Respan Dataset Explorer

                            As a prompt generator for a generative AI called "Midjourney", you will create image prompts for the AI to visualize. I will give you a concept, and you will provide a detailed prompt for Midjourney AI to generate an image.
                            
                            Please adhere to the structure and formatting below, and follow these guidelines:
                            
                            Do not use the words "description" or ":" in any form.
                            Do not place a comma between [ar] and [v].
                            Write each prompt in one line without using return.
                            Structure:
                            [1] = 卡通游戏资产，中国古代山河，游戏地图,战争,简洁的风格，中国传统文化，地图背景，卡通的风格，2.5D等距，
                            [2] = a detailed description of [1] with specific imagery details.
                            [3] = a detailed description of the scene's environment.
                            [4] = a detailed description of the compositions.
                            [5] = a detailed description of the scene's mood, feelings, and atmosphere.
                            [6] = A style (e.g. photography, painting, illustration, sculpture, artwork, paperwork, 3D, etc.) for [1].
                            [7] =  a detailed description of the scene's mood, feelings, and atmosphere.
                            [ar] = Use "--ar 16:9" for horizontal images, "--ar 9:16" for vertical images, or "--ar 1:1" for square images.
                            [v] = Use "--niji 6" for Japanese art style, or "--v 6" for other styles.
                            
                            
                            Formatting:
                            Follow this prompt structure: "/imagine prompt: [1], [2], [3], [4], [5], [6], [7], [ar] [v]".
                            
                            Your task: Create 4 distinct prompts for each concept [1], varying in details description, environment,compositions,atmosphere, and realization.
                            
                            Write your prompts in english.
                            Do not describe unreal concepts as "real" or "photographic".
                            Include one realistic photographic style prompt with lens type and size.
                            Separate different prompts with two new lines.
                            Example Prompts:
                            
                            /imagine prompt: cute dog, fluffy fur, wagging tail, playful expression, sitting on a grassy field, under a clear blue sky, with a colorful collar, in a natural and vibrant setting, by a lake, captured with a Nikon D750 camera, 50mm lens, shallow depth of field, composition focused on the dog's face, capturing its joyful spirit, in a style reminiscent of William Wegman's iconic dog portraits. --ar 1:1 --v 6
                            /imagine prompt: beautiful women in the coffee shop, elegant and sophisticated, sipping a cup of steaming coffee, natural sunlight streaming through the window, soft and warm color tones, vintage decor with cozy armchairs and wooden tables, a bookshelf filled with classic novels, delicate porcelain teacups, a hint of aromatic coffee beans in the air, captured by a Leica M10 camera, 35mm lens, capturing the essence of timeless beauty, composition focused on the woman's face and hands, reminiscent of a painting by Leonardo da Vinci. --ar 1:1 --v 6
                            /imagine prompt: A captivating Halo Reach landscape with a Spartan amidst a battlefield, fallen enemies around, smoke and fire in the background, emphasizing the Spartan's determination and bravery, detailed environment blending chaos and beauty, Illustration, digital art, --ar 16:9 --v 6
                                                        

/imagine prompt: cartoon-style game assets of ancient Chinese mountains and rivers, game map with a war theme, simplistic style, traditional Chinese culture references, 2.5D isometric view, detailed imagery of temples, forests, and valleys, characters in traditional warrior attire, serene atmosphere with a touch of battle tension, in an anime art style. --ar 16:9 --v 6

/imagine prompt: colorful and vibrant cartoon assets depicting a mythical Chinese world, featuring ancient kingdoms and mystical creatures, game map filled with hidden treasures and secrets, intricate design details in architecture and landscapes, characters inspired by Chinese folklore and legends, mystical atmosphere with a sense of adventure and discovery, 2.5D perspective with rich textures and patterns, in a vibrant and dynamic art style. --ar 16:9 --v 6

/imagine prompt: whimsical and charming game assets of a fantasy version of ancient China, with magical floating islands and mystical creatures, game map showcasing enchanted forests and ethereal mountains, characters in magical attire with unique abilities, dreamlike atmosphere with a touch of mystery and wonder, detailed illustrations of mythical creatures and ancient ruins, in a fairy tale illustration style. --ar 16:9 --v 6

