How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("wavespeed-ai/z-image", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("D33pStateTech/aznten_Z-image_lora")

prompt = "aznten, 35mm film photography style, a photo taken on an iPhone 17 perspective. A confident and charming woman standing in a high-end luxury bar, wearing a form-fitting, elegant black short dress with thin shoulder straps. She is looking directly into the camera with a subtle, confident smile.   The indoor lighting is bright and dramatic, featuring strong light reflections, direct flash highlights on natural skin textures, and smooth transitions into dark shadows, creating a cinematic atmosphere.   Background features a sophisticated bar, crystal chandeliers, metallic accents, and rich dark wooden furniture. Shallow depth of field with a softly blurred background, slight film grain, fine noise, realistic texture, and rich lighting layers. High realism, photorealistic detail."
image = pipe(prompt).images[0]

aznten_Z-image_lora

Prompt
aznten, 35mm film photography style, a photo taken on an iPhone 17 perspective. A confident and charming woman standing in a high-end luxury bar, wearing a form-fitting, elegant black short dress with thin shoulder straps. She is looking directly into the camera with a subtle, confident smile. The indoor lighting is bright and dramatic, featuring strong light reflections, direct flash highlights on natural skin textures, and smooth transitions into dark shadows, creating a cinematic atmosphere. Background features a sophisticated bar, crystal chandeliers, metallic accents, and rich dark wooden furniture. Shallow depth of field with a softly blurred background, slight film grain, fine noise, realistic texture, and rich lighting layers. High realism, photorealistic detail.

Model description

a character lora for an asian woman used in T2I on Z-image

Trigger words

You should use aznten to trigger the image generation.

Download model

Download them in the Files & versions tab.

Downloads last month
21
Inference Examples
Examples
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support