metadata

license: other
license_name: bespoke-lora-trained-license
license_link: >-
  https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=RentCivit&allowDerivatives=True&allowDifferentLicense=True
tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - template:sd-lora
  - migrated
  - character
  - photorealistic
  - sexy
  - woman
  - girls
  - realistic
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Sexy girl
widget:
  - text: ' '
    parameters:
      negative_prompt: text, watermark，Blurring, blurring,depth of field，anime
    output:
      url: 26655170.jpeg
  - text: ' '
    parameters:
      negative_prompt: text, watermark，Blurring, blurring,depth of field，anime
    output:
      url: 26655193.jpeg
  - text: ' '
    parameters:
      negative_prompt: text, watermark，Blurring, blurring,depth of field，anime
    output:
      url: 26655023.jpeg
  - text: ' '
    parameters:
      negative_prompt: text, watermark，Blurring, blurring,depth of field，anime
    output:
      url: 26655122.jpeg
  - text: ' '
    parameters:
      negative_prompt: text, watermark，Blurring, blurring,depth of field，anime
    output:
      url: 26655301.jpeg

Asian beauty - Flux Lora

Prompt

Negative Prompt
text, watermark，Blurring, blurring,depth of field，anime

Model description

Tag word is: Sexy girl,
A Flux Dev Lora of Sexy Asian beauty. Works best at 0.7~1.5 weight,About 0.9 is a good weight, will have a good generalization effect, sampler 40 steps will have a good effect. Recommended sampler: enlar a, scheduler: beta,cfg: 1~3, common size: 1024*1024*1536

Trigger words

You should use Sexy girl 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

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/asian-beauty-flux-lora', weight_name='Sexy_Asian_beauty_lora.safetensors')
image = pipeline('`Sexy girl`').images[0]

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