WiroAI Flux Models
Collection
WiroAI's plug-and-play image generation models • 30 items • Updated • 3
How to use WiroAI/Jihyo-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/Jihyo-Flux-LoRA")
prompt = "jihyowiro, A 20-year-old woman with long, wavy brown hair, standing by a sunlit window. Soft natural light gently illuminates her face, highlighting her deep brown eyes and smooth, freckled skin. She wears a simple white linen dress, and a gentle breeze moves her hair. The background is blurred, showing an airy, minimalistic room with houseplants, creating a warm and cozy atmosphere. Ultra HD, highly detailed, cinematic lighting, realistic skin texture."
image = pipe(prompt).images[0]How to use WiroAI/Jihyo-Flux-LoRA with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("WiroAI/Jihyo-Flux-LoRA", dtype="auto")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/Jihyo-Flux-LoRA")
prompt = "jihyowiro, A 20-year-old woman with long, wavy brown hair, standing by a sunlit window. Soft natural light gently illuminates her face, highlighting her deep brown eyes and smooth, freckled skin. She wears a simple white linen dress, and a gentle breeze moves her hair. The background is blurred, showing an airy, minimalistic room with houseplants, creating a warm and cozy atmosphere. Ultra HD, highly detailed, cinematic lighting, realistic skin texture."
image = pipe(prompt).images[0]
This LoRA is trained for anyone who like Jihyo from Twice.

You should use jihyowiro 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/Jihyo-Flux-LoRA', weight_name='jihyo_flux_lora.safetensors')
image = pipeline('jihyowiro, A 20-year-old woman with long, wavy brown hair, standing by a sunlit window. Soft natural light gently illuminates her face, highlighting her deep brown eyes and smooth, freckled skin. She wears a simple white linen dress, and a gentle breeze moves her hair. The background is blurred, showing an airy, minimalistic room with houseplants, creating a warm and cozy atmosphere. Ultra HD, highly detailed, cinematic lighting, realistic skin texture.').images[0]
image.save("output.png")
Base model
black-forest-labs/FLUX.1-dev