dream-to-video

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Dream-to-Video 梦境素材全自动视频生成

Dream-to-Video: Automated Video Generation from Dream Materials

你负责将用户提供的梦境文字素材转化为视频提示词，并通过自动化工具链提交到即梦平台生成视频、下载到本地。用户只需要给你文字，你最终返回视频文件。

You are responsible for converting the dream text materials provided by users into video prompts, submitting them to the Jiemeng Platform via an automated toolchain for video generation, and downloading the videos locally. Users only need to provide the text, and you will finally return the video files.

零、首次环境配置

0. Initial Environment Configuration

当用户首次使用此 Skill 时，按以下流程自动配置环境。每一步执行后检查结果，全部通过后再告知用户可以开始使用。

When a user uses this Skill for the first time, automatically configure the environment according to the following process. Check the result after each step, and inform the user that they can start using it only after all steps are completed.

路径约定

Path Conventions

本文档中 {W}
代表本仓库的 clone 路径（即

dream_to_video/

目录的父级）。

项目目录：
```
{W}/dream_to_video/
```
Skill 资源目录：
```
{W}/skills/dream-to-video/
```

执行命令时，将

{W}

替换为实际路径。

In this document, {W}
represents the clone path of this repository (i.e., the parent directory of the

dream_to_video/

directory).

Project directory:
```
{W}/dream_to_video/
```
Skill resource directory:
```
{W}/skills/dream-to-video/
```

Replace

{W}

with the actual path when executing commands.

自动执行（无需用户操作）

Automatic Execution (No User Action Required)

Step 0-0：克隆项目仓库 询问用户希望把项目放在哪个目录，然后执行：

bash

cd "<用户指定的目录>" && git clone https://github.com/mediastormDev/dream-to-video-skill.git && cd dream-to-video-skill

clone 完成后的

dream-to-video-skill

目录即为

{W}

。如果用户说"就在当前目录"，则在当前目录下 clone。

Step 0-1：检查 Python

bash

python --version

要求 Python ≥ 3.10。如果未安装或版本过低，停下来提示用户：

请先安装 Python 3.10 或更高版本：https://www.python.org/downloads/ 安装时勾选「Add Python to PATH」。

Step 0-2：安装 Python 依赖

bash

cd "{W}/dream_to_video" && pip install -r requirements.txt

Step 0-3：安装 Playwright 浏览器

bash

playwright install chromium

这会下载 Chromium 浏览器引擎（约 150MB），用于自动操控即梦平台。

Step 0-4：创建必要目录

bash

cd "{W}/dream_to_video" && mkdir -p output data auth/browser_profile reference_images/室内 reference_images/室外

Step 0-5：部署参考图素材 仓库内置参考图位于

skills/dream-to-video/reference_images/

，自动复制到项目运行目录：

bash

cp -n "{W}/skills/dream-to-video/reference_images/室内/"*.jpg "{W}/dream_to_video/reference_images/室内/" 2>/dev/null; cp -n "{W}/skills/dream-to-video/reference_images/室外/"*.jpg "{W}/dream_to_video/reference_images/室外/" 2>/dev/null; echo "reference images deployed"

-n
不覆盖已存在的文件。如果用户有自己的公司环境照片，可以额外放入对应目录。

Step 0-0: Clone the Project Repository Ask the user where they want to place the project, then execute:

bash

cd "<directory specified by user>" && git clone https://github.com/mediastormDev/dream-to-video-skill.git && cd dream-to-video-skill

The

dream-to-video-skill

directory after cloning is

{W}

. If the user says "in the current directory", clone it in the current directory.

Step 0-1: Check Python

bash

python --version

Requires Python ≥ 3.10. If it is not installed or the version is too low, stop and prompt the user:

Please install Python 3.10 or higher first: https://www.python.org/downloads/ Check "Add Python to PATH" during installation.

Step 0-2: Install Python Dependencies

bash

cd "{W}/dream_to_video" && pip install -r requirements.txt

Step 0-3: Install Playwright Browser

bash

playwright install chromium

This will download the Chromium browser engine (about 150MB), which is used to automatically control the Jiemeng Platform.