/imagine prompt: cartoon-style assets of a reimagined historical Chinese landscape, featuring majestic palaces and bustling marketplaces, game map filled with cultural landmarks and intricate details, characters in traditional attire engaged in daily activities, lively atmosphere with a mix of historical accuracy and whimsical charm, detailed illustrations of cityscapes and natural scenery, in a nostalgic and storytelling art style. --ar 16:9 --v 6

I can't afford the Yakuza games so to counter-act this, I'm gonna play Postal 2 in Japanese lol

That sounds like an interesting plan! While Yakuza games offer a rich narrative and cultural immersion in a stylized version of Japan, Postal 2 is a very different experience with its own unique brand of chaotic humor and controversial gameplay. Playing Postal 2 in Japanese could certainly provide an amusing twist on the game and might even help you pick up some Japanese language skills along the way.

If you enjoy blending cultural experiences, you might also consider exploring other games with Japanese language options or themes. Some indie games might offer a blend of humor, action, and Japanese cultural elements that could be both affordable and entertaining.

Happy gaming, and good luck with your Japanese practice!

class AdaGrad(Optimizer):
    def __init__(self, params, lr=0.01, eps=1e-3):
        super(AdaGrad, self).__init__(params)
        self.lr = lr
        self.eps = eps
        
        self.squared_grads = [torch.zeros_like(param) for param in self.params]

    def step(self):
        with torch.no_grad():
            ## TODO: 补全更新步骤
            ## hint: 可以类似SGDMomentum，先在`__init__`中定义好中间变量
            
            for i, param in enumerate(self.params):
                self.squared_grads[i] += param.grad**2
                param -= self.lr * param.grad / (torch.sqrt(self.squared_grads[i]) + self.eps)补全代码，实现AdaGrad

Sure! Here is the complete implementation of the AdaGrad optimizer in PyTorch:

```python
import torch
from torch.optim.optimizer import Optimizer

class AdaGrad(Optimizer):
    def __init__(self, params, lr=0.01, eps=1e-3):
        defaults = dict(lr=lr, eps=eps)
        super(AdaGrad, self).__init__(params, defaults)

    def __setstate__(self, state):
        super(AdaGrad, self).__setstate__(state)

    def step(self, closure=None):
        loss = None
        if closure is not None:
            loss = closure()

        for group in self.param_groups:
            for param in group['params']:
                if param.grad is None:
                    continue

                grad = param.grad.data
                state = self.state[param]

                # State initialization
                if len(state) == 0:
                    state['step'] = 0
                    state['sum_sq_grad'] = torch.zeros_like(param.data)

                state['step'] += 1

                sum_sq_grad = state['sum_sq_grad']
                sum_sq_grad.addcmul_(grad, grad, value=1)  # Accumulate squared gradient

                std = sum_sq_grad.sqrt().add_(group['eps'])
                param.data.addcdiv_(grad, std, value=-group['lr'])

        return loss
```

### Explanation:
1. **Initialization (`__init__`)**:
   - We call the parent class initializer (`super`) with `params` and default arguments for learning rate (`lr`) and epsilon (`eps`).
   - We store these parameters in a `defaults` dictionary which the parent class will store for us.

2. **State Initialization**:
   - For each parameter (`param`), a state entry dictionary is created on the first occurrence.
   - This state dictionary contains:
     - `step`: Counts the number of updates for each parameter.
     - `sum_sq_grad`: Keeps track of the sum of squares of gradients for adjusting the learning rate.

3. **Gradient Update (`step`)**:
   - For each parameter in `group['params']`:
     - We skip if the gradient is `None`.
     - Accumulate the squared gradients in `sum_sq_grad`.
     - Calculate the standard deviation (`std`).
     - Update the parameter (`param.data`) by scaling the gradient according to `AdaGrad`'s update rule.

The optimizer is now complete and can be used like any other PyTorch optimizer. For example:

```python
model = YourModel()
optimizer = AdaGrad(model.parameters(), lr=0.01)

# In your training loop:
optimizer.zero_grad()
output = model(input)
loss = criterion(output, target)
loss.backward()
optimizer.step()
```

This implementation provides a custom optimizer compatible with PyTorch's training mechanisms.

