Commit ·
4c3fd0d
verified ·
0
Parent(s):
initial commit
Browse files- .gitattributes +55 -0
- README.md +131 -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 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- text-to-image
|
| 4 |
+
- lora
|
| 5 |
+
- diffusers
|
| 6 |
+
- template:diffusion-lora
|
| 7 |
+
widget:
|
| 8 |
+
- output:
|
| 9 |
+
url: images/1767136066194__000004600_1.jpg
|
| 10 |
+
text: >-
|
| 11 |
+
Hunter Schafer, The image is a high-resolution photograph of a young woman
|
| 12 |
+
with a pale, fair complexion, light blonde hair, and piercing blue eyes. Her
|
| 13 |
+
hair is slicked back, with a few loose strands framing her face. She is
|
| 14 |
+
wearing a pink hair clip on the right side, near the front, and another clip
|
| 15 |
+
on the left side, which holds back a section of her hair. The woman's
|
| 16 |
+
facial features are sharp and slightly angular, with a neutral expression.
|
| 17 |
+
Her skin is smooth with a slight sheen, and she has a few freckles on her
|
| 18 |
+
cheeks. She is wearing a multicolored, graphic T-shirt featuring a mix of
|
| 19 |
+
abstract patterns and monochrome images, including black, white, and various
|
| 20 |
+
shades of gray. The background of the image is a simple, plain brown wall,
|
| 21 |
+
which contrasts with the vibrant colors of her clothing. The wall appears to
|
| 22 |
+
be part of a hallway or backstage area, indicated by the presence of a
|
| 23 |
+
textured, speckled floor and a wooden door or panel visible at the top left
|
| 24 |
+
of the frame. The lighting is soft and even, casting minimal shadows,
|
| 25 |
+
focusing attention on her face and clothing. The overall mood of the
|
| 26 |
+
photograph is professional, likely taken for a fashion or editorial shoot.
|
| 27 |
+
- output:
|
| 28 |
+
url: images/1767136119022__000004600_2.jpg
|
| 29 |
+
text: >-
|
| 30 |
+
Hunter Schafer, The image is a high-resolution photograph of a young woman
|
| 31 |
+
with a striking, retro-inspired look. She has light, platinum blonde hair
|
| 32 |
+
styled in a voluminous, teased-updo, reminiscent of the 1960s. Her facial
|
| 33 |
+
features are youthful, with fair skin and a slightly pouty expression. She
|
| 34 |
+
is wearing dark, rectangular sunglasses with thin, gold frames, which she
|
| 35 |
+
holds up with both hands, her fingers adorned with long, bright red nail
|
| 36 |
+
polish. Her makeup is bold and dramatic, featuring heavy, winged eyeliner in
|
| 37 |
+
a striking blue color that extends beyond her eyes, giving her a
|
| 38 |
+
distinctive, edgy look. She is dressed in a colorful, geometric-patterned
|
| 39 |
+
sweater with blocks of red, green, and beige, which adds a playful contrast
|
| 40 |
+
to her serious expression. Around her neck, she wears a black scarf with
|
| 41 |
+
white text, possibly a band name or logo, cinched tightly at the back,
|
| 42 |
+
adding a punk-rock vibe to her outfit. The background is a dimly lit, indoor
|
| 43 |
+
setting, with a warm, neutral-toned wall and a glimpse of a ceiling light
|
| 44 |
+
fixture, suggesting she might be indoors, possibly at a fashion or music
|
| 45 |
+
event. The overall aesthetic combines elements of vintage, punk, and
|
| 46 |
+
avant-garde styles, creating a bold and edgy
|
| 47 |
+
- output:
|
| 48 |
+
url: images/Image01_00225_.png
|
| 49 |
+
text: >-
|
| 50 |
+
An ultra-realistic 8K cinematic studio portrait framed from mid-thigh up,
|
| 51 |
+
featuring a woman, Hunter schafer standing confidently against a vibrant
|
| 52 |
+
ochre-red background. The subject wears an oversized, highly textured bomber
|
| 53 |
+
jacket with an eclectic, abstract patchwork pattern in muted and vivid reds,
|
| 54 |
+
blues, greens, and beiges, paired with loose drab olive cargo pants and a
|
| 55 |
+
white T-shirt. Lighting is harsh and frontal, creating crisp shadows and
|
| 56 |
+
emphasizing fabric textures. Shot in a high-fashion editorial style with
|
| 57 |
+
sharp focus on the primary figure, shallow depth of field, and precise
|
| 58 |
+
studio realism, delivering a bold, experimental, avant-garde mood.
