Instructions to use JunkieMonkey69/StefanieJoosten_ZimageTurbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use JunkieMonkey69/StefanieJoosten_ZimageTurbo 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("JunkieMonkey69/StefanieJoosten_ZimageTurbo") prompt = "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." image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Commit ·
609a9af
verified ·
0
Parent(s):
initial commit
Browse files- .gitattributes +55 -0
- README.md +185 -0
.gitattributes
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.lz4 filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
# Audio files - uncompressed
|
| 38 |
+
*.pcm filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
*.sam filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
*.raw filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
# Audio files - compressed
|
| 42 |
+
*.aac filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
*.flac filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
*.mp3 filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
*.ogg filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
*.wav filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
# Image files - uncompressed
|
| 48 |
+
*.bmp filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
*.gif filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
*.png filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
*.tiff filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
# Image files - compressed
|
| 53 |
+
*.jpg filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
*.jpeg filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
*.webp filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- text-to-image
|
| 4 |
+
- lora
|
| 5 |
+
- diffusers
|
| 6 |
+
- template:diffusion-lora
|
| 7 |
+
widget:
|
| 8 |
+
- output:
|
| 9 |
+
url: images/Image01_00380_.png
|
| 10 |
+
text: >-
|
| 11 |
+
A Caucasian woman, Stefanie, with hazel eyes, high cheekbones and dimples.
|
| 12 |
+
Ultra-detailed lifestyle portrait of a graceful woman sitting at an outdoor
|
| 13 |
+
Parisian café with a perfect view of the Eiffel Tower under a bright blue
|
| 14 |
+
sky with soft clouds. She is wearing a sophisticated white halter dress with
|
| 15 |
+
a flowing silhouette, styled with pearl earrings and a gold wristwatch,
|
| 16 |
+
radiating timeless elegance. Her long dark hair cascades over her shoulder
|
| 17 |
+
in soft waves, catching natural sunlight that highlights her warm smile and
|
| 18 |
+
glowing complexion. The table is set with crystal-clear wine glasses,
|
| 19 |
+
cutlery, and a crisp white tablecloth, creating a refined dining atmosphere.
|
| 20 |
+
The lush green hedge frames the scene, contrasting with the metallic lattice
|
| 21 |
+
of the Eiffel Tower in the background. Captured in natural daylight, the
|
| 22 |
+
textures are crisp and realistic: the smooth fabric of the dress, the
|
| 23 |
+
sparkle of jewelry, the reflective surfaces of the glassware, and the sharp
|
| 24 |
+
architectural lines of the tower. High-fashion editorial meets cinematic
|
| 25 |
+
travel photography style, Parisian romance aesthetic, 8K resolution.
|
| 26 |
+
- output:
|
| 27 |
+
url: images/Image01_00376_.png
|
| 28 |
+
text: >-
|
| 29 |
+
A Caucasian woman, Stefanie, with hazel eyes, high cheekbones and dimples.
|
| 30 |
+
Black and white cinematic editorial portrait, retro Vogue aesthetic. A
|
| 31 |
+
person with long flowing platinum blonde hair, dramatic fringe, wearing a
|
| 32 |
+
delicate fringed white dress. Motion blur in the hair and fabric, ethereal
|
| 33 |
+
soft grainy texture, high-contrast studio lighting, moody and mysterious
|
| 34 |
+
atmosphere. Shot on vintage film, fashion photography style, dreamy and
|
| 35 |
+
surreal, 1970s retro glamour. Ultra-detailed, sharp focus on eyes and hair,
|
| 36 |
+
artistic film grain, textured skin,
|
| 37 |
+
- output:
|
| 38 |
+
url: images/Image01_00378_.png
|
| 39 |
+
text: >-
|
| 40 |
+
A Caucasian woman, Stefanie, with hazel eyes, high cheekbones and dimples.
|
| 41 |
+
The shot captures a moment of gentle serenity and natural splendor. The
|
| 42 |
+
woman is lying down, turning her head toward the camera, her expressive gaze
|
| 43 |
+
with slight thoughtfulness drawing attention. The skin glows with a soft
|
| 44 |
+
radiance, emphasizing delicate features and fine structure. Abundant black
|
| 45 |
+
hair is spread out freely, creating a velvety veil with a silky texture. She
|
| 46 |
+
is wearing a voluminous fur jacket in warm brownish tones with thick fluffy
|
| 47 |
+
wool, the shades of which are visible in highlights and shadows, creating
|
| 48 |
+
depth around the figure. Light from the top-left softly defines the contours
|
| 49 |
+
of the face and the texture of the fur, making the frame three-dimensional
|
| 50 |
+
and lifelike. The background of light fabric with a barely perceptible
|
| 51 |
+
structure contrasts with the rich colors and focuses attention on the model.
