CoolFace
Modelpublic

Keltezaa/flux-realistic-asian-girls-face-flux

sourceHugging Faceotherupdated 2y agoView on Hugging Face
12likes265downloads
Model Card

Flux | Realistic Asian girls face Flux

<Gallery />

Model description

<p><span style="color:rgba(255, 255, 255, 0.85)">This is a Realistic Asian Girls Portrait LORA of Flux.</span></p><p><span style="color:rgba(255, 255, 255, 0.85)">这是 Flux 的逼真亚洲女孩肖像 LORA。</span></p><p><span style="color:rgba(255, 255, 255, 0.85)">Recommended settings:</span></p><p><span style="color:rgba(255, 255, 255, 0.85)">推荐设置:</span></p><p><span style="color:rgba(255, 255, 255, 0.85)">Make sure you are aware on the usage instructions of LORA</span></p><p><span style="color:rgba(255, 255, 255, 0.85)">确保您了解 LORA 的使用说明</span></p><p><span style="color:rgba(255, 255, 255, 0.85)">Trigger Words:1girl</span></p><p><span style="color:rgba(255, 255, 255, 0.85)">触发词:1girl</span></p><p><span style="color:rgba(255, 255, 255, 0.85)">LORA weight for txt2img: anywhere between 0.6 to 0.1 are recommended</span></p><p><span style="color:rgba(255, 255, 255, 0.85)">txt2img 的 LORA 权重:建议介于 0.6 到 0.1 之间</span></p><p></p><p><em>If you enjoy it, feel free to share more of your creations.</em>🫰🏻<br /><em>如果您喜歡它,請隨意分享更多您的創作。</em> 🫰🏻</p><p><em>如果您喜欢它,请多分享更多您的创作。</em>🫰🏻<br /><em>如果您喜歡它,請多分享更多您的創作。</em> 🫰🏻</p>

Trigger words

You should use 1girl to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

py
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/flux-realistic-asian-girls-face-flux', weight_name='Flux  Realistic Asian girls face Flux_01.safetensors')
image = pipeline('`1girl`').images[0]

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