前言

不知道为啥，嫂子揉面的视频有点火🤔，到底大家关注点在哪里了（再次思考🤔），我刷了几个，其实没啥嘛。

用最新通义 Wan 2.1 模型，可以生成一堆，不信大家往后看

搜子揉面但 Wan 2.1

为了便于各位观看，先看看 gif 版的，文末附上高清视频版集合。

嫂子青涩揉面

嫂子不太会揉面

嫂子完全不会揉面

嫂子熟练揉面

嫂子迷茫揉面

嫂子头发太长不揉面

嫂子卖萌不揉面

嫂子认真揉面

大家看够了吗？准备好上课了😂。

工作流讲解

工作流分解图，大家可以看看基础的模块如何配合：

由于使用了 wan 2.1 的 i2v 流程，所以图片的输入很关键，所以这里采用了两次采样，以 flux 强大的能力，提供优质、真实图片输入。 Wan 2.1 使用 sageattn 和分离 sigma 加速，极大地提升了生成速度，同时使用 gguf 量化模型，可以大幅度降低显存占用，8 G 显存可玩。

提示词处理

建立有 Qwen 和 DeepSeek R1 双剑合璧的原画到画面视频的提示语处理流程。

画面部分提示语：

act as prompt generator, I will give you text and you describe an image that matches that text in details, answer with one response only.if I input in Chinese to communicate with you, but it is crucial that your response be in English.

画面部分提示语：

## Role

You are a director and action design expert with a flair for climax action design and artistic aesthetics, possessing a strong sense of cinematography, akin to a blockbuster film. Based on my input, produce the perfect prompts according to the following rules.  
## Duration
The video duration is about 2-3 seconds, pay attention to the relationship between action amplitude and duration.
## Basic Prompt Formula:  
Prompt = Subject + Scene + Action + Shot  

**Example of Basic AI Video Prompt**: Soaring Eagle  

## Sample  
**Subject**: Soaring Eagle  
**Scene**: Under a clear blue sky, a majestic mountain range with snow-capped peaks  
**Action**: The eagle glides gracefully in the air, effortlessly riding the thermal updrafts, with sunlight reflecting off its vibrant feathers  

**Complete Prompt**: Above a majestic mountain range with snow-capped peaks under a clear blue sky, a soaring eagle glides gracefully in the air. The sunlight sparkles on its vibrant feathers, highlighting the power and elegance of its wings as it effortlessly rides the thermal updrafts. Below lies a vast expanse of the mountain range with patches of green and rocky outcrops, and the air is filled with a sense of freedom and tranquility.  

**Shot**: The camera focuses on the eagle, then slowly rotates and pulls back, revealing the vastness of the sky.  

## Output Requirements  
Only output the final **Complete Prompt:**.

看看 R1 的强大顿悟能力：

我输入的：

镜头：俯拍镜头拍摄，半身肖像，
主体：一个中国女人，浓厚的直发，穿着性感衣服，身材很好，皮肤白皙；
动作：在厨房揉面，挥汗如雨，
附加：撩人的眼神

R1 输出的：

**Complete Prompt:** In a warmly lit, modern-traditional kitchen with steam rising from a simmering pot and polished wooden countertops scattered with flour, a striking Chinese woman kneads dough with vigorous precision. Her voluminous straight black hair cascades down her back, contrasting against her porcelain-fair skin, which glistens with a thin sheen of sweat. Clad in a form-fitting crimson qipao that accentuates her curves, she pauses, tilting her chin upward. Her eyes—sharp, dark, and smoldering—lock onto the viewer with a teasing, flirtatious intensity, lips parted slightly as a bead of sweat trails down her neck. The camera begins tight on her face, capturing the magnetism of her gaze, then slowly pulls back in a sweeping overhead arc to reveal her poised figure, the dough beneath her hands, and a traditional ink-painted scroll hanging faintly in the background, bathed in golden-hour light.