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("Tongyi-MAI/Z-Image", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("NiwWin/z-image-base-tzuyu-lora")

prompt = "asdf_wmn_tzuyu, Create a hyper-realistic 8K café-editorial fashion portrait of a young asian woman Pose & Framing:  Medium close-up or half-body shot. She leans back casually or stands near a café wall. One hand lightly touching her hair or sleeve. wissy Expression is calm, confident, and effortless.  Hair & Accessories:  Low loose ponytail or half-tied hairstyle.  Accessories: small gold hoop earrings or statement claw clip.  Outfit:  More styled look: soft structured blazer or cardigan over a fitted tank or top in muted café tones wissy (latte, oat, dusty pink).  Scene & Props:  Near a café counter or textured wall, holding a canvas tote bag.  Lighting & Style:  Natural side lighting, editorial contrast but still soft. wissy  Warm pastel grading, shallow depth of field, high-end Korean Gen-Z café aesthetic."
image = pipe(prompt).images[0]

tzuyu lora - z image base

Prompt
asdf_wmn_tzuyu, Create a hyper-realistic 8K café-editorial fashion portrait of a young asian woman Pose & Framing: Medium close-up or half-body shot. She leans back casually or stands near a café wall. One hand lightly touching her hair or sleeve. wissy Expression is calm, confident, and effortless. Hair & Accessories: Low loose ponytail or half-tied hairstyle. Accessories: small gold hoop earrings or statement claw clip. Outfit: More styled look: soft structured blazer or cardigan over a fitted tank or top in muted café tones wissy (latte, oat, dusty pink). Scene & Props: Near a café counter or textured wall, holding a canvas tote bag. Lighting & Style: Natural side lighting, editorial contrast but still soft. wissy Warm pastel grading, shallow depth of field, high-end Korean Gen-Z café aesthetic.

Trigger words

You should use asdf_wmn_tzuyu to trigger the image generation.

Download model

Download them in the Files & versions tab.

Downloads last month
165
Inference Examples
Examples
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for NiwWin/z-image-base-tzuyu-lora

Adapter
(144)
this model