Instructions to use jarod2212/PhysioShade_ZIT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use jarod2212/PhysioShade_ZIT 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("jarod2212/PhysioShade_ZIT") prompt = "-" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Commit ·
4b22b95
verified ·
0
Parent(s):
initial commit
Browse files- .gitattributes +55 -0
- README.md +163 -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 +1,163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- text-to-image
|
| 4 |
+
- lora
|
| 5 |
+
- diffusers
|
| 6 |
+
- template:diffusion-lora
|
| 7 |
+
widget:
|
| 8 |
+
- output:
|
| 9 |
+
url: images/Copilot_20260606_181357.png
|
| 10 |
+
text: '-'
|
| 11 |
+
- output:
|
| 12 |
+
url: images/3a777800030026b7d14495b865fcd167.jpg
|
| 13 |
+
text: '-'
|
| 14 |
+
- output:
|
| 15 |
+
url: images/3baaab95d9292c366c7bacd293024c5f.jpg
|
| 16 |
+
text: '-'
|
| 17 |
+
- output:
|
| 18 |
+
url: images/64a7ab0f9c78fcf6f3ffb692dfd1e90a.jpg
|
| 19 |
+
text: '-'
|
| 20 |
+
- output:
|
| 21 |
+
url: images/21075b23182b45032b0f48efaa3f5b6a.jpg
|
| 22 |
+
text: '-'
|
| 23 |
+
- output:
|
| 24 |
+
url: images/627288b9eaef9948fb486db9d27eb6ab.jpg
|
| 25 |
+
text: '-'
|
| 26 |
+
- output:
|
| 27 |
+
url: images/643910a7875ddb3f31de43ffd90f740f.jpg
|
| 28 |
+
text: '-'
|
| 29 |
+
- output:
|
| 30 |
+
url: images/a6e31c1e56a6d6576379713fb988f4fa.jpg
|
| 31 |
+
text: '-'
|
| 32 |
+
- output:
|
| 33 |
+
url: images/c1a21190bef7b74461bb18190e259906.jpg
|
| 34 |
+
text: '-'
|
| 35 |
+
- output:
|
| 36 |
+
url: images/c67f3bc27afade506a5426d2da0355e0.jpg
|
| 37 |
+
text: '-'
|
| 38 |
+
- output:
|
| 39 |
+
url: images/c76c5bc10f32e1b2a0067ac9e591b289.jpg
|
| 40 |
+
text: '-'
|
| 41 |
+
- output:
|
| 42 |
+
url: images/e47d0d48a8f76d981c6585a2abeed4a4.jpg
|
| 43 |
+
text: '-'
|
| 44 |
+
base_model: Tongyi-MAI/Z-Image-Turbo
|
| 45 |
+
instance_prompt: physioshade
|
| 46 |
+
license: apache-2.0
|
| 47 |
+
---
|
| 48 |
+
# PhysioShade detail Enhancer for Zimage Turbo LORA
|
| 49 |
+
|
| 50 |
+
<Gallery />
|
| 51 |
+
|
| 52 |
+
## Model description
|
| 53 |
+
|
| 54 |
+
PhysioShade is a professional detail enhancer designed exclusively for Zimage Turbo. It doesn’t add filters, it doesn’t invent textures, and it doesn’t alter the subject. Instead, it enhances the physical behavior of the most complex materials with clean, natural, and stable results.
|
| 55 |
+
|
| 56 |
+
PhysioShade improves human skin, all types of skin materials, chrome, steel, glass, hair, eyes, and fabrics with physically coherent shading.