用中文说一遍

好的，这是一个完整的 AdaGrad 优化器在 PyTorch 中的实现：

```python
import torch
from torch.optim.optimizer import Optimizer

class AdaGrad(Optimizer):
    def __init__(self, params, lr=0.01, eps=1e-3):
        defaults = dict(lr=lr, eps=eps)
        super(AdaGrad, self).__init__(params, defaults)

    def __setstate__(self, state):
        super(AdaGrad, self).__setstate__(state)

    def step(self, closure=None):
        loss = None
        if closure is not None:
            loss = closure()

        for group in self.param_groups:
            for param in group['params']:
                if param.grad is None:
                    continue

                grad = param.grad.data
                state = self.state[param]

                # 状态初始化
                if len(state) == 0:
                    state['step'] = 0
                    state['sum_sq_grad'] = torch.zeros_like(param.data)

                state['step'] += 1

                sum_sq_grad = state['sum_sq_grad']
                sum_sq_grad.addcmul_(grad, grad, value=1)  # 累积平方梯度

                std = sum_sq_grad.sqrt().add_(group['eps'])
                param.data.addcdiv_(grad, std, value=-group['lr'])

        return loss
```

### 解释：
1. **初始化 (`__init__`)**:
   - 调用父类的初始化器 (`super`) 并传入 `params` 和默认参数：学习率 (`lr`) 和 epsilon (`eps`)。
   - 将这些参数存储在一个 `defaults` 字典中，父类将为我们存储这些参数。

2. **状态初始化**:
   - 对于每个参数 (`param`)，在第一次调用时创建一个状态字典。
   - 这个状态字典包含：
     - `step`：计数更新步数。
     - `sum_sq_grad`：用于跟踪累计平方梯度以调整学习率。

3. **梯度更新 (`step`)**:
   - 对于 `group['params']` 中的每个参数:
     - 如果梯度为 `None`，则跳过。
     - 在 `sum_sq_grad` 中累积平方梯度。
     - 计算标准差 (`std`)。
     - 按照 AdaGrad 的更新规则通过调整梯度更新参数 (`param.data`)。

这个优化器现在是完整的，可以像其他 PyTorch 优化器一样使用。例如：

```python
model = YourModel()
optimizer = AdaGrad(model.parameters(), lr=0.01)

# 在训练循环中:
optimizer.zero_grad()
output = model(input)
loss = criterion(output, target)
loss.backward()
optimizer.step()
```

这个实现提供了一个与 PyTorch 训练机制兼容的自定义优化器。

WARNING: Retrying (Retry(total=4, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ProxyError('Cannot connect to proxy.', OSError(0, 'Error'))': /simple/matplotlib/
WARNING: Retrying (Retry(total=3, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ProxyError('Cannot connect to proxy.', OSError(0, 'Error'))': /simple/matplotlib/
WARNING: Retrying (Retry(total=2, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ProxyError('Cannot connect to proxy.', OSError(0, 'Error'))': /simple/matplotlib/
WARNING: Retrying (Retry(total=1, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ProxyError('Cannot connect to proxy.', OSError(0, 'Error'))': /simple/matplotlib/
WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ProxyError('Cannot connect to proxy.', OSError(0, 'Error'))': /simple/matplotlib/
ERROR: Could not find a version that satisfies the requirement matplotlib (from versions: none)
ERROR: No matching distribution found for matplotlib解释一下报错

这个错误信息表明在通过 `pip` 安装 `matplotlib` 时遇到了网络连接问题，具体来说是代理（proxy）配置问题。以下是对这些警告和错误的详细解释：

### 警告说明：
- **WARNING: Retrying (Retry(total=4, ...))**：
  - 这是`pip`尝试进行重试的次数，由于每次尝试都由于网络连接问题而失败，因此`Retry(total=4)`表示还有4次重试机会。
- **ProxyError('Cannot connect to proxy.', OSError(0, 'Error'))**：
  - 这个错误信息表示`pip`在连接到代理服务器时失败。此处的 `ProxyError` 表明是与代理服务器的连接问题，比如代理配置错误或代理服务器不可用。

