LoRA
Collection
7 items • Updated
How to use bean980310/headswap-xl-animagine with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("cagliostrolab/animagine-xl-3.1", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("bean980310/headswap-xl-animagine")
prompt = "masterpiece, best quality, very aesthetic, absurdres, digital art, outdoors, cowboy shot, solo, a girl with the head of a boy and very handsome shortcut hair and very handsome face and perfect female body and large breasts wearing white and blue military uniform with epaulettes and aiguillette and (military white jacket with white long sleeves:1.4) and white buttoned shirt on top and (white lace trim bridal gloves:1.2) on hands and (white cape with shoulder cape:1.2) on shoulders and brown belt with gold belt buckle and (pleated blue miniskirt with white stripes:1.3) on bottom and (white thighhighs with floral lace trim:1.2) on legs and standing with legs together and gentle face"
image = pipe(prompt).images[0]import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("cagliostrolab/animagine-xl-3.1", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("bean980310/headswap-xl-animagine")
prompt = "masterpiece, best quality, very aesthetic, absurdres, digital art, outdoors, cowboy shot, solo, a girl with the head of a boy and very handsome shortcut hair and very handsome face and perfect female body and large breasts wearing white and blue military uniform with epaulettes and aiguillette and (military white jacket with white long sleeves:1.4) and white buttoned shirt on top and (white lace trim bridal gloves:1.2) on hands and (white cape with shoulder cape:1.2) on shoulders and brown belt with gold belt buckle and (pleated blue miniskirt with white stripes:1.3) on bottom and (white thighhighs with floral lace trim:1.2) on legs and standing with legs together and gentle face"
image = pipe(prompt).images[0]


a girl with boy's head
Trained on Animagine XL V3.1 with 343 images of generated images by 2590 steps and 10 epochs.
You should use a girl with the head of a boy to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Base model
stabilityai/stable-diffusion-xl-base-1.0