Lora-Maurice-Prendergast-Flux Open-Source Model - Freely Generate Images in the Artistic Style of Maurice Prendergast

Lora Maurice Prendergast Flux

Developed by davidrd123

A LoRA model trained on FLUX.1-dev, specifically designed to generate images in the artistic style of Maurice Prendergast.

Image Generation Open Source License:Openrail #Impressionist oil painting style #High-density crowd scenes #Multi-element composition

Downloads 1,047

Release Time : 8/13/2024

Model Overview

This LoRA model fine-tunes the FLUX.1-dev base model to generate images with Maurice Prendergast's artistic style, excelling in complex scenes and group portraits.

Model Features

Artistic style transfer

Converts the base model's output into Maurice Prendergast's distinctive artistic style

Complex scene handling

Excels at processing scenes with numerous characters and complex elements, such as streets, parks, and other public spaces

Color control

Supports precise control over color distribution and combinations through prompts

Detail preservation

Maintains scene details and element integrity during style transfer

Model Capabilities

Text-to-image generation

Artistic style transfer

Complex scene rendering

Color control

Use Cases

Artistic creation

Artistic style reproduction

Generate original artworks in Maurice Prendergast's style

Can produce images with signatures and characteristics matching the artist's style

Scene recreation

Create public space scenes with specific historical period features

Accurately presents period characteristics such as clothing and architectural styles

Design assistance

Concept design

Provide stylized concept art for illustrations, stage designs, etc.

Quickly generates multiple stylized solutions

🚀 lora-Maurice-Prendergast-Flux

This project is a LoRA model derived from black-forest-labs/FLUX.1-dev, which is designed for text-to-image generation tasks.

🚀 Quick Start

Prerequisites

Install necessary libraries:

pip install diffusers torch

Inference Example

import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'davidrd123/lora-Maurice-Prendergast-Flux'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "mp_style, Street scene, 50 figures (many women: colorful dresses, many men: suits), 23 umbrellas (orange, red, yellow, green), bridge, buildings background, water, boats, Italian flag, steps, lamps, crowd ascending descending bridge, signature bottom-left"


pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
    prompt=prompt,
    num_inference_steps=20,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
    width=1024,
    height=1024,
    guidance_scale=7.5,
).images[0]
image.save("output.png", format="PNG")

✨ Features

Based on the black-forest-labs/FLUX.1-dev base model.
Supports text-to-image generation with specific styles.
Uses LoRA technology for efficient fine-tuning.

📦 Installation

To use this LoRA model, you need to install the diffusers and torch libraries:

pip install diffusers torch

💻 Usage Examples

Basic Usage

import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'davidrd123/lora-Maurice-Prendergast-Flux'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "mp_style, Street scene, 50 figures (many women: colorful dresses, many men: suits), 23 umbrellas (orange, red, yellow, green), bridge, buildings background, water, boats, Italian flag, steps, lamps, crowd ascending descending bridge, signature bottom-left"


pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
    prompt=prompt,
    num_inference_steps=20,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
    width=1024,
    height=1024,
    guidance_scale=7.5,
).images[0]
image.save("output.png", format="PNG")

📚 Documentation

Validation settings

Parameter	Value
CFG	`7.5`
CFG Rescale	`0.0`
Steps	`20`
Sampler	`None`
Seed	`42`
Resolution	`1024`

Note: The validation settings are not necessarily the same as the training settings.

Training settings

Parameter	Value
Training epochs	235
Training steps	4000
Learning rate	0.0004
Effective batch size	6
Micro - batch size	6
Gradient accumulation steps	1
Number of GPUs	1
Prediction type	flow - matching
Rescaled betas zero SNR	False
Optimizer	AdamW, stochastic bf16
Precision	Pure BF16
Xformers	Not used
LoRA Rank	64
LoRA Alpha	None
LoRA Dropout	0.1
LoRA initialisation style	default

Datasets - MauricePrendergastRedo3

Attribute	Details
Repeats	0
Total number of images	102
Total number of aspect buckets	1
Resolution	1024 px
Cropped	True
Crop style	center
Crop aspect	square

🔧 Technical Details

This LoRA model is derived from the black-forest-labs/FLUX.1-dev base model. It uses the LoRA technique for fine-tuning, which allows for more efficient training and adaptation to specific datasets. The training process involves multiple settings such as the optimizer, precision, and LoRA parameters, which are carefully configured to achieve the best performance.

📄 License

This project is licensed under the creativeml-openrail-m 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