### 最终错误：
- **ERROR: Could not find a version that satisfies the requirement matplotlib (from versions: none)**：
  - 这个错误表示`pip`无法找到满足`matplotlib`包需求的版本。原因可能是前面的连接问题导致`pip`无法访问包索引来确定可用版本。
- **ERROR: No matching distribution found for matplotlib**：
  - 这个错误进一步确认了`pip`无法找到任何`matplotlib`的匹配发行版本，同样可能是由于无法连接到包索引导致的。

### 可能的解决方法：
1. **检查代理配置**：
   - 如果你在使用代理服务器，确保代理配置正确。你可以使用以下命令设置代理：
     ```sh
     pip install matplotlib --proxy http://proxyserver:port
     ```
   - 如果不需要代理，可以取消代理设置：

     在 Windows 上，按以下步骤操作解除 HTTP 或 HTTPS 代理：
     ```sh
     set http_proxy=
     set https_proxy=
     ```

     在 Linux 或 MacOS 上，可以用以下命令解除 HTTP 或 HTTPS 代理：
     ```sh
     unset http_proxy
     unset https_proxy
     ```

2. **直接下载并安装**：
   - 从 [Python Package Index (PyPI)](https://pypi.org/project/matplotlib/#files) 手动下载 `matplotlib` 的 wheel 包，然后使用以下命令进行安装：
     ```sh
     pip install /path/to/downloaded/package.whl
     ```

3. **检查网络连接**：
   - 确保你的网络连接稳定，没有防火墙或其他网络限制阻止 `pip` 访问 PyPI。

4. **更新 `pip`**：
   - 可能你的 `pip` 版本较老，更新 `pip` 可能解决某些问题：
     ```sh
     pip install --upgrade pip
     ```

5. **使用镜像源**：
   - 由于网络问题无法访问官方源，可以尝试使用国内或替代的镜像源，例如清华大学的镜像：
     ```sh
     pip install matplotlib -i https://pypi.tuna.tsinghua.edu.cn/simple
     ```

通过这些方法，你应该可以解决连接问题，成功安装 `matplotlib`。

タイ・カダイ語族のタイ語派の架空言語をつくって．語彙の文字はIPA通りの文字で．

もちろん、架空のタイ・カダイ語族のタイ語派の言語を作成してみます。この言語の名前を「Fai」と呼びます。以下にいくつかの基本的な語彙とその発音を示します。なお、この言語の語彙は全てIPAに基づいて書かれています。

### 母音 (Vowels)
この言語の母音は以下の通りです：
- /a/
- /i/
- /u/
- /e/
- /o/
- /ɛ/
- /ɔ/

### 子音 (Consonants)
この言語の子音は以下の通りです：
- /p/, /b/
- /t/, /d/
- /k/, /ɡ/
- /m/, /n/, /ŋ/
- /f/, /v/
- /s/, /z/
- /ʃ/, /ʒ/
- /x/, /ɣ/
- /l/, /r/
- /w/, /j/
- /h/

### 声調 (Tones)
タイ語族の特徴として声調が重要です。この言語でも5つの声調を持つとしましょう：
1. 高平調 (High level): ˥
2. 中平調 (Mid level): ˧
3. 低平調 (Low level): ˩
4. 上昇調 (Rising): ˩˥
5. 下降調 (Falling): ˥˩

### 基本の語彙 (Basic Vocabulary)
1. こんにちは (Hello): `saw˧ʔatʰ˥ti˥`
2. ありがとう (Thank You): `kʰɔ˩ɔb˥kun˧`
3. はい (Yes): `ʔɯ˧a`
4. いいえ (No): `mɑi˧`
5. 水 (Water): `nām˧`
6. 食べる (Eat): `kin˥`
7. 家 (House): `bɑ˧n`
8. 語 (Language): `phɑ˧sǎ˨`
9. 行く (Go): `khaw˥`
10. 学ぶ (Learn): `rʉ˩an˧`

### 文例 (Sentence Examples)
1. 私は水を飲む (I drink water): `kʰun˧ kin˧ nām˧`
2. 彼は家に行く (He goes to the house): `khaw˥ pay˥ bɑn˧`
3. 私はタイ語を学ぶ (I learn Thai): `kʰun˧ rʉan˩ phɑ˧sǎ˨ phɑ˧sǎ˨ fay˧`

