tensor_type:
  - BF16
library_name:
  - pytorch
  - safetensors
frameworks:
  - pytorch
language:
  - en
downloads: 505
stars: 5
tags:
  - Style
  - Ghibli
  - FluxKontext
  - Image-to-Image
---

# Kontext-Style-Loras

> Kontext-Style-Loras - AI-ModelScope 在 ModelScope 开源的模型。Style LoRAs for FLUX.1 Kontext Model This repository provides a collection of 20+ style LoRA adapters for the FLUX.1 Kontext Model, enabling a wide range of artistic and cartoon styles for high-quality…

AI-ModelScope/Kontext-Style-Loras 是 ModelScope 魔搭社区上的 3.9B 参数image-to-image模型，基于 black-forest-labs/FLUX.1-Kontext-dev 构建。

- **Repository**: AI-ModelScope/Kontext-Style-Loras
- **Tasks**: image-to-image
- **Parameters**: 3.9B
- **Base model**: black-forest-labs/FLUX.1-Kontext-dev
- **Tags**: Style, Ghibli, FluxKontext, Image-to-Image
- **Downloads**: 505
- **Stars**: 5
- **Last updated**: 2025-07-26

Source: https://www.modelscope.cn/models/AI-ModelScope/Kontext-Style-Loras

---

# Style LoRAs for FLUX.1 Kontext Model
This repository provides a collection of 20+ style LoRA adapters for the FLUX.1 Kontext Model, enabling a wide range of artistic and cartoon styles for high-quality image-to-image generation.
These LoRAs are trained on high-quality paired data generated by GPT-4o. 

**Srouce training code: https://github.com/Owen718/Kontext-Lora-Trainer**

The data is from [Omniconsistency](https://huggingface.co/datasets/showlab/OmniConsistency).
## News!
**We create [Kontext-Style](https://huggingface.co/Kontext-Style) to host each LoRA as its own repo! And we provide [space demo](https://huggingface.co/spaces/Kontext-Style/Kontext-Style-LoRAs) to directly run our LoRAs online!**

![Comparison02](./style_comparison_02.jpg)
![Comparison01](./style_comparion_01.jpg)
![Comparison03](./style_comparion_03.jpg)
![Comparison04](./style_comparion_04.jpg)

Contributor: Tian YE&Song FEI, HKUST Guangzhou.

## Inference Example
```python
from huggingface_hub import hf_hub_download
from diffusers import FluxKontextPipeline
from diffusers.utils import load_image
import torch

STYLE_NAME = "3D_Chibi"

style_type_lora_dict = {
    "3D_Chibi": "3D_Chibi_lora_weights.safetensors",
    "American_Cartoon": "American_Cartoon_lora_weights.safetensors",
    "Chinese_Ink": "Chinese_Ink_lora_weights.safetensors",
    "Clay_Toy": "Clay_Toy_lora_weights.safetensors",
    "Fabric": "Fabric_lora_weights.safetensors",
    "Ghibli": "Ghibli_lora_weights.safetensors",
    "Irasutoya": "Irasutoya_lora_weights.safetensors",
    "Jojo": "Jojo_lora_weights.safetensors",
    "Oil_Painting": "Oil_Painting_lora_weights.safetensors",
    "Pixel": "Pixel_lora_weights.safetensors",
    "Snoopy": "Snoopy_lora_weights.safetensors",
    "Poly": "Poly_lora_weights.safetensors",
    "LEGO": "LEGO_lora_weights.safetensors",
    "Origami" : "Origami_lora_weights.safetensors",
    "Pop_Art" : "Pop_Art_lora_weights.safetensors",
    "Van_Gogh" : "Van_Gogh_lora_weights.safetensors",
    "Paper_Cutting" : "Paper_Cutting_lora_weights.safetensors",
    "Line" : "Line_lora_weights.safetensors",
    "Vector" : "Vector_lora_weights.safetensors",
    "Picasso" : "Picasso_lora_weights.safetensors",
    "Macaron" : "Macaron_lora_weights.safetensors",
    "Rick_Morty" : "Rick_Morty_lora_weights.safetensors"
}


hf_hub_download(repo_id="Owen777/Kontext-Style-Loras", filename=style_type_lora_dict[STYLE_NAME], local_dir="./LoRAs")
image = load_image("https://huggingface.co/datasets/black-forest-labs/kontext-bench/resolve/main/test/images/0003.jpg").resize((1024, 1024))
image.save("0037.png")
pipeline = FluxKontextPipeline.from_pretrained("black-forest-labs/FLUX.1-Kontext-dev", torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights(f"./LoRAs/{style_type_lora_dict[STYLE_NAME]}", adapter_name="lora")
pipeline.set_adapters(["lora"], adapter_weights=[1])
image = pipeline(image=image, prompt=f"Turn this image into the {STYLE_NAME.replace('_', ' ')} style.",height=1024,width=1024,num_inference_steps=24).images[0]
image.save(f"{STYLE_NAME}.png")
```



Feel free to open an issue or contact us for feedback or collaboration!
We will release more style LoRAs soon!