|
| 57 |
+
|
| 58 |
+
🎯 What PhysioShade Enhances
|
| 59 |
+
✔ Human Skin
|
| 60 |
+
realistic micro‑texture
|
| 61 |
+
|
| 62 |
+
natural pores
|
| 63 |
+
|
| 64 |
+
smooth transitions
|
| 65 |
+
|
| 66 |
+
believable subsurface scattering
|
| 67 |
+
|
| 68 |
+
zero plastic look
|
| 69 |
+
|
| 70 |
+
✔ Material Skin (leather, eco‑leather, latex)
|
| 71 |
+
correct roughness
|
| 72 |
+
|
| 73 |
+
controlled reflections
|
| 74 |
+
|
| 75 |
+
no fake gloss
|
| 76 |
+
|
| 77 |
+
✔ Metals (chrome, steel, polished surfaces)
|
| 78 |
+
clean highlights
|
| 79 |
+
|
| 80 |
+
physically plausible reflections
|
| 81 |
+
|
| 82 |
+
realistic micro‑scratches and imperfections
|
| 83 |
+
|
| 84 |
+
✔ Glass
|
| 85 |
+
accurate refractions
|
| 86 |
+
|
| 87 |
+
clean transparency
|
| 88 |
+
|
| 89 |
+
zero artifacts
|
| 90 |
+
|
| 91 |
+
natural optical distortion
|
| 92 |
+
|
| 93 |
+
✔ Eyes
|
| 94 |
+
complex, layered iris
|
| 95 |
+
|
| 96 |
+
clean reflections
|
| 97 |
+
|
| 98 |
+
natural sclera shading
|
| 99 |
+
|
| 100 |
+
no “glassy” effect
|
| 101 |
+
|
| 102 |
+
✔ Hair
|
| 103 |
+
defined strands
|
| 104 |
+
|
| 105 |
+
natural volume
|
| 106 |
+
|
| 107 |
+
clean texture
|
| 108 |
+
|
| 109 |
+
✔ Fabrics
|
| 110 |
+
readable weave
|
| 111 |
+
|
| 112 |
+
realistic fibers
|
| 113 |
+
|
| 114 |
+
natural folds
|
| 115 |
+
|
| 116 |
+
⚙️ Recommended Strength
|
| 117 |
+
0.7 – 0.85 → general use, maximum naturalness
|
| 118 |
+
|
| 119 |
+
0.85 – 1.0 → maximum impact on materials and micro‑detail
|
| 120 |
+
|
| 121 |
+
Trigger word: physioshade Compatibility: Zimage Turbo only
|
| 122 |
+
|
| 123 |
+
🧪 Prompt Showcase
|
| 124 |
+
Realistic Portrait (skin + eyes + hair)
|
| 125 |
+
physioshade, ultra realistic portrait, natural skin texture, sharp eyes, realistic hair strands, soft daylight, photorealistic
|
| 126 |
+
|
| 127 |
+
Backlight + Metal (earrings, leather)
|
| 128 |
+
physioshade, cinematic portrait with warm golden backlight, white gold earrings with sharp rim highlights, natural skin texture, realistic hair glow
|
| 129 |
+
|
| 130 |
+
Macro Eye
|
| 131 |
+
physioshade, extreme macro close-up of a human eye, ultra detailed iris, wet waterline, micro skin texture, 8k macro lens
|
| 132 |
+
|
| 133 |
+
Chrome / Steel
|
| 134 |
+
physioshade, close-up of a polished chrome engine, sharp reflections, warm sunlight, detailed textures, photorealistic
|
| 135 |
+
|
| 136 |
+
Glass + Flowers
|
| 137 |
+
physioshade, glass vase with fresh flowers on a glass table, realistic refractions, soft natural light, detailed petals and stems
|
| 138 |
+
|
| 139 |
+
📌 Technical Notes
|
| 140 |
+
Trained exclusively on Zimage Turbo
|
| 141 |
+
|
| 142 |
+
Does not alter style or color palette
|
| 143 |
+
|
| 144 |
+
No artifacts on skin or materials
|
| 145 |
+
|
| 146 |
+
Optimized for micro‑texture and physically complex surfaces
|
| 147 |
+
|
| 148 |
+
Stable, predictable behavior
|
| 149 |
+
|
| 150 |
+
⭐ Why PhysioShade Is Different
|
| 151 |
+
Because it doesn’t “decorate” the image — it understands it.
|
| 152 |
+
|
| 153 |
+
PhysioShade behaves like a physical shading module, not an aesthetic LoRA. It’s built for creators who want clean, professional, believable detail.
|
| 154 |
+
|
| 155 |
+
## Trigger words
|
| 156 |
+
|
| 157 |
+
You should use `physioshade` to trigger the image generation.
|
| 158 |
+
|
| 159 |
+
|
| 160 |
+
## Download model
|
| 161 |
+
|
| 162 |
+
|
| 163 |
+
[Download](/jarod2212/PhysioShade_ZIT/tree/main) them in the Files & versions tab.
|