Flux-Midjourney-Painterly-LoRA Open Source Model - Free Generation of Midjourney-Style Artistic Images

Flux Midjourney Painterly LoRA

Developed by strangerzonehf

LoRA adapter based on FLUX.1-dev foundation model, specifically designed for generating Midjourney-style artistic images

Image Generation Open Source License:Other #Midjourney style painting #Low-rank adaptation diffusion model #Anime portrait generation

Downloads 24

Release Time : 5/3/2025

Model Overview

This model fine-tunes the base diffusion model through LoRA (Low-Rank Adaptation) technology, capable of generating images with distinctive Midjourney painting styles, particularly excelling in character portraits and animal illustrations

Model Features

Midjourney style simulation

Specially optimized for generating Midjourney-like painting style images

LoRA efficient fine-tuning

Employs low-rank adaptation technology to achieve style adaptation while maintaining base model performance

Precise parameter control

Provides detailed generation parameter configurations including resolution, inference steps optimization recommendations

Model Capabilities

Text-to-image generation

Art style transfer

Portrait painting generation

Illustration creation

Use Cases

Digital art creation

Character portrait generation

Generates artistic character portraits with Midjourney characteristics

Examples showcase various styles of character close-ups

Animal illustrations

Creates stylized animal figures

Includes artistic representations of animals like cats

Concept design

Character design

Quickly generates anime-style character concept art

Diverse characters with various hairstyles, costumes and expressions

🚀 Flux-Midjourney-Painterly-LoRA

A LoRA model for text-to-image generation, enabling the creation of painterly images based on the black-forest-labs/FLUX.1-dev base model.

🚀 Quick Start

Model Setup

import torch
from pipelines import DiffusionPipeline

base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "strangerzonehf/Flux-Midjourney-Painterly-LoRA"
trigger_word = "mj painterly"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

Triggering Image Generation

You should use mj painterly to trigger the image generation.

Downloading the Model

Weights for this model are available in Safetensors format. Download them in the Files & versions tab.

✨ Features

Text-to-Image Generation: Generate painterly images based on text prompts.
LoRA Integration: Utilize LoRA technology to enhance the base model's performance.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

import torch
from pipelines import DiffusionPipeline

base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "strangerzonehf/Flux-Midjourney-Painterly-LoRA"
trigger_word = "mj painterly"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

# Example prompt
prompt = f"{trigger_word}, a monochromatic drawing of a womans face is displayed against a dark blue backdrop."
image = pipe(prompt).images[0]
image.save("output.png")

📚 Documentation

Model Description

Image Processing Parameters

Parameter	Value	Parameter	Value
LR Scheduler	constant	Noise Offset	0.03
Optimizer	AdamW	Multires Noise Discount	0.1
Network Dim	64	Multires Noise Iterations	10
Network Alpha	32	Repeat & Steps	25 & 3400
Epoch	20	Save Every N Epochs	1 [40]

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 26 [ Midjourney Generated Synthetic Image ]

Best Dimensions & Inference

Dimensions	Aspect Ratio	Recommendation
1280 x 832	3:2	Best
1024 x 1024	1:1	Default

Inference Range

Recommended Inference Steps: 30-35

🔧 Technical Details

The model is based on the black-forest-labs/FLUX.1-dev base model and uses LoRA technology for fine-tuning. The training process involves specific image processing parameters and a set of synthetic images generated by Midjourney.

📄 License

This model is licensed under the flux-1-dev-non-commercial-license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご