## 🧔 Middle-aged Fat Professor —— Asian Middle-aged## 🧔 中年胖教授 —— 亚洲中年Design Concept / 设计理念： A realistic Asian middle-aged chubby bear professor focused on portraying thick, warm, and mature bear daddy charm. Through specialized fine-tuning, it strengthens round soft belly, broad shoulders, and steady professor aura, aiming to generate authentic, authoritative yet approachable middle-aged bear dad images.以写实亚洲中年胖熊教授为核心，专注于刻画厚实温暖的熊叔魅力。通过特殊微调，强化圆润胖肚、宽厚身材与稳重教授气质，目标是生成既有生活感又充满权威温暖的真实中年熊爸形象。Core Features / 核心特征： Thick round soft belly, broad sturdy shoulders, soft chest and abdomen, Asian middle-aged professor face (around 50 years old), short black-gray buzz cut, steady gentle expression, natural skin texture, light body hair, thick arms and thighs.厚实圆润的胖肚、宽厚肩膀、柔软胸腹、亚洲中年教授脸庞（50岁左右）、短寸黑灰发、稳重温和表情、自然皮肤纹理、轻微体毛、厚实手臂与大腿。Main Strengths / 主要优势： Extremely realistic chubby bear body performance, natural professor temperament, stable hand and body proportions, rich and delicate expressions. Excellent for office, study, lecture hall and various Asian middle-aged professor scenes, covering subtle age and body details around 50.极致写实胖熊身材表现、教授气场自然生动、手部与身体比例稳定、表情丰富细腻。适合职场、书房、讲台等多种亚洲中年教授场景，年龄覆盖50岁左右不同微表情与体型细节。### 🔑 Trigger Word / 触发词 *<code>han nano</code>**- Compatible Base Models / 兼容底模： Flux Klein- Strengthens Asian middle-aged male features + bear-style fat dad bod.Recommended Generation Settings / 推荐生成设置：- Sampler: Euler- Steps: 20-30- CFG Scale: 4-5- LoRA Weight: 0.8-1.0 (daily recommended 0.85, stronger belly effect 0.95-1.0; for editing or combining LoRAs, lower to 0.6-0.8)- Resolution: 1024x10244K Version Note / 4K 版本特别说明：Supports higher resolution (recommended 1328x1328+), skin texture and belly details will be more outstanding. Best used with Hires fix.### 💡 Practical Tips / 实用小贴士1. Natural Language Prompt Recommendation：Flux Klein works best with natural language. Use LLM (Claude / Grok / Qwen etc.) to polish descriptions like “a 50-year-old fat professor bear daddy standing at the podium”.2. Civitai Online Generation：Local generation recommended for Flux Klein; online may require multiple attempts.3. Enhancement Tips：- More chubby/bear<code>prominent soft belly, thick waist, dad bod, body hair</code>- Stronger professor vibe<code>glasses, bookshelves, academic setting, authoritative expression</code>- Asian features<code>east asian features, black hair, monolids</code>---欢迎使用和提建议，如有帮助，可以选择支持我（BUZZ），谢谢。Welcome to use and give feedback. If helpful, you may support me (BUZZ). Thank you.Collection for more Asian bear middle-aged / Bara Daddy LoRAs：对此类亚洲熊中年 / Bara Daddy 感兴趣，可以在这个 Collection 查看更多

Middle-aged Fat Professor   中年胖教授

zimageTurbo-qin_nano_V1_c1-st3000.safetensors

v2.0 (ZIT)

v1.0（Z image Base ZIB）

v1.0(flux.2 klein 9B)


# 

## Model Introduction

This model is trained using the [Civision/model training](https://modelscope.ai/civision/modelTraining) environment and computing resources provided by ModelScope.

* Model Type: LoRA
* Base Model: [Tongyi-MAI/Z-Image-Turbo](https://modelscope.ai/models/Tongyi-MAI/Z-Image-Turbo)
* Training Code: [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* Data amount：20
* Total training steps：4000
* License: Apache-2.0

## Inference Code

Install [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio):

```bash
pip install diffsynth
```

Inference:

```python
from diffsynth.pipelines.z_image import ZImagePipeline, ModelConfig
import torch

pipe = ZImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="transformer/*.safetensors"),
        ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="text_encoder/*.safetensors"),
        ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
    ],
    tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="tokenizer/"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="jlhe2016/zimageTurbo-qin_nano_V1", origin_file_pattern="zimageTurbo-qin_nano_V1_c1-st4000.safetensors"))
prompt = "a cat"
image = pipe(prompt=prompt, num_inference_steps=8, cfg_scale=1)
image.save("image.jpg")
```


Files with SHA256: 4146a972d4c5f13357d95f8a27bbb3ad8f543d1706449818b7e4e59a198bf994