JunkieMonkey69's picture
initial commit
609a9af verified
|
Raw History Blame Contribute Delete
9.45 kB
---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- output:
url: images/Image01_00380_.png
text: >-
A Caucasian woman, Stefanie, with hazel eyes, high cheekbones and dimples.
Ultra-detailed lifestyle portrait of a graceful woman sitting at an outdoor
Parisian café with a perfect view of the Eiffel Tower under a bright blue
sky with soft clouds. She is wearing a sophisticated white halter dress with
a flowing silhouette, styled with pearl earrings and a gold wristwatch,
radiating timeless elegance. Her long dark hair cascades over her shoulder
in soft waves, catching natural sunlight that highlights her warm smile and
glowing complexion. The table is set with crystal-clear wine glasses,
cutlery, and a crisp white tablecloth, creating a refined dining atmosphere.
The lush green hedge frames the scene, contrasting with the metallic lattice
of the Eiffel Tower in the background. Captured in natural daylight, the
textures are crisp and realistic: the smooth fabric of the dress, the
sparkle of jewelry, the reflective surfaces of the glassware, and the sharp
architectural lines of the tower. High-fashion editorial meets cinematic
travel photography style, Parisian romance aesthetic, 8K resolution.
- output:
url: images/Image01_00376_.png
text: >-
A Caucasian woman, Stefanie, with hazel eyes, high cheekbones and dimples.
Black and white cinematic editorial portrait, retro Vogue aesthetic. A
person with long flowing platinum blonde hair, dramatic fringe, wearing a
delicate fringed white dress. Motion blur in the hair and fabric, ethereal
soft grainy texture, high-contrast studio lighting, moody and mysterious
atmosphere. Shot on vintage film, fashion photography style, dreamy and
surreal, 1970s retro glamour. Ultra-detailed, sharp focus on eyes and hair,
artistic film grain, textured skin,
- output:
url: images/Image01_00378_.png
text: >-
A Caucasian woman, Stefanie, with hazel eyes, high cheekbones and dimples.
The shot captures a moment of gentle serenity and natural splendor. The
woman is lying down, turning her head toward the camera, her expressive gaze
with slight thoughtfulness drawing attention. The skin glows with a soft
radiance, emphasizing delicate features and fine structure. Abundant black
hair is spread out freely, creating a velvety veil with a silky texture. She
is wearing a voluminous fur jacket in warm brownish tones with thick fluffy
wool, the shades of which are visible in highlights and shadows, creating
depth around the figure. Light from the top-left softly defines the contours
of the face and the texture of the fur, making the frame three-dimensional
and lifelike. The background of light fabric with a barely perceptible
structure contrasts with the rich colors and focuses attention on the model.
The composition concentrates on deep emotion.
- output:
url: images/Image01_00373_.png
text: >-
A Caucasian woman, Stefanie, with hazel eyes, high cheekbones and dimples.
Portrait of a young woman in a cozy, intimate setting, with an emphasis on
dramatic natural lighting. Woman details: A young woman is sitting, hugging
her knees pulled up to her chest with her arms. She is wearing a voluminous,
thick knitted sweater with a chunky knit in dark gray or graphite color.
Below the sweater, clothing is not visible, creating a sense of relaxation
or home comfort. On her right leg (which is visible), she is wearing a white
short sock with a black swoosh or logo resembling Nike. The woman has wavy
or curly hair that falls freely around her face and shoulders, partially
covering one side of her face. Her gaze is directed straight into the
camera, her facial expression serious, thoughtful, or slightly melancholic.
On the fingers of both hands (visible) there are several thin gold or silver
rings. Do not change facial features. Pose and composition: The woman
occupies most of the frame, shot at eye level, possibly slightly from below,
which adds a sense of mystery. Her pose is cozy and closed, but her gaze is
direct and open. Her arms are intertwined around her knees, creating a line
that leads the viewer’s eye to her face. Lighting: The main feature of the
image is strong, dramatic side natural lighting. Bright sunlight falls from
the right side (relative to the viewer), creating sharp shadows on the left
side of the woman’s face and body. The face is partially lit with golden
light and partially immersed in deep shadow, emphasizing contours and adding
volume. The shadows are soft but expressive. A light source is visible
behind her, creating a subtle rim light on the hair. Environment
(background): The background is blurred and consists of light, almost white,
semi-transparent curtains or drapes near a window through which the light
enters. A silhouette of a window frame or another object behind the curtains
may be visible, also blurred. This creates a soft, airy background that does
not distract from the main subject. The overall color palette is warm,
dominated by beige, cream, gray, and golden tones. Mood and style:
Introspective, melancholic, cozy, intimate, natural, cinematic. The
aesthetic of a home portrait with elements of fashion photography thanks to
the stylish sweater and socks. High image quality, clean details, possibly
light film grain.
