How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2509", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("ReyChiaro/StyleController")

prompt = "Turn this cat into a dog"
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")

image = pipe(image=input_image, prompt=prompt).images[0]

StyleController

Staying True to the Origin: Continuous Image Stylization with Smooth Transitions

Rui Xu  Β·  Hanmo Zhang  Β·  Songhua Liu
Shanghai Jiao Tong University

Hugging Face Dataset Hugging Face Model Project Page arXiv GitHub

StyleController is a controllable image-stylization adapter collection. Given a content image, a style reference, a text instruction, and a scalar strength, it generates stylized images while providing continuous control over the amount of transferred style.

This repository contains model weights only. Inference and training code are maintained in the StyleController GitHub repository.

Available models

Variant Base model Precision Strength anchors Status
qwenimage_edit_2509 Qwen/Qwen-Image-Edit-2509 BF16 0.1–0.9 Available

Repository layout

StyleController/
β”œβ”€β”€ README.md
β”œβ”€β”€ MODEL_CARD.md
β”œβ”€β”€ LICENSE
β”œβ”€β”€ NOTICE
β”œβ”€β”€ model_manifest.json
└── qwenimage_edit_2509/
    β”œβ”€β”€ README.md
    β”œβ”€β”€ stylecontroller_config.json
    β”œβ”€β”€ checksums.sha256
    β”œβ”€β”€ styctrl_qwenimage_edit_2509.safetensors
    └── projectors/
        β”œβ”€β”€ s01.safetensors
        β”œβ”€β”€ ...
        └── s09.safetensors

Download

Install the Hugging Face CLI and download the current variant:

pip install -U huggingface_hub

hf download ReyChiaro/StyleController \
  --include "qwenimage_edit_2509/*" \
  --local-dir hf_weights

Inference

Clone and install the implementation:

git clone https://github.com/ReyChiaro/StyleController.git
cd StyleController
uv sync

Run Qwen-Image-Edit-2509 inference at strength 0.55:

uv run python infer_styctrl.py \
  --model qwen \
  --pretrained-pipeline Qwen/Qwen-Image-Edit-2509 \
  --content examples/content.jpg \
  --style examples/style.jpg \
  --prompt "Transfer the style of image 2 to image 1 while preserving the content structure." \
  --strength 0.55 \
  --output outputs/result_055.png \
  --lora-checkpoint hf_weights/qwenimage_edit_2509/styctrl_qwenimage_edit_2509.safetensors \
  --projector-checkpoints \
    hf_weights/qwenimage_edit_2509/projectors/s01.safetensors \
    hf_weights/qwenimage_edit_2509/projectors/s02.safetensors \
    hf_weights/qwenimage_edit_2509/projectors/s03.safetensors \
    hf_weights/qwenimage_edit_2509/projectors/s04.safetensors \
    hf_weights/qwenimage_edit_2509/projectors/s05.safetensors \
    hf_weights/qwenimage_edit_2509/projectors/s06.safetensors \
    hf_weights/qwenimage_edit_2509/projectors/s07.safetensors \
    hf_weights/qwenimage_edit_2509/projectors/s08.safetensors \
    hf_weights/qwenimage_edit_2509/projectors/s09.safetensors \
  --anchor-strengths 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9

License

The model-weight release is provided under the Apache License 2.0. The StyleController source code is separately licensed under MIT. The Qwen base model and SmoothStyle dataset remain governed by their own licenses and notices; see NOTICE.

Citation

Downloads last month
-
Inference Providers NEW

Model tree for ReyChiaro/StyleController

Adapter
(79)
this model

Dataset used to train ReyChiaro/StyleController