Anya Taylor-Joy - Flux Lora Open - Source Image Generation Model: Precise Restoration of Character Features and Free Local Training

Anyataylorjoy FluxLora

Developed by DeZoomer

A text-to-image model trained using AI-Toolkit (Flux.1 Dev Edition), utilizing 20 publicly available images for local training, focusing on character feature restoration.

Image Generation Open Source License:Other #Celebrity Portrait Generation #Low-Rank Adaptation Optimization #Flux-Guided Control

Downloads 88

Release Time : 11/1/2024

Model Overview

This model is a text-to-image generation model based on the Stable Diffusion architecture, specifically optimized for generating portrait images of Anya Taylor-Joy. Supports low-rank adaptation modules and flux-guided technology.

Model Features

Low-Rank Adaptation Technology

Supports low-rank adaptation modules with intensity levels of 0.8-1.2 for fine-tuning model outputs.

Flux Guidance

Supports 3-4 levels of flux guidance to enhance the quality and consistency of generated images.

Character Feature Restoration

Focuses on 100% restoration of specific character features, typically resulting in larger model files compared to similar products.

No Trigger Words Required

No need to use specific trigger words when generating images.

Model Capabilities

Text-to-Image Generation

Portrait Generation

Stylized Image Generation

Use Cases

Creative Arts

Portrait Creation

Generate Anya Taylor-Joy style portraits based on text descriptions.

Sample images showcase various styles of character portraits.

Concept Art Creation

Generate concept art images for film, gaming, and other projects.

🚀 Anya Taylor-Joy | Flux

This project is a text - to - image model based on Flux, LoRA, and Stable Diffusion. It can generate high - quality images of Anya Taylor - Joy with specific settings.

🚀 Quick Start

Model Information

Property	Details
Base Model	black-forest-labs/FLUX.1-dev
License	other (flux-1-dev-non-commercial-license, License Link)
Inference Width	768
Inference Height	1024

Gallery

✨ Features

High - Quality Generation: Trained locally with 20 publicly accessible images using AI - Toolkit (Flux.1 Dev), it can generate high - quality images of Anya Taylor - Joy.
Flexible Parameters: Use with LoRA strength between 0.8 - 1.2 and FluxGuidance between 3 - 4. No keywords needed.
Customization Available: Commissions for custom/private LoRAs are open.

📚 Documentation

Model description

The model was trained locally with 20 publicly accessible images using AI - Toolkit (Flux.1 Dev). You can use it with a LoRA strength between 0.8 - 1.2 and FluxGuidance between 3 - 4, and no keywords are needed.

For example, in ComfyUI, you can use the prompt Portrait photo of a woman in a garden.

💡 Usage Tip

If you want a custom/private LoRA, you can request it here: https://ko-fi.com/de_zoomer/commissions.

Background

I've been deeply exploring how to create LoRAs with 100% accuracy to the original character. My focus is on quality, which is why my files tend to be heavier than others.

After creating over 100+ LoRAs for testing, using both Kohya and AI - Toolkit since day one, I've consistently stayed up to date with the latest releases, exchanging knowledge in their communities.

My expertise is mainly with characters, so I’m not as familiar with LoRAs for style or anime, although the process might not differ too much.

If you want your own custom LoRa, feel free to message me! Commissions are open—check out my Ko - fi link above.

📦 Installation

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

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