|
| 52 |
+
The composition concentrates on deep emotion.
|
| 53 |
+
- output:
|
| 54 |
+
url: images/Image01_00373_.png
|
| 55 |
+
text: >-
|
| 56 |
+
A Caucasian woman, Stefanie, with hazel eyes, high cheekbones and dimples.
|
| 57 |
+
Portrait of a young woman in a cozy, intimate setting, with an emphasis on
|
| 58 |
+
dramatic natural lighting. Woman details: A young woman is sitting, hugging
|
| 59 |
+
her knees pulled up to her chest with her arms. She is wearing a voluminous,
|
| 60 |
+
thick knitted sweater with a chunky knit in dark gray or graphite color.
|
| 61 |
+
Below the sweater, clothing is not visible, creating a sense of relaxation
|
| 62 |
+
or home comfort. On her right leg (which is visible), she is wearing a white
|
| 63 |
+
short sock with a black swoosh or logo resembling Nike. The woman has wavy
|
| 64 |
+
or curly hair that falls freely around her face and shoulders, partially
|
| 65 |
+
covering one side of her face. Her gaze is directed straight into the
|
| 66 |
+
camera, her facial expression serious, thoughtful, or slightly melancholic.
|
| 67 |
+
On the fingers of both hands (visible) there are several thin gold or silver
|
| 68 |
+
rings. Do not change facial features. Pose and composition: The woman
|
| 69 |
+
occupies most of the frame, shot at eye level, possibly slightly from below,
|
| 70 |
+
which adds a sense of mystery. Her pose is cozy and closed, but her gaze is
|
| 71 |
+
direct and open. Her arms are intertwined around her knees, creating a line
|
| 72 |
+
that leads the viewer’s eye to her face. Lighting: The main feature of the
|
| 73 |
+
image is strong, dramatic side natural lighting. Bright sunlight falls from
|
| 74 |
+
the right side (relative to the viewer), creating sharp shadows on the left
|
| 75 |
+
side of the woman’s face and body. The face is partially lit with golden
|
| 76 |
+
light and partially immersed in deep shadow, emphasizing contours and adding
|
| 77 |
+
volume. The shadows are soft but expressive. A light source is visible
|
| 78 |
+
behind her, creating a subtle rim light on the hair. Environment
|
| 79 |
+
(background): The background is blurred and consists of light, almost white,
|
| 80 |
+
semi-transparent curtains or drapes near a window through which the light
|
| 81 |
+
enters. A silhouette of a window frame or another object behind the curtains
|
| 82 |
+
may be visible, also blurred. This creates a soft, airy background that does
|
| 83 |
+
not distract from the main subject. The overall color palette is warm,
|
| 84 |
+
dominated by beige, cream, gray, and golden tones. Mood and style:
|
| 85 |
+
Introspective, melancholic, cozy, intimate, natural, cinematic. The
|
| 86 |
+
aesthetic of a home portrait with elements of fashion photography thanks to
|
| 87 |
+
the stylish sweater and socks. High image quality, clean details, possibly
|
| 88 |
+
light film grain.
|
| 89 |
+
- output:
|
| 90 |
+
url: images/Image01_00375_.png
|
| 91 |
+
text: >-
|
| 92 |
+
A Caucasian woman, Stefanie, with hazel eyes, high cheekbones and dimples.
|
| 93 |
+
A cozy indoor portrait of a woman sitting on a soft cream-textured chair in
|
| 94 |
+
a minimal modern living room. Pose: relaxed, one arm propped against the
|
| 95 |
+
side of her head, elbow resting, the other arm draped naturally; legs pulled
|
| 96 |
+
up casually toward the chest. Hair: sleek straight hairstyle with a middle
|
| 97 |
+
parting and two soft front face-framing strands, length tucked behind the
|
| 98 |
+
shoulders. Outfit: oversized off-shoulder knitted sweater and matching wide
|
| 99 |
+
knit pants in neutral cream tones; sleeves long and loose covering part of
|
| 100 |
+
the hands. Lighting: soft diffused natural daylight from a window, smooth
|
| 101 |
+
shadows, clean highlights on skin and fabric. Camera: medium close-up,
|
| 102 |
+
eye-level angle, slight forward lean toward the lens, sharp focus on the
|
| 103 |
+
face and upper body, blurred minimal background with a tall mirror and white
|
| 104 |
+
cabinetry. Mood: calm, warm, effortless luxury, quiet at-home elegance.
