by Lykon
Open source · 16k downloads · 24 likes
AAM XL AnimeMix is an AI model specialized in generating stylized images in the style of Japanese anime and manga, based on Stable Diffusion technology. It excels at creating detailed illustrations, characters, and scenes inspired by the anime universe, featuring vibrant colors and distinctive traits. This model is ideal for artists, content creators, or enthusiasts looking to quickly produce high-quality visuals without advanced drawing skills. What sets it apart is its ability to generate coherent and aesthetically pleasing images from text prompts while offering flexibility to adjust the style as needed. It caters to both personal projects and commercial applications, all within the framework of a dedicated ethical license.
Lykon/AAM_XL_AnimeMix is a Stable Diffusion model that has been fine-tuned on stabilityai/stable-diffusion-xl-base-1.0.
Please consider supporting me:
License: Fair AI Public License 1.0-SD
For more general information on how to run text-to-image models with 🧨 Diffusers, see the docs.
pip install diffusers transformers accelerate
from diffusers import AutoPipelineForText2Image, DEISMultistepScheduler
import torch
pipe = AutoPipelineForText2Image.from_pretrained('Lykon/AAM_XL_AnimeMix', torch_dtype=torch.float16, variant="fp16")
pipe.scheduler = DEISMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to("cuda")
prompt = "anime girl, night, blue light behind her, ((Galaxy, Lens flare)), short hair, flower field, night sky, cinematic shot. Wallpaper. (Blue color schema), detailed background, a city in the distance"
generator = torch.manual_seed(0)
image = pipe(prompt, num_inference_steps=25).images[0]
image.save("./image.png")
