World of Warcraft Cinematic Style SDXL Open-Source Model - Generate World of Warcraft Movie-Level Style Images

World Of Warcraft Cinematic Style Sdxl

Developed by Norod78

A cinematic-style LoRA model trained based on World of Warcraft game trailers, compatible with SDXL base models

Image Generation OtherOpen Source License:Other #World of Warcraft Cinematic Style #SDXL-LoRA Style Transfer #Fantasy Movie Effects

Downloads 26

Release Time : 4/11/2024

Model Overview

This LoRA model is trained using cinematic frames extracted from World of Warcraft game trailers, capable of transforming input content into artworks with the cinematic style of World of Warcraft, particularly suitable for generating fantasy-themed images.

Model Features

Cinematic Visual Quality

Trained on official World of Warcraft trailers, generating images with cinematic visual effects

Widescreen Optimization

Specially optimized for widescreen image generation, outperforming square and portrait formats

Style Consistency

Maintains the unique artistic style and atmosphere of the World of Warcraft universe

Broad Compatibility

Works with SDXL base models, supporting various samplers and parameter settings

Model Capabilities

Transform ordinary images into World of Warcraft cinematic style

Generate fantasy-themed artworks

Preserve the distinctive characteristics of World of Warcraft characters and scenes

Support high-resolution image generation

Use Cases

Artistic Creation

Character Style Conversion

Convert characters from other works into World of Warcraft cinematic style

Examples include 'Frozen's Elsa', 'Wonder Woman' conversion effects

Fantasy Scene Creation

Generate fantasy scenes with World of Warcraft characteristics

Examples include 'Cthulhu Rising from Stormy Seas' and other scenes

Entertainment Applications

Fun Image Generation

Add World of Warcraft style to pop culture elements

Examples include 'The Simpsons', 'Pikachu' and other amusing conversions

🚀 World of Warcraft cinematic style [SDXL]

This model is trained on cinematic images from World of Warcraft trailers up to the "Shadowlands" expansion, enabling text-to-image generation in a World of Warcraft cinematic style.

🚀 Quick Start

This model is used for text-to-image generation. You can trigger the World of Warcraft cinematic style by appending the prompt with World of Warcraft cinematic style.

✨ Features

Specific Style Training: Trained on cinematic images from World of Warcraft trailers up to the "Shadowlands" expansion, which seems to produce better results in landscape than in square and portrait.
Flexible Usage: Can be used with the 🧨 diffusers library for text-to-image generation.

📦 Installation

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

💻 Usage Examples

Basic Usage

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('Norod78/world-of-warcraft-cinematic-style-sdxl', weight_name='SDXL-World-of-Warcraft-cinematic-style-Lora-r32-000005.safetensors')
image = pipeline('benderbot World of Warcraft cinematic style   ').images[0]

Advanced Usage

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers

📚 Documentation

Model description

Trained upon cinematic images taken from World of Warcraft trailers up till the "Shadowlands" expansion. This is also why it seems to produce better results in landscape than in square and portrait. I got the best results with "Euler a" 32 steps 7.5 cfg + Refiner and/or Hi-Res fix (to avoid pixelated results). Append your prompts with "World of Warcraft cinematic style" to trigger the style.