- output:
url: images/Image01_00375_.png
text: >-
A Caucasian woman, Stefanie, with hazel eyes, high cheekbones and dimples.
A cozy indoor portrait of a woman sitting on a soft cream-textured chair in
a minimal modern living room. Pose: relaxed, one arm propped against the
side of her head, elbow resting, the other arm draped naturally; legs pulled
up casually toward the chest. Hair: sleek straight hairstyle with a middle
parting and two soft front face-framing strands, length tucked behind the
shoulders. Outfit: oversized off-shoulder knitted sweater and matching wide
knit pants in neutral cream tones; sleeves long and loose covering part of
the hands. Lighting: soft diffused natural daylight from a window, smooth
shadows, clean highlights on skin and fabric. Camera: medium close-up,
eye-level angle, slight forward lean toward the lens, sharp focus on the
face and upper body, blurred minimal background with a tall mirror and white
cabinetry. Mood: calm, warm, effortless luxury, quiet at-home elegance.
base_model: Tongyi-MAI/Z-Image-Turbo
instance_prompt: null
license: apache-2.0
---
# Stefanie_Joosten
<Gallery />
## Model description
🧩 **LoRA Name:** **Stefanie_Character**
&gt; Base Model: Tongyi-MAI &#x2F; Z-Image-Turbo
&gt; LoRA Type: Character &#x2F; Original Person
&gt; Trigger Word(s): Stefanie *(name-based prompting recommended)*
&gt; Recommended Weight: 0.6 – 0.85 (sweet spot ≈ 0.75)
---
✨ **Overview**
&gt; This LoRA is trained to capture the facial identity, proportions, and expressive range of **Stefanie**, focusing on natural realism and emotionally grounded presence. Optimized for ZimageTurbo, it preserves consistent likeness across casual, cinematic, and lifestyle-oriented scenes, with particular strength in intimate portraits and urban night settings.
The model balances softness and realism, rendering natural skin texture, subtle expressions, and believable body language, making it well suited for narrative portraits, candid moments, and cinematic lifestyle imagery.
---
🎨 **What This LoRA Is Good At**
&gt; Consistent facial identity with hazel eyes, high cheekbones, and dimples
&gt; Natural skin texture with soft, realistic lighting response
&gt; Strong performance in both indoor lifestyle and night-time urban scenes
&gt; Expressive, candid poses with relaxed body language
&gt; Works well for cinematic, casual, and emotional portrait compositions
---
⚙️ **Usage Notes**
&gt; Best results with portrait, mid-shot, and upper-body framing
&gt; Prompting **“Stefanie”** is sufficient; avoid stacking other strong character LoRAs
&gt; Performs especially well with soft lighting, city bokeh, and intimate indoor setups
&gt; Guidance scale ≤ 1 is recommended for native ZimageTurbo behavior
---
🧪 **Example Prompt**
Stefanie, cinematic portrait, soft ambient light,
natural expression, shallow depth of field, realistic skin texture
---
📐 **Training Details**
&gt; Dataset Size: 37 images (fully captioned)
&gt; Training Resolutions: 512 &#x2F; 768
&gt; Total Steps: 3,700
&gt; Batch Size: 1
&gt; Content vs Style: Balanced
&gt; Noise Scheduler: FlowMatch
&gt; Optimizer: AdamW 8-bit
&gt; Learning Rate: 1e-4
&gt; Precision: BF16
&gt; Text Encoder Training: Disabled
&gt; UNet Training: Enabled
&gt; Quantization: QFloat8 (model + text encoder)
&gt; Architecture: ZImage Turbo LoRA (LoKR full-rank enabled)
---
⚠️ **Limitations &#x2F; Notes**
&gt; Not intended for anime or heavily stylized cartoon outputs
&gt; Extreme facial distortion or exaggerated wide-angle lenses may reduce likeness
&gt; Heavy glam makeup or extreme fashion styling may reduce character fidelity
## Download model
[Download](/JunkieMonkey69/StefanieJoosten_ZimageTurbo/tree/main) them in the Files & versions tab.