SD3.5-Large-Anime-LoRA Open-Source Model - Efficiently Generate High-Quality Anime-Style Images

SD3.5 Large Anime LoRA

Developed by prithivMLmods

An anime-style LoRA adapter based on the stable-diffusion-3.5-large model, capable of generating high-quality anime-style images

Image Generation Open Source License:Openrail #Anime style generation #LoRA fine-tuned diffusion model #High-resolution cartoon rendering

Downloads 1,529

Release Time : 10/29/2024

Model Overview

This model is a LoRA adapter for stable-diffusion-3.5-large, specifically optimized for anime-style image generation, able to produce images with specific anime styles based on text descriptions.

Model Features

Anime style optimization

Specially trained for anime 35 style, capable of generating high-quality anime-style images

LoRA technology integration

Uses LoRA technology to fine-tune the base model, enhancing specific style representation while maintaining the base model's capabilities

High-resolution output

Supports generating high-resolution images such as 960×1280

Model Capabilities

Text-to-image generation

Anime-style image generation

High-resolution image generation

Specific style image generation

Use Cases

Anime creation

Anime character design

Generate anime character images with specific styles based on text descriptions

Can generate anime characters with specific hair colors, clothing, and expressions

Anime scene generation

Generate anime-style background scenes

Can generate anime-style scenes such as cafes, beaches, etc.

Concept design

Character concept design

Quickly generate character concept art

Helps designers quickly visualize character concepts

🚀 SD3.5-Large-Anime-LoRA

This is a text-to-image model based on LoRA and Diffusers, specifically designed for generating anime-style images using Stable Diffusion 3.5 Large. It's still in the training phase, and the current version may have some artifacts and performance issues.

✨ Features

Anime Style: Specializes in generating high - quality anime - style images.
Easy to Use: Can be easily integrated into existing Stable Diffusion pipelines.

📦 Installation

import torch
from diffusers import StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3.5-large", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("prithivMLmods/SD3.5-Large-Anime-LoRA", weight_name="SD3.5-Large-Anime-LoRA.safetensors")
pipe.fuse_lora(lora_scale=1.0)
pipe.to("cuda")

💻 Usage Examples

Basic Usage

prompt = "Man in the style of dark beige and brown, uhd image, youthful protagonists, nonrepresentational photography"
negative_prompt = "(lowres, low quality, worst quality)"

image = pipe(prompt=prompt,
             negative_prompt=negative_prompt,
             num_inference_steps=24, 
             guidance_scale=4.0,
             width=960, height=1280,
            ).images[0]
image.save(f"example.jpg")

📚 Documentation

Model description

prithivMLmods/SD3.5-Large-Anime-LoRA

Property	Details
Model Type	LoRA for Stable Diffusion 3.5 Large
LR Scheduler	constant
Noise Offset	0.03
Optimizer	AdamW
Multires Noise Discount	0.1
Network Dim	64
Network Alpha	32
Epoch	15
Save Every N Epochs	1
Multires Noise Iterations	10
Repeat & Steps	25 & 2.7K
Labeling	florence2 - en(natural language & English)
Training Data	23 images

Sample Image

prithivMLmods/SD3.5-Large-Anime-LoRA

Trigger words 🧨

⚠️ Important Note

You should use Anime 35 to trigger the image generation.

Download model

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

📄 License

This model 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