Trained remotely on Modal using Qwen/Qwen-Image-2512 as the base model. This repository contains the LoRA adapter only and does not redistribute the base model.
Description
A LoRA model fine-tuned to generate soft impressionist images with broken color, luminous garden light, reflective water, loose painterly texture, atmospheric streets, cozy interiors, flowers, fields, cafes, and quiet everyday scenes.
The model works best when the prompt begins with the trigger phrase, then describes a simple subject clearly, and ends with a few style cues such as soft reflections, warm natural light, loose impressionist brushwork, or a pastel color palette.
Trigger words
Use Monet Style to activate the LoRA style/concept.
Usage
I recommend using this LoRA with Qwen Image 2512 in ComfyUI, Diffusers, Draw Things, or another compatible LoRA loader.
Recommended starting settings:
LoRA weight: 0.75-0.90
Steps: 30-40
Guidance: 3.0-3.5
Shift: 2.83
Sampler: FlowMatch if available, otherwise UniPC Trailing
Resolution: 1024 x 1024
Prompt format:
Monet Style, [clear subject and setting], soft natural light, loose impressionist brushwork, pastel color palette
Example prompt:
Monet Style, a lily pond at sunrise with water lilies and gentle ripples, soft reflections, luminous garden light, loose impressionist brushwork, pastel color palette
Preview images use the images/preview_01.png through images/preview_06.png naming pattern.
Training Data
This model was trained on 100 GPT-generated Monet-style impressionist image-caption pairs.
