sWizad/all-disney-princess-xl-lora-model-from-ralph-breaks-the-internet
All Disney Princess XL LoRA Model from Ralph Breaks the Internet
<Gallery />
(CivitAI)
Model description
<h1 id="heading-45"><strong>All Disney Princess XL LoRA Model - Ralph Breaks the Internet</strong></h1><p>If You Like This Model, Give It a ❤️</p><p>This LoRA model is trained on screen capture images featuring beloved Disney princesses from the movie Ralph Breaks the Internet, including Rapunzel, Snow White, Ariel, Aurora, Belle, Cinderella, Elsa, Anna, Jasmine, Mulan, Merida, Tiana, Moana, and Pocahontas. It's designed to be an All-in-One Model for your creative endeavors.</p><p></p><p>Check out SD1.5 Version Here: <a target="_blank" rel="ugc" href="https://civitai.com/models/202866/all-princesses-from-disneys-ralph-2-ralph-breaks-the-internet-or-all-in-one-lora-model">https://civitai.com/models/202866/all-princesses-from-disneys-ralph-2-ralph-breaks-the-internet-or-all-in-one-lora-model</a></p><p></p><h2 id="heading-46"><strong>Bonus Characters</strong></h2><p>Additionally, this model includes representations of other characters like Vanellope, Shank, Raya, Namaari, Asha, and Rapunzel with short hair. While these extras are included, the quality may vary.</p><p></p><h2 id="heading-47"><strong>Quick Tips</strong></h2><ul><li><p><strong>Direct Name Usage</strong>: You can generate any princess by directly prompting their names, such as <code>Anna</code>, <code>Ariel</code>, <code>Aurora</code>, <code>Belle</code>, <code>Cinderella</code>, <code>Elsa</code>, <code>Asha</code>, <code>Jasmine</code>, <code>Merida</code>, <code>Moana</code>, <code>Mulan</code>, <code>Namaari</code>, <code>Pocahontas</code>, <code>Rapunzel</code>, <code>Raya</code>, <code>Shank</code>, <code>Snow White</code>, <code>Tiana</code>, <code>Vanellope</code>.</p><ul><li><p>More Character in v2 including: <code>Alice</code>, <code>Chel</code>,<code>Esmerada</code>, <code>Jane Porter</code>, <code>Kida</code>, <code>Megera</code>,<code>Mirabel Madrigal</code>, <code>Isabela Madrigal</code>, <code>Dolores Madrigal</code> and some secret character! </p></li></ul></li><li><p><strong>LoRA Scale</strong>: Optimal LoRA scales range between 0.6-0.7 for close-up character generation and 0.3-0.5 for full-body generation. Combining these scales using the ADetailer plugin can yield enhanced results. Ensure an adequate number of sampling steps for better output.</p></li><li><p><strong>Base Models</strong>: Although various base models can function, models with animation styles like DreamShaper or RealCartoon are preferred for optimal performance.</p></li></ul><p>Enjoy exploring the LoRA!</p>
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Use it with the 🧨 diffusers library
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('sWizad/all-disney-princess-xl-lora-model-from-ralph-breaks-the-internet', weight_name='princess_xl_v2.safetensors')
image = pipeline('Jasmine, ,').images[0]For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers