Linaqruf/pastel-anime-xl-lora

<style> .title-container { display: flex; flex-direction: column; / Allow vertical stacking of title and subtitle / justify-content: center; align-items: center; height: 100vh; background-color: #f5f5f5; }

.title { font-size: 2.5em; text-align: center; color: #333; font-family: 'Verdana', sans-serif; text-transform: uppercase; letter-spacing: 0.2em; padding: 1em; border: 2px solid #7ed56f; box-shadow: 5px 5px 15px rgba(0,0,0,0.1); }

.title span, .subtitle span { background: -webkit-linear-gradient(45deg, #ff9a9e, #fad0c4, #f6d365); -webkit-background-clip: text; -webkit-text-fill-color: transparent; }

.subtitle { margin-top: 15px; font-size: 1em; font-family: 'Verdana', sans-serif; color: #666; text-align: center; } .custom-table { table-layout: fixed; width: 100%; border-collapse: collapse; margin-top: 2em; } .custom-table td { width: 50%; vertical-align: top; padding: 10px; box-shadow: 0px 0px 10px 0px rgba(0,0,0,0.15); } .custom-image { width: 100%; height: auto; object-fit: cover; border-radius: 10px; transition: transform .2s; margin-bottom: 1em; } .custom-image:hover { transform: scale(1.05); } </style>

<h1 class="title"><span>Pastel Anime LoRA for SDXL</span></h1> <h2 class="subtitle"><span>TRAINED WITH </span><a href="https://huggingface.co/Linaqruf/animagine-xl"><span>ANIMAGINE XL</span></a></h2>

<hr>

<table class="custom-table"> <tr> <td> <a href="https://huggingface.co/Linaqruf/pastel-anime-xl-lora/blob/main/samples/xloutputupscaled00001.png"> <img class="custom-image" src="https://huggingface.co/Linaqruf/pastel-anime-xl-lora/resolve/main/samples/xloutputupscaled00001.png" alt="sample1"> </a> </td> <td> <a href="https://huggingface.co/Linaqruf/pastel-anime-xl-lora/blob/main/samples/xloutputupscaled00006.png"> <img class="custom-image" src="https://huggingface.co/Linaqruf/pastel-anime-xl-lora/resolve/main/samples/xloutputupscaled00006.png" alt="sample2"> </a> </td> </tr> </table>

<hr>

Overview

Pastel Anime LoRA for SDXL is a high-resolution, Low-Rank Adaptation model for Stable Diffusion XL. The model has been fine-tuned using a learning rate of 1e-5 over 1300 global steps with a batch size of 24 on a curated dataset of superior-quality anime-style images. This model is derived from Animagine XL.

Like other anime-style Stable Diffusion models, it also supports Danbooru tags to generate images.

e.g. **face focus, cute, masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck**

<hr>

Model Details

• —Developed by: Linaqruf
• —Model type: Low-rank adaptation of diffusion-based text-to-image generative model
• —Model Description: This is a small model that should be used with big model and can be used to generate and modify high quality anime-themed images based on text prompts.
• —License: CreativeML Open RAIL++-M License
• —Finetuned from model: Animagine XL

<hr>

🧨 Diffusers

Make sure to upgrade diffusers to >= 0.18.2:

pip install diffusers --upgrade

In addition make sure to install transformers, safetensors, accelerate as well as the invisible watermark:

pip install invisible_watermark transformers accelerate safetensors

Running the pipeline (if you don't swap the scheduler it will run with the default EulerDiscreteScheduler in this example we are swapping it to EulerAncestralDiscreteScheduler:

import torch
from torch import autocast
from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler

base_model = "Linaqruf/animagine-xl"
lora_model_id = "Linaqruf/pastel-anime-xl-lora"
lora_filename = "pastel-anime-xl.safetensors"

pipe = StableDiffusionXLPipeline.from_pretrained(
    model, 
    torch_dtype=torch.float16, 
    use_safetensors=True, 
    variant="fp16"
    )

pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
pipe.to('cuda')

pipe.load_lora_weights(lora_model_id, weight_name=lora_filename)

prompt = "face focus, cute, masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck"
negative_prompt = "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry"

image = pipe(
    prompt, 
    negative_prompt=negative_prompt, 
    width=1024,
    height=1024,
    guidance_scale=12,
    target_size=(1024,1024),
    original_size=(4096,4096),
    num_inference_steps=50
    ).images[0]

image.save("anime_girl.png")

<hr>

Limitation

This model inherit Stable Diffusion XL 1.0 limitation