Diffusers How to use AIImageStudio/RadianceChromeVoluptuous_z_image_turbo_v1.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Tongyi-MAI/Z-Image-Turbo", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("AIImageStudio/RadianceChromeVoluptuous_z_image_turbo_v1.0")
prompt = "grok film style, lighting and shadow effects, color cast, wrong white balance, expired film, wide angle,A Japanese beautiful woman with a curvy figure featuring prominent bust, slim waist, and long legs sits elegantly on an ornate floral-patterned velvet armchair in a vintage-style room; she wears a glossy black satin corset adorned with sparkling silver embellishments at the hip paired with sheer fishnet stockings that have lace trim around the thighs and garter straps; her dark brown hair is styled up in voluminous curls framing her face as she gazes directly into the camera with one hand gently touching near her temple while wearing delicate earrings; behind her stands a tall gold-framed floor lamp with two amber glass globes casting warm ambient lighting across the scene which highlights soft shadows under the chairâs arms and along her silhouette against the backdrop of pink-toned wallpaper decorated with rose motifs and a matching patterned rug beneath polished hardwood floors; the composition utilizes a medium close-up angle from slightly above eye level capturing her upper body to mid-thighs within a diagonally framed shot emphasizing depth through layered furniture including a reddish-pink bookshelf holding decorative objects; the overall color palette leans toward rich jewel tonesâdeep blacks, muted pinks, metallic gold accentsâwith balanced white balance enhancing skin tone realism without overpowering the dramatic warmth emitted by artificial illumination sources creating a luxurious yet intimate mood suitable for high-end fashion or sensual photography contexts."
image = pipe(prompt).images[0] 