### 文法上の特徴 (Grammatical Features)
- **語順**: 主語 (Subject) - 動詞 (Verb) - 目的語 (Object) の順
- **時制・相**: 動詞本体の変更を基本とし、副詞で詳細を表現
- **助詞**: 概して副詞や補助的な文で述べる

注意点として、この言語はタイ語やラオ語に似た性格を持ちつつも、独自の声調と語彙を持っています。さらに詳細な文法や語彙は必要に応じて追加していくと良いでしょう。

文字

了解しました。この架空の言語「Fai（ファイ）」に適した独自の文字体系をデザインしてみます。以下に各IPA記号に対応する文字を設定します。

### 母音の文字 (Vowel Characters)
- /a/ : 𐌀 
- /i/ : 𐌉 
- /u/ : 𐌖 
- /e/ : 𐌄 
- /o/ : 𐍉 
- /ɛ/ : 𐌅 
- /ɔ/ : 𐌀𐍉 

### 子音の文字 (Consonant Characters)
- /p/ : 𐌐 
- /b/ : 𐌁 
- /t/ : 𐌕 
- /d/ : 𐌃 
- /k/ : 𐌊 
- /ɡ/ : 𐌠 
- /m/ : 𐌌 
- /n/ : 𐌍 
- /ŋ/ : 𐌑 
- /f/ : 𐍆 
- /v/ : 𐌅 
- /s/ : 𐌔 
- /z/ : 𐌆 
- /ʃ/ : 𐌔𐌔 
- /ʒ/ : 𐌆𐌔 
- /x/ : 𐌗 
- /ɣ/ : 𐌗𐍉 
- /l/ : 𐌋 
- /r/ : 𐌓 
- /w/ : 𐍅 
- /j/ : 𐌉𐍆 
- /h/ : 𐌇 

### 声調の記号 (Tone Marks)
- 高平調 (High level): ◌̋ 
- 中平調 (Mid level): ◌̄ 
- 低平調 (Low level): ◌̏ 
- 上昇調 (Rising): ◌ˇ 
- 下降調 (Falling): ◌̂ 

### 基本の語彙 (Basic Vocabulary) - 独自文字
1. こんにちは (Hello): 𐌔𐌀𐍅˧𐌡𐌄𐌏𐌔˥𐌕𐌋˥
2. ありがとう (Thank You): 𐌗𐫤𐌉˩𐍉𐌌𐌁˥𐌗𐌏𐌗𐌍˧
3. はい (Yes): 𐌉𐌡˧𐍅𐌀
4. いいえ (No): 𐌏𐌠𐌉˧
5. 水 (Water): 𐌍𐌀𐌑˧
6. 食べる (Eat): 𐌊𐌡𐌋˥
7. 家 (House): 𐌁𐌌𐌑˧
8. 語 (Language): 𐌗𐌌𐌌˧𐌌𐌑˨
9. 行く (Go): 𐌗𐌁𐌡˥
10. 学ぶ (Learn): 𐌉𐌏˩𐌑𐌍˧

### 文例 (Sentence Examples) - 独自文字
1. 私は水を飲む (I drink water): 𐌗𐌌𐌏˧ 𐌊𐌏𐌏𐌍˧ 𐌍𐌌𐌑˧
2. 彼は家に行く (He goes to the house): 𐌗𐌡𐌍˥ 𐌏𐫤𐌌˥ 𐌁𐌌𐌑˧
3. 私はタイ語を学ぶ (I learn Thai): 𐌗𐌌𐌏˧ 𐌉𐌏˩𐌑˧ 𐌗𐌌𐌌˧𐌑˧ 𐌗𐌌𐌌˧𐌑˧ 𐌊𐌡𐌏˧

### 文法上の特徴 (Grammatical Features)
- **語順**: 主語 (Subject) - 動詞 (Verb) - 目的語 (Object) の順
- **時制・相**: 動詞本体の変更を基本とし、副詞で詳細を表現
- **助詞**: 概して副詞や補助的な文で述べる

