Modelpublic

neonforestmist/qwen-image-2512-pointillism-lora

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face

0likes17downloads

Model Card

POINTILLISM LORA FOR QWEN IMAGE

Model description

Pointillism - QWEN IMAGE 2512

Acknowledgment

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 pointillism-style images with dense paint dots, luminous color mixing, clear silhouettes, and decorative light patterns.

The model is best for gardens, rainy interiors, sunset lakes, plants, cozy subjects, and painterly landscape scenes.

Trigger words

Use pointillism painting 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: 0.85-1.00
—Steps: 25-32
—Guidance: 3.0-3.4
—Shift: 2.83
—Sampler: FlowMatch if available, otherwise UniPC Trailing
—Resolution: 1024 x 1024

Preview images use the images/preview_01.png through images/preview_06.png naming pattern.

Example prompt:

text

pointillism painting of a moonlit garden path with glowing flowers and soft lantern light, dense paint dots, luminous blue and gold color mixing

Training Data

This model was trained on 70 GPT-generated pointillism images.

File

qwen_image_2512_pointillism_lora.safetensors

SHA256:

text

003c613fdd486707e441729d9db0e32b169aab3eb02ed56fba9aec19b2fee256

License

This model is licensed under the Apache License 2.0.

Trigger words

You should use pointillism painting to trigger the image generation.

Download model

Download the model from the Files & versions tab.