You can click on the link below to try it out directly. If the effect is good, you can deploy it locally<a target="_blank" rel="ugc" href="https://www.runninghub.ai/post/2086745289859379202?inviteCode=rh-v1559">https://www.runninghub.ai/post/2086745289859379202?inviteCode=rh-v1559</a>Experience this LoRA for free at the link below! Powered by a Krea2 workflow, it enables seamless direct 4K high-definition generation.Model OverviewWelcome to SoftCurves_Youth_v1!A specialized photorealistic LoRA engineered for the Krea2 Architecture, focusing on young Asian female portraits with enhanced low-angle perspectives, mature fashion styling, and focused camera compositions.This model excels at capturing the contrast between youthful features and sophisticated attire, specifically enhancing low-angle dynamic shots, tight-fitting mini skirts, pantyhose and stockings textures, and waist/skirt camera framing. Perfectly suited for creating aesthetic young adult fashion portraiture, modern urban street style snapshots, and allure-focused photography.Recommended ParametersBase Architecture: Krea2 Running Version: Krea2 Turbo Sampling Steps: 8 CFG Scale: 1 LoRA Weight: 1.0 (Recommended 0.8 to 1.0) Core Trigger Tags: softcurves youth, young asian woman, low angle shot, looking down at viewer, tight skirt, pantyhose, camera focus on skirt, off-shoulder top, raw photography, masterpiece portraitPrompting &amp; Style Tips<ol><li>Perspective &amp; Framing Enhancements: For Low Angle &amp; Skirt Focus: low angle view, extreme perspective, looking down, camera focus on waist and skirt, dynamic wide angle shot For Outfit &amp; Texture Details: wearing off-shoulder crop top, fitted mini skirt, sheer black pantyhose, fine fabric texture, sleek waistline</li><li>Environment &amp; Atmospheric Prompts: For Urban &amp; Outdoor Mood: standing on balcony, glass railing, moody sky background, cloudy overcast lighting, wind blowing hair, natural skin texture, 8k portrait</li></ol>

SoftCurves_Youth_v1

SoftCurves_Youth_v1.safetensors

v1.0


# 初熟特写  SoftCurves_Youth

## 模型介绍

本模型依托魔搭社区（ModelScope）AIGC专区[模型训练](https://modelscope.cn/aigc/modelTraining)环境与算力完成训练。

* 模型类型：LoRA
* 基础模型：[krea/Krea-2-Turbo](https://modelscope.cn/models/krea/Krea-2-Turbo)
* 训练代码：[DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* 训练数据量：94
* 总训练步数：3000
* 开源协议：Apache-2.0

## 推理代码

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

```bash
pip install diffsynth
```

开始推理：

```python
from diffsynth.pipelines.krea2 import Krea2Pipeline, ModelConfig
import torch

pipe = Krea2Pipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="krea/Krea-2-Turbo", origin_file_pattern="turbo.safetensors"),
        ModelConfig(model_id="Qwen/Qwen3-VL-4B-Instruct", origin_file_pattern="*.safetensors"),
        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
    ],
    tokenizer_config=ModelConfig(model_id="Qwen/Qwen3-VL-4B-Instruct", origin_file_pattern=""),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="zhouwenbin1994/SoftCurves_Youth_v1", origin_file_pattern="SoftCurves_Youth_v1_c2-st3000.safetensors"))
prompt = "a cat"
image = pipe(
    prompt, seed=0,
    num_inference_steps=8, cfg_scale=1, mu=1.15,
)
image.save("image.jpg")
```


Files with SHA256: cc5b36fe47d48a10131d8e9ecfd0d20a4fd4c43890c97e9c51488f39d9868243