この文字体系と音韻構造を基に、Fai言語のさらなる発展を楽しんでください。

タイ文字で

了解しました。架空のタイ・カダイ語族の言語「Fai（ファイ）」をタイ文字で表現してみます。以下に基本語彙と文章をタイ文字で示します。

### 母音 (Vowel Symbols)
タイ文字の母音をそのまま使います。
- /a/: อะ
- /i/: อิ
- /u/: อุ
- /e/: เอะ
- /o/: โอะ
- /ɛ/: แอะ
- /ɔ/: เอาะ

### 子音 (Consonant Symbols)
タイ文字での子音は以下の通りです：
- /p/: ป
- /b/: บ
- /t/: ต
- /d/: ด
- /k/: ก
- /ɡ/: ง
- /m/: ม
- /n/: น
- /ŋ/: ง
- /f/: ฟ
- /v/: ว
- /s/: ส
- /z/: ซ
- /ʃ/: ช
- /ʒ/: ฌ
- /x/: ฮ
- /ɣ/: ก
- /l/: ล
- /r/: ร
- /w/: ว
- /j/: ย
- /h/: ห

### 声調記号 (Tone Marks)
タイの声調記号は以下を使います：
- 高平調 (High level): ◌่
- 中平調 (Mid level): (通常表記なし)
- 低平調 (Low level): ◌่
- 上昇調 (Rising): ◌้
- 下降調 (Falling): ◌๊

### 基本の語彙 (Basic Vocabulary) - タイ文字
1. こんにちは (Hello): สวัสดี (sa˨wat˧di˧)
2. ありがとう (Thank You): ขอบคุณ (khɔ˨ɔp˦kun˧)
3. はい (Yes): ใช่ (cha˧)
4. いいえ (No): ไม่ (mai˥)
5. 水 (Water): น้ำ (na˦˥m˦)
6. 食べる (Eat): กิน (kin˧)
7. 家 (House): บ้าน (ba˧n˥)
8. 語 (Language): ภาษา (pʰa˧sa˩˩)
9. 行く (Go): ไป (pai˧)
10. 学ぶ (Learn): เรียน (ri˦˥an˧)

### 文例 (Sentence Examples) - タイ文字
1. 私は水を飲む (I drink water): ฉันดื่มน้ำ (chan˦˥ dʉ˩m˦˥ na˦˥m)
2. 彼は家に行く (He goes to the house): เขาไปบ้าน (kʰao˦ pai˧ baan˥)
3. 私はタイ語を学ぶ (I learn Thai): ฉันเรียนภาษาไทย (chan˦˥ rian˩ pʰa˧sa˩˩ tʰai˧)

### 文法上の特徴 (Grammatical Features)
- **語順**: 主語 (Subject) - 動詞 (Verb) - 目的語 (Object) の順
- **時制・相**: 動詞本体の変更を基本とし、副詞で詳細を表現
- **助詞**: 概して副詞や補助的な文で述べる

このタイ文字と音韻構造を基に、Fai言語のさらに各部分を発展させてください。初めは基本語彙から始めて、文法規則を拡大していくと良いでしょう。

                            As a prompt generator for a generative AI called "Midjourney", you will create image prompts for the AI to visualize. I will give you a concept, and you will provide a detailed prompt for Midjourney AI to generate an image.
                            
                            Please adhere to the structure and formatting below, and follow these guidelines:
                            
                            Do not use the words "description" or ":" in any form.
                            Do not place a comma between [ar] and [v].
                            Write each prompt in one line without using return.
                            Structure:
                            [1] = 现代设计的厕所刷 配套的刷架 简洁的白色主色调 搭配蓝色和金色点缀 时尚且具有现代感 圆形刷头 蓝色刷子毛 修长且轻便的白色刷柄 利于手持操作 圆筒形刷架 内侧装有清洁装置 能容纳并固定厕所刷 前端有透明窗格 观察内部清洁程度 存储状态显示 刷架一面可打开 良好的清洁功能 通风功能
                            [2] = a detailed description of [1] with specific imagery details.
                            [3] = a detailed description of the scene's environment.
                            [4] = a detailed description of the compositions.
                            [5] = a detailed description of the scene's mood, feelings, and atmosphere.
                            [6] = A style (e.g. photography, painting, illustration, sculpture, artwork, paperwork, 3D, etc.) for [1].
                            [7] =  a detailed description of the scene's mood, feelings, and atmosphere.
                            [ar] = Use "--ar 16:9" for horizontal images, "--ar 9:16" for vertical images, or "--ar 1:1" for square images.
                            [v] = Use "--niji" for Japanese art style, or "--v 5" for other styles.
                            
