Sampling: LMS/IPNDM/IPNDM_V for best skin texture or EULER for smoother skin
Weight: 0.8-1.0
Sampling Steps: 20-25 closeup, 25-30 half body/upper body, 30-35 full body
HiRes Fix. with Denoise strength 0.15-0.2 closeup, 0.2-0.25 half body/upper body, 0.25-0.3 full body
Adetailer Inpaint Denoise strength 0.2-0.3, only needed for 3/4 to full body

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Keltezaa/hanni-makina-flux', weight_name='makinaflux_hanni_v1.0.safetensors')
image = pipeline('a petite young asian woman  posing in a stylish and coordinated outfit. She is wearing a white sleeveless crop top paired with a matching white mini skirt, creating a chic and fashionable look. The top features a black and white tie with "Chanel" branding, adding a luxurious touch to the ensemble. Her long hair is styled in two high pigtails, decorated with accessories, giving her a youthful and trendy appearance. The background is minimalistic, with gray walls, keeping the focus on her outfit and pose. Her expression is neutral and poised, suggesting a confident and composed attitude.. ,, . , looking at camera').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers