Simple-Doodle-SD3.5-Turbo Open Source Model - Free Generation of Simple Doodle-Style Images

Simple Doodle SD3.5 Turbo

Developed by prithivMLmods

A LoRA fine-tuned model based on Stable Diffusion 3.5 Turbo, specifically designed for generating simple doodle-style images

Image Generation Open Source License:Openrail #Doodle style generation #LoRA fine-tuning #Quick sketch

Downloads 16

Release Time : 11/8/2024

Model Overview

This model utilizes LoRA technology to fine-tune the Stable Diffusion 3.5 Turbo base model, focusing on generating images with doodle and sketch styles. Suitable for quickly creating cartoon-style characters, scenes, and objects.

Model Features

Doodle style generation

Specially optimized for generating simple doodle and sketch-style images

LoRA fine-tuning

Employs LoRA technology for lightweight fine-tuning of the base model, adding specific styles while preserving original capabilities

Fast generation

Optimized based on SD3.5 Turbo version, maintaining fast generation speed

Model Capabilities

Text-to-image generation

Stylized image generation

Cartoon character generation

Sketch scene generation

Use Cases

Creative design

Cartoon character design

Generate cartoon characters in various styles

Examples showcase generation effects of cartoon characters with different features

Scene illustration

Create sketch-style natural scenes and backgrounds

Examples demonstrate doodle-style representations of natural elements like mountains and trees

Educational applications

Teaching material generation

Quickly generate sketch materials for teaching purposes

🚀 Simple-Doodle-SD3.5-Turbo

This model is designed for text - to - image generation, leveraging LoRA and Diffusers technology. It can create simple doodle - style images based on given text prompts.

🚀 Quick Start

Setting Up

from diffusers import DiffusionPipeline
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model_repo_id = "stabilityai/stable-diffusion-3.5-large-turbo"

torch_dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32

pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
pipe = pipe.to(device)

pipe.load_lora_weights("prithivMLmods/Simple-Doodle-SD3.5-Turbo", weight_name="SD3.5-Turbo-Realism-2.0-LoRA.safetensors")
trigger_word = "Simple Doodle"  
pipe.fuse_lora(lora_scale=1.0)

Trigger words

You should use Simple Doodle to trigger the image generation.

✨ Features

Text - to - Image Generation: Generate simple doodle - style images from text prompts.
LoRA Integration: Utilize LoRA technology to fine - tune the base model.

📦 Installation

The weights for this model are available in Safetensors format. You can Download them in the Files & versions tab.

📚 Documentation

Model description

prithivMLmods/Simple-Doodle-SD3.5-Turbo

Property	Details
Model Type	Text - to - Image Generation Model
Base Model	stabilityai/stable - diffusion - 3.5 - large - turbo
Labeling	florence2 - en(natural language & English)
Total Images Used for Training	18

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	20 & 2300
Epoch	10	Save Every N Epochs	1

App File Structure

/project-root/
├── .gitattributes         
├── README.md      
├── app.py             
├── pythonproject.py

Gallery

Important Note

The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.

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