WiroAI Flux Models
Collection
WiroAI's plug-and-play image generation models • 30 items • Updated • 3
How to use WiroAI/Sawako-Kuronuma-Flux-LoRA with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("WiroAI/Sawako-Kuronuma-Flux-LoRA")
prompt = "swkwiro, anime coloring, an anime girl, black hair, solo, long hair, school uniform, smile, black eyes, blush, looking at viewer, open mouth, bow, blazer, bangs, blunt bangs, upper body, shirt, red bow, bowtie, long sleeves, hime cut, waving at viewer"
image = pipe(prompt).images[0]How to use WiroAI/Sawako-Kuronuma-Flux-LoRA with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("WiroAI/Sawako-Kuronuma-Flux-LoRA", dtype="auto")
This LoRA is trained for anyone who like Sawako Kuronuma from Kimi ni Todoke.


You should use swkwiro to trigger the image generation.
from diffusers import FluxPipeline
import torch
pipeline = FluxPipeline.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('WiroAI/Sawako-Kuronuma-Flux-LoRA', weight_name='sawako_flux_lora.safetensors')
image = pipeline('swkwiro, anime coloring, an anime girl, black hair, solo, long hair, traditional Japanese kimono, gentle smile, deep brown eyes, cherry blossom background, looking at viewer, soft blush, elegant pose, floral hairpin, sakura petals, long sleeves, calm expression, serene lighting').images[0]
image.save("output.png")
Base model
black-forest-labs/FLUX.1-dev