metadata

library_name: diffusers
license: openrail++
language:
  - en
tags:
  - text-to-image
  - stable-diffusion
  - lora
  - safetensors
  - stable-diffusion-xl
base_model: Linaqruf/animagine-xl-2.0
widget:
  - text: >-
      face focus, cute, masterpiece, best quality, 1girl, green hair, sweater,
      looking at viewer, upper body, beanie, outdoors, night, turtleneck
    parameter:
      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
    example_title: 1girl
  - text: >-
      face focus, bishounen, masterpiece, best quality, 1boy, green hair,
      sweater, looking at viewer, upper body, beanie, outdoors, night,
      turtleneck
    parameter:
      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
    example_title: 1boy

Style Enhancer XL LoRA

Twilight Whispers

"A serene gaze into the dusky lights"

Bloom of Youth

"Amidst the dance of petals and sunbeams"

Starry-eyed Dreams

"Lost in the constellation of imagination"

Sunset Serenade

"A fiery glance that kindles the heart"

Overview

Style Enhancer XL LoRA is a high resolution, LoRA adapter for Animagine XL 2.0. The model has been fine-tuned using a curated dataset of superior-quality anime-style images.

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

Model Details

Developed by: Linaqruf
Model type: LoRA adapter
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. This adapter can enhance Animagine XL 2.0 style and also get old-school SD 1.5 anime model artstyle.
License: CreativeML Open RAIL++-M License
Finetuned from model: Animagine XL 2.0

🧨 Diffusers

Make sure to upgrade diffusers to >= 0.23.0:

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 (The default scheduler for Animagine XL 2.0 is EulerAncestralDiscreteScheduler but you may also declare it in the code if you want to make sure)*:

import torch
from diffusers import (
    StableDiffusionXLPipeline, 
    EulerAncestralDiscreteScheduler,
    AutoencoderKL
)

lora_model_id = "Linaqruf/style-enhancer-xl-lora"
lora_filename = "style-enhancer-xl.safetensors"

vae = AutoencoderKL.from_pretrained(
    "madebyollin/sdxl-vae-fp16-fix", 
    torch_dtype=torch.float16
)

pipe = StableDiffusionXLPipeline.from_pretrained(
    "Linaqruf/animagine-xl-2.0", 
    vae=vae,
    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)
pipe.fuse_lora(lora_scale=0.6)

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,
    num_inference_steps=50
).images[0]

pipe.unfuse_lora()

image.save("anime_girl.png")

Limitation

This model inherit Stable Diffusion XL 1.0 limitation