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-2.1", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("prithivMLmods/Qwen-Image-2.1-Voxel-Style")

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]

prithivMLmods/Qwen-Image-2.1-Voxel-Style prithivMLmods/Qwen-Image-2.1-Voxel-Style

Qwen-Image-2.1-Voxel-Style

Qwen-Image-2.1-Voxel-Style is a LoRA adapter for Qwen-Image-2.1, designed to transform input images into a distinctive voxel-art style with block-based geometry, simplified forms, low-resolution 3D structures, and a stylized digital aesthetic. The adapter converts subjects, objects, and environments into voxel-inspired compositions while retaining recognizable features, colors, spatial relationships, and important visual elements from the original image. It can be used to create voxel-style characters, objects, environments, illustrations, and scenes from a wide range of input images.

This is an experimental preview model. Results may vary depending on the input image, subject, composition, and visual complexity.

Download

Download the model files from the Files & versions tab:

Download Qwen-Image-2.1-Voxel-Style

Usage

Load the LoRA adapter with Qwen-Image-2.1 and provide an input image.

Use the trigger prompt:

Transform the image into a voxel style

For best results, use input images with clearly defined subjects, objects, and environments. The adapter can be applied to photographs, illustrations, characters, objects, and other visual compositions.

Base Model

This adapter is designed for:

License

Please refer to the license terms of the base model, Qwen-Image-2.1, and ensure compliance with its terms when using or redistributing this adapter.

Acknowledgements

This adapter was created by prithivMLmods and is built for use with Qwen-Image-2.1.

Downloads last month
79
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for prithivMLmods/Qwen-Image-2.1-Voxel-Style

Adapter
(78)
this model

Collections including prithivMLmods/Qwen-Image-2.1-Voxel-Style