|
| 105 |
+
base_model: Tongyi-MAI/Z-Image-Turbo
|
| 106 |
+
instance_prompt: null
|
| 107 |
+
license: apache-2.0
|
| 108 |
+
---
|
| 109 |
+
# Stefanie_Joosten
|
| 110 |
+
|
| 111 |
+
<Gallery />
|
| 112 |
+
|
| 113 |
+
## Model description
|
| 114 |
+
|
| 115 |
+
🧩 **LoRA Name:** **Stefanie_Character**
|
| 116 |
+
|
| 117 |
+
> Base Model: Tongyi-MAI / Z-Image-Turbo
|
| 118 |
+
> LoRA Type: Character / Original Person
|
| 119 |
+
> Trigger Word(s): Stefanie *(name-based prompting recommended)*
|
| 120 |
+
> Recommended Weight: 0.6 – 0.85 (sweet spot ≈ 0.75)
|
| 121 |
+
|
| 122 |
+
---
|
| 123 |
+
|
| 124 |
+
✨ **Overview**
|
| 125 |
+
|
| 126 |
+
> 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.
|
| 127 |
+
|
| 128 |
+
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.
|
| 129 |
+
|
| 130 |
+
---
|
| 131 |
+
|
| 132 |
+
🎨 **What This LoRA Is Good At**
|
| 133 |
+
|
| 134 |
+
> Consistent facial identity with hazel eyes, high cheekbones, and dimples
|
| 135 |
+
> Natural skin texture with soft, realistic lighting response
|
| 136 |
+
> Strong performance in both indoor lifestyle and night-time urban scenes
|
| 137 |
+
> Expressive, candid poses with relaxed body language
|
| 138 |
+
> Works well for cinematic, casual, and emotional portrait compositions
|
| 139 |
+
|
| 140 |
+
---
|
| 141 |
+
|
| 142 |
+
⚙️ **Usage Notes**
|
| 143 |
+
|
| 144 |
+
> Best results with portrait, mid-shot, and upper-body framing
|
| 145 |
+
> Prompting **“Stefanie”** is sufficient; avoid stacking other strong character LoRAs
|
| 146 |
+
> Performs especially well with soft lighting, city bokeh, and intimate indoor setups
|
| 147 |
+
> Guidance scale ≤ 1 is recommended for native ZimageTurbo behavior
|
| 148 |
+
|
| 149 |
+
---
|
| 150 |
+
|
| 151 |
+
🧪 **Example Prompt**
|
| 152 |
+
Stefanie, cinematic portrait, soft ambient light,
|
| 153 |
+
natural expression, shallow depth of field, realistic skin texture
|
| 154 |
+
|
| 155 |
+
---
|
| 156 |
+
|
| 157 |
+
📐 **Training Details**
|
| 158 |
+
|
| 159 |
+
> Dataset Size: 37 images (fully captioned)
|
| 160 |
+
> Training Resolutions: 512 / 768
|
| 161 |
+
> Total Steps: 3,700
|
| 162 |
+
> Batch Size: 1
|
| 163 |
+
> Content vs Style: Balanced
|
| 164 |
+
> Noise Scheduler: FlowMatch
|
| 165 |
+
> Optimizer: AdamW 8-bit
|
| 166 |
+
> Learning Rate: 1e-4
|
| 167 |
+
> Precision: BF16
|
| 168 |
+
> Text Encoder Training: Disabled
|
| 169 |
+
> UNet Training: Enabled
|
| 170 |
+
> Quantization: QFloat8 (model + text encoder)
|
| 171 |
+
> Architecture: ZImage Turbo LoRA (LoKR full-rank enabled)
|
| 172 |
+
|
| 173 |
+
---
|
| 174 |
+
|
| 175 |
+
⚠️ **Limitations / Notes**
|
| 176 |
+
|
| 177 |
+
> Not intended for anime or heavily stylized cartoon outputs
|
| 178 |
+
> Extreme facial distortion or exaggerated wide-angle lenses may reduce likeness
|
| 179 |
+
> Heavy glam makeup or extreme fashion styling may reduce character fidelity
|
| 180 |
+
|
| 181 |
+
|
| 182 |
+
## Download model
|
| 183 |
+
|
| 184 |
+
|
| 185 |
+
[Download](/JunkieMonkey69/StefanieJoosten_ZimageTurbo/tree/main) them in the Files & versions tab.
|