                            
                            Formatting:
                            Follow this prompt structure: "/imagine prompt: [1], [2], [3], [4], [5], [6], [7], [ar] [v]".
                            
                            Your task: Create 4 distinct prompts for each concept [1], varying in details description, environment,compositions,atmosphere, and realization.
                            
                            Write your prompts in english.
                            Do not describe unreal concepts as "real" or "photographic".
                            Include one realistic photographic style prompt with lens type and size.
                            Separate different prompts with two new lines.
                            Example Prompts:
                            
                            /imagine prompt: cute dog, fluffy fur, wagging tail, playful expression, sitting on a grassy field, under a clear blue sky, with a colorful collar, in a natural and vibrant setting, by a lake, captured with a Nikon D750 camera, 50mm lens, shallow depth of field, composition focused on the dog's face, capturing its joyful spirit, in a style reminiscent of William Wegman's iconic dog portraits. --ar 1:1 --v 5.2
                            /imagine prompt: beautiful women in the coffee shop, elegant and sophisticated, sipping a cup of steaming coffee, natural sunlight streaming through the window, soft and warm color tones, vintage decor with cozy armchairs and wooden tables, a bookshelf filled with classic novels, delicate porcelain teacups, a hint of aromatic coffee beans in the air, captured by a Leica M10 camera, 35mm lens, capturing the essence of timeless beauty, composition focused on the woman's face and hands, reminiscent of a painting by Leonardo da Vinci. --ar 1:1 --v 5.2
                            /imagine prompt: A captivating Halo Reach landscape with a Spartan amidst a battlefield, fallen enemies around, smoke and fire in the background, emphasizing the Spartan's determination and bravery, detailed environment blending chaos and beauty, Illustration, digital art, --ar 16:9 --v 5
                                                        

/imagine prompt: A modern design toilet brush set with a sleek white color scheme and hints of blue and gold accents, featuring a circular brush head with blue bristles, a slender white handle for easy grip, a cylindrical brush holder with inner cleaning mechanism, equipped to store and secure the brush, transparent viewing window at the front to monitor cleanliness level, storage status display, one side of the holder can open for efficient cleaning function and ventilation. --ar 1:1 --v 5.2

/imagine prompt: The toilet brush set sits in a contemporary bathroom with minimalist décor, clean lines, and ample natural light filtering in through a frosted window, the brush holder placed near the sleek ceramic toilet, reflecting the overall modern aesthetic of the space, the crisp white and blue tones create a refreshing atmosphere, geometric shapes and simplicity in design echoing throughout the environment. --ar 16:9 --v 5

/imagine prompt: A close-up view of the toilet brush set focusing on the circular brush head and the intricate details of the blue bristles, showcasing the slender white handle and the neat arrangement inside the cylindrical brush holder which features a transparent viewing window to observe the cleanliness level, the overall composition highlighting the functionality and stylish elements of the design. --ar 9:16 --v 5

/imagine prompt: The toilet brush ensemble exudes a sense of sophistication and cleanliness, set against a backdrop of a modern luxury bathroom with marble accents and soft ambient lighting, the circular brush head gleaming under the light, the sleek handle and holder exuding elegance and efficiency, the overall mood serene and chic, capturing the essence of contemporary home decor. --ar 16:9 --v 5.

                            As a prompt generator for a generative AI called "Midjourney", you will create image prompts for the AI to visualize. I will give you a concept, and you will provide a detailed prompt for Midjourney AI to generate an image.
                            
