LoRA-FLUX-anime-style-v2 Open Source Model - Free to Generate High-Quality Anime-Style Images

Lora FLUX Anime Style V2

Developed by minpeter

A low-rank adaptation model trained on the FLUX.1-dev base model, specializing in generating high-quality anime-style images

Image Generation Open Source License:Other #Anime Style Adapter #Low-Rank Diffusion Model #High-Detail Illustration Generation

Downloads 724

Release Time : 3/20/2025

Model Overview

This model is a text-to-image diffusion model fine-tuned using Low-Rank Adaptation (LoRA) technology, particularly skilled at generating digital illustrations and food images with anime aesthetics.

Model Features

Anime Style Optimization

Specially optimized for anime-style image generation, capable of producing high-quality, detail-rich anime artworks

Low-Rank Adaptation Technology

Utilizes LoRA technology to fine-tune the base model, enhancing specific style generation while preserving base model capabilities

Adjustable Parameters

Provides adapter weight adjustment (0.7~1.0) for flexible control over style intensity

Model Capabilities

Anime-style image generation

Character illustration creation

Food image generation

Stylized rendering

Use Cases

Digital Art Creation

Anime Character Design

Generate unique anime character designs

Sample/s1.png shows charming anime character illustrations

Food Illustration

Generate appealing anime-style food images

Sample/s2.png displays exquisite fruit tart illustrations

Concept Art

Fantasy Scene Creation

Generate anime-style scenes with fantasy elements

Sample/s3.png presents mystical fantasy scenes

🚀 Fantasy Anime Style

A Flux LoRA trained on a local computer, offering a unique anime - style image generation experience.

This Flux LoRA is trained on a local computer with [ostris/ai - toolkit](https://github.com/ostris/ai - toolkit). It fixes certain character style biases that existed in FAS v1. Although it still has some difficulties generating images that are not people or food, the hope is that this issue will be resolved in the next version, enabling it to be used as a "style LoRA". It is recommended to set guidance_scale to 3.5 and adapter_weights between 0.7 and 1.0. Feel free to adjust the rest of the parameters and test it out.

✨ Features

Style Bias Fix: Resolved specific character style biases present in FAS v1.
Anime Style Generation: Utilize the anime style trigger words to generate unique anime - style images.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

You should use anime style to trigger the image generation.

Advanced Usage

import torch
from diffusers import AutoPipelineForText2Image

pipe = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to("cuda")

pipe.unload_lora_weights()
pipe.load_lora_weights("minpeter/FAS-v2", weight_name="adapter.safetensors", adapter_name="fas-v2")
pipe.set_adapters(["fas-v2"], adapter_weights=[0.8])

prompt = "anime style, Digital illustration with a glamorous and captivating atmosphere. Attractive figure with stylish short black bob and bangs. Eye-catching composition showing a beautiful side profile with head turned to the right from the back. Wearing large, sparkling, ornate gold earrings and an elegant lace choker that accentuates the neckline. In the background is a huge, brightly shining mysterious orange full moon dominating the night sky. Dramatic yet warm lighting gently envelops the figure and adds a dreamy feel."

image = pipe(
    prompt=prompt,
    guidance_scale=3.5,
    height=1024,
    width=1024,
    num_inference_steps=15,
    # generator=torch.Generator(device="cpu").manual_seed(208070), # for reproducibility
).images[0]

image.save("s4.png")

📚 Documentation

Trigger words

Use anime style to trigger the image generation.

Recommended Parameters

It is recommended to set guidance_scale to 3.5 and adapter_weights between 0.7 and 1.0. You can adjust other parameters according to your needs.

📄 License

This project uses the flux - 1 - dev - non - commercial - license. You can view the detailed license information at License Link.

Information Table

Property	Details
Base Model	black - forest - labs/FLUX.1 - dev
Instance Prompt	anime style
License	other
License Name	flux - 1 - dev - non - commercial - license
License Link	https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md

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