Qd - Sketch Open - source Image Generation Model: Freely Generate High - quality Abstract Paintings Based on Text Descriptions

Qd Sketch

Developed by strangerzonehf

Qd-Sketch is a LoRA model trained on the FLUX.1-dev base model, specializing in text-to-image generation tasks, capable of producing high-quality abstract painting-style images based on detailed textual descriptions.

Image Generation Open Source License:Other #Abstract figure painting #High-contrast colors #LoRA fine-tuning

Downloads 2,427

Release Time : 1/20/2025

Model Overview

This model is a text-to-image diffusion model, particularly adept at generating artistic-style female portraits, accurately capturing detailed features such as clothing, poses, and backgrounds.

Model Features

Artistic style generation

Exceptionally skilled at generating abstract painting-style images, capable of handling complex artistic style descriptions.

Detail control

Accurately captures detailed features such as clothing, hairstyles, and poses.

LoRA fine-tuning

Fine-tuned with LoRA on the FLUX.1-dev base model, enhancing specific style generation capabilities while preserving the base model's strengths.

Model Capabilities

Text-to-image generation

Artistic style transfer

Portrait generation

Abstract painting creation

Use Cases

Digital art creation

Abstract portrait generation

Generates artistic-style female portraits based on detailed textual descriptions.

Produces artistic-style images matching the description, such as the abstract painting style shown in examples.

Scene composition

Generates artistic scenes with specific backgrounds and atmospheres.

Examples include lakeside sunset scenes or dreamy vortex backgrounds.

Concept design

Character design

Quickly generates character concept art, including details like clothing and hairstyles.

Produces unified-style character design illustrations.

🚀 Qd-Sketch: Text-to-Image LoRA Model

This is a text-to-image LoRA model based on the black-forest-labs/FLUX.1-dev base model. It can generate various images of women according to different text descriptions, providing rich and vivid image outputs.

🚀 Quick Start

Setting Up

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/Qd-Sketch"
trigger_word = "Qd-Sketch"  
pipe.load_lora_weights(lora_repo)

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

Trigger words

You should use Qd-Sketch to trigger the image generation.

✨ Features

Rich Image Styles: It can generate abstract paintings, animated images, and more, covering a variety of styles.
Diverse Descriptions: Support different text descriptions, such as clothing, background, and facial expressions, to generate corresponding images.

📦 Installation

The installation process is included in the "Setting Up" section above.

💻 Usage Examples

Basic Usage

# After setting up as above
prompt = "Qd Sketch, An abstract painting of a woman in a green t-shirt and black pants. The woman is facing the left side of the frame, her left hand is covering her face with her right hand. Her right hand is positioned in front of her face. Her hair is a dark shade of black, and her eyes are a light brown. Her lips are a darker shade of brown. The background is a peach color, and the womans shirt is a vibrant green."
image = pipe(prompt).images[0]
image.save("output.png")

📚 Documentation

Model description for Qd-Sketch

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	26 & 3830
Epoch	20	Save Every N Epochs	1

Labeling

Labeling: florence2-en(natural language & English)

Total Images Used for Training

Total Images Used for Training : 23

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

Download model

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

📄 License

This model uses the flux-1-dev-non-commercial-license. You can view the license details here.

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