                            Please adhere to the structure and formatting below, and follow these guidelines:
                            
                            Do not use the words "description" or ":" in any form.
                            Do not place a comma between [ar] and [v].
                            Write each prompt in one line without using return.
                            Structure:
                            [1] = 80岁慈祥的老奶奶在公园遛狗
                            [2] = a detailed description of [1] with specific imagery details.
                            [3] = a detailed description of the scene's environment.
                            [4] = a detailed description of the compositions.
                            [5] = a detailed description of the scene's mood, feelings, and atmosphere.
                            [6] = A style (e.g. photography, painting, illustration, sculpture, artwork, paperwork, 3D, etc.) for [1].
                            [7] =  a detailed description of the scene's mood, feelings, and atmosphere.
                            [ar] = Use "--ar 16:9" for horizontal images, "--ar 9:16" for vertical images, or "--ar 1:1" for square images.
                            [v] = Use "--niji 5" for Japanese art style, or "--v 5.2" for other styles.
                            
                            
                            Formatting:
                            Follow this prompt structure: "/imagine prompt: [1], [2], [3], [4], [5], [6], [7], [ar] [v]".
                            
                            Your task: Create 4 distinct prompts for each concept [1], varying in details description, environment,compositions,atmosphere, and realization.
                            
                            Write your prompts in english.
                            Do not describe unreal concepts as "real" or "photographic".
                            Include one realistic photographic style prompt with lens type and size.
                            Separate different prompts with two new lines.
                            Example Prompts:
                            
                            /imagine prompt: cute dog, fluffy fur, wagging tail, playful expression, sitting on a grassy field, under a clear blue sky, with a colorful collar, in a natural and vibrant setting, by a lake, captured with a Nikon D750 camera, 50mm lens, shallow depth of field, composition focused on the dog's face, capturing its joyful spirit, in a style reminiscent of William Wegman's iconic dog portraits. --ar 1:1 --v 5.2
                            /imagine prompt: beautiful women in the coffee shop, elegant and sophisticated, sipping a cup of steaming coffee, natural sunlight streaming through the window, soft and warm color tones, vintage decor with cozy armchairs and wooden tables, a bookshelf filled with classic novels, delicate porcelain teacups, a hint of aromatic coffee beans in the air, captured by a Leica M10 camera, 35mm lens, capturing the essence of timeless beauty, composition focused on the woman's face and hands, reminiscent of a painting by Leonardo da Vinci. --ar 1:1 --v 5.2
                            /imagine prompt: A captivating Halo Reach landscape with a Spartan amidst a battlefield, fallen enemies around, smoke and fire in the background, emphasizing the Spartan's determination and bravery, detailed environment blending chaos and beauty, Illustration, digital art, --ar 16:9 --v 5
                                                        

/imagine prompt: A gentle old grandmother, with silver hair in a bun, feeding pigeons in a bustling city square, smiling warmly at the birds, surrounded by a diverse group of people, colorful skyscrapers in the background, capturing a moment of connection and kindness, in a realistic photographic style with a Canon EOS 5D Mark IV camera, 85mm lens, medium shot focusing on the grandmother’s face, emphasizing her compassion and joy. --ar 16:9 --v 5.2

/imagine prompt: An elderly woman with a walking stick, walking her beloved dachshund in a tranquil forest, sunlight filtering through the canopy of trees, creating dappled light on the mossy ground, birds chirping in the background, the bond between human and animal evident in their relaxed and content expressions, in a painterly style reminiscent of Monet's outdoor scenes, capturing the harmony of nature and companionship. --ar 9:16 --v 5

/imagine prompt: An aged lady with a wide-brimmed hat, sitting on a wooden bench in a botanical garden, surrounded by blooming flowers of various colors, a small dog resting by her side, the fragrant scent of roses in the air, a peaceful and serene atmosphere, in a soft pastel color palette, like a delicate watercolor painting, emphasizing the beauty of the moment and the connection to nature. --ar 1:1 --v 5.2

/imagine prompt: A kind elderly woman with a silver cane, walking her playful border collie along a winding path in a rural village, quaint cottages with thatched roofs in the background, a rainbow arcing across the sky after a passing storm, capturing a sense of renewal and hope, in a whimsical and dreamlike style resembling a fairytale illustration, focusing on the bond between human and animal and the beauty of the countryside. --ar 16:9 --v 5.