|
| 59 |
+
base_model: Tongyi-MAI/Z-Image-Turbo
|
| 60 |
+
instance_prompt: Hunter Schafer
|
| 61 |
+
license: apache-2.0
|
| 62 |
+
---
|
| 63 |
+
# HunterSchafer
|
| 64 |
+
|
| 65 |
+
<Gallery />
|
| 66 |
+
|
| 67 |
+
## Model description
|
| 68 |
+
|
| 69 |
+
🧩 LoRA Name: HunterSchafer_Actress
|
| 70 |
+
|
| 71 |
+
>Base Model: Tongyi-MAI / Z-Image-Turbo
|
| 72 |
+
>LoRA Type: Character / Actress
|
| 73 |
+
>Trigger Word(s): Hunter Schafer
|
| 74 |
+
>Recommended Weight: 0.65 – 0.85 (sweet spot ≈ 0.75)
|
| 75 |
+
|
| 76 |
+
✨ Overview
|
| 77 |
+
|
| 78 |
+
>This LoRA captures the distinctive facial structure, styling range, and editorial presence of Hunter Schafer, optimized for ZimageTurbo. It is trained to preserve identity consistency across varied fashion, lighting, and mood setups, performing well in both clean studio portraits and stylized editorial scenes.
|
| 79 |
+
|
| 80 |
+
The model balances realism with high-fashion expressiveness, making it suitable for portrait photography, magazine-style shoots, and cinematic close-ups.
|
| 81 |
+
|
| 82 |
+
🎨 What This LoRA Is Good At
|
| 83 |
+
|
| 84 |
+
>Strong facial identity retention across angles and lighting
|
| 85 |
+
>Editorial and fashion-oriented aesthetics
|
| 86 |
+
>Clean skin rendering with natural facial detail
|
| 87 |
+
>Works well with both minimal and stylized makeup
|
| 88 |
+
>Consistent results across portrait and mid-shot compositions
|
| 89 |
+
|
| 90 |
+
⚙️ Usage Notes
|
| 91 |
+
|
| 92 |
+
>Best results with portrait, upper-body, and editorial framing
|
| 93 |
+
>Prompting the name “Hunter Schafer” is sufficient; no extra trigger token required
|
| 94 |
+
>Avoid stacking multiple strong character LoRAs simultaneously
|
| 95 |
+
>Performs especially well with fashion, studio, and cinematic lighting prompts
|
| 96 |
+
|
| 97 |
+
🧪 Example Prompt
|
| 98 |
+
Hunter Schafer, high-fashion editorial portrait, soft studio lighting,
|
| 99 |
+
clean background, cinematic composition, detailed facial features
|
| 100 |
+
|
| 101 |
+
📐 Training Details
|
| 102 |
+
|
| 103 |
+
>Dataset Size: 46 images (fully captioned)
|
| 104 |
+
>Training Resolutions: 512 / 768 / 1024
|
| 105 |
+
>Total Steps: 4,600
|
| 106 |
+
>Batch Size: 1
|
| 107 |
+
>Content vs Style: Balanced
|
| 108 |
+
>Noise Scheduler: FlowMatch
|
| 109 |
+
>Optimizer: AdamW 8-bit
|
| 110 |
+
>Learning Rate: 1e-4
|
| 111 |
+
>Precision: BF16
|
| 112 |
+
>Text Encoder Training: Disabled
|
| 113 |
+
>UNet Training: Enabled
|
| 114 |
+
>Quantization: QFloat8 (model + text encoder)
|
| 115 |
+
>Architecture: ZImage Turbo LoRA (LoKR full-rank enabled)
|
| 116 |
+
|
| 117 |
+
⚠️ Limitations / Notes
|
| 118 |
+
|
| 119 |
+
>Not designed for anime or heavily stylized cartoon outputs
|
| 120 |
+
>Extreme fisheye angles or exaggerated facial distortion may reduce likeness
|
| 121 |
+
>Best results achieved with guidance scale ≤ 1 (ZimageTurbo native behavior)
|
| 122 |
+
|
| 123 |
+
## Trigger words
|
| 124 |
+
|
| 125 |
+
You should use `Hunter Schafer` to trigger the image generation.
|
| 126 |
+
|
| 127 |
+
|
| 128 |
+
## Download model
|
| 129 |
+
|
| 130 |
+
|
| 131 |
+
[Download](/JunkieMonkey69/HunterSchafer_ZimageTurbo/tree/main) them in the Files & versions tab.
|