metadata
language:
- en
license: other
license_name: flux-1-dev-non-commercial-license
license_link: LICENSE.md
library_name: diffusers
pipeline_tag: text-to-image
tags:
- text-to-image
- image-generation
- shuttle
widget:
- text: >-
a sexy girl,poses,look at camera,Slim figure, gigantic
breasts,poses,natural,High-quality photography, creative composition,
fashion foresight, a strong visual style, and an aura of luxury and
sophistication collectively define the distinctive aesthetic of Vogue
magazine.
output:
url: assets/t1.webp
- text: real model slight smile girl in real life
output:
url: assets/t2.webp
instance_prompt: null
DarkIdol-flux-v1.2
- Online Test https://huggingface.co/spaces/aifeifei798/DarkIdol-flux
- Online Test https://huggingface.co/spaces/aifeifei798/allinone-DarkIdol-flux
896 x 1152 (8 steps) 
a sexy girl,poses,look at camera,Slim figure, gigantic breasts,poses,natural,High-quality photography, creative composition, fashion foresight, a strong visual style, and an aura of luxury and sophistication collectively define the distinctive aesthetic of Vogue magazine.
Inference code
from diffusers import FluxPipeline
import torch
import numpy as np
MAX_SEED = np.iinfo(np.int32).max
seed = random.randint(0, MAX_SEED)
generator = torch.Generator().manual_seed(seed)
pipeline = FluxPipeline.from_pretrained(
"aifeifei798/DarkIdol-flux-v1.2", torch_dtype=torch.bfloat16
).to("cuda")
# Enable VAE big pic
pipeline.vae.enable_slicing()
pipeline.vae.enable_tiling()
image = pipeline(
prompt="real model slight smile girl in real life",
guidance_scale=0,
num_inference_steps=9,
height=1152,
width=896,
max_sequence_length=512,
generator=generator,
).images[0]
image.save("DarkIdol.png")