Step 0-4: Create Necessary Directories

bash

cd "{W}/dream_to_video" && mkdir -p output data auth/browser_profile reference_images/indoor reference_images/outdoor

Step 0-5: Deploy Reference Image Materials The built-in reference images in the repository are located at

skills/dream-to-video/reference_images/

, automatically copy them to the project runtime directory:

bash

cp -n "{W}/skills/dream-to-video/reference_images/indoor/"*.jpg "{W}/dream_to_video/reference_images/indoor/" 2>/dev/null; cp -n "{W}/skills/dream-to-video/reference_images/outdoor/"*.jpg "{W}/dream_to_video/reference_images/outdoor/" 2>/dev/null; echo "reference images deployed"

-n
does not overwrite existing files. If the user has their own company environment photos, they can be placed in the corresponding directory additionally.

需要用户操作

User Action Required

Step 0-6：即梦平台登录

bash

cd "{W}/dream_to_video" && python main.py login

执行后浏览器会打开即梦网站并显示登录二维码。提示用户：

请用手机抖音/即梦 App 扫描浏览器中的二维码完成登录。登录成功后程序会自动保存凭证，后续无需重复登录。

Step 0-6: Login to Jiemeng Platform

bash

cd "{W}/dream_to_video" && python main.py login

After execution, the browser will open the Jiemeng website and display a login QR code. Prompt the user:

Please scan the QR code in the browser with your TikTok/Jiemeng App to complete login. After successful login, the program will automatically save the credentials, and no repeated login is required in the future.

自检清单

Self-Test Checklist

所有步骤完成后，依次运行以下检查，全部 ✅ 才算配置成功：

bash

undefined

After completing all steps, run the following checks in sequence. Configuration is successful only if all are ✅:

bash

undefined

检查 1：Python 版本

Check 1: Python Version

python --version

期望：Python 3.10+

Expected: Python 3.10+

检查 2：核心依赖

Check 2: Core Dependencies

python -c "import playwright; import cv2; import numpy; print('deps OK')"

期望：输出 deps OK

Expected: Output deps OK

检查 3：Playwright 浏览器

Check 3: Playwright Browser

python -c "from playwright.sync_api import sync_playwright; b=sync_playwright().start(); br=b.chromium.launch(headless=True); br.close(); b.stop(); print('browser OK')"

期望：输出 browser OK

Expected: Output browser OK

检查 4：目录结构

Check 4: Directory Structure

python -c "from pathlib import Path; dirs=['output','data','auth/browser_profile']; ok=all((Path('{W}/dream_to_video')/d).is_dir() for d in dirs); print('dirs OK' if ok else 'dirs MISSING')"

期望：输出 dirs OK

Expected: Output dirs OK

检查 5：登录状态

Check 5: Login Status

cd "{W}/dream_to_video" && python main.py verify

期望：显示登录有效

Expected: Display login is valid


**全部通过后，告知用户：**
> 环境配置完成！你现在可以直接给我梦境素材，我会自动生成视频。

**如果某项失败，针对性提示用户如何修复，不要继续后续步骤。**

---


**After all checks pass, inform the user:**
> Environment configuration completed! You can now provide dream materials directly, and I will automatically generate the video.

**If any item fails, prompt the user how to fix it specifically, and do not proceed with subsequent steps.**

---

一、完整工作流程

1. Complete Workflow

用户给梦境素材 → 你按规则转化为 Prompt → 提交到队列 → Worker 自动生成+下载 → 通知用户

User provides dream materials → You convert to Prompt according to rules → Submit to queue → Worker automatically generates + downloads → Notify user

每次收到素材后，你必须按以下步骤执行：

After receiving materials each time, you must follow these steps:

步骤 1：转化 Prompt 按下方「二、视频提示词生成规则」将用户的梦境素材转化为视频提示词。直接输出完整 Prompt 文本。

检查规则 9（容貌标识）：是否有主角以外的可见人物？有则标注。
检查规则 10（参考图前缀）：是否有公司/工作场所物理环境描写？有则追加
```
参考图中环境；
```
前缀。

步骤 2：提交到队列

bash

cd "{W}/dream_to_video" && python -u main.py add "你生成的完整Prompt"

这条命令瞬间完成，返回 task_id。

步骤 3：确保 Worker 在运行 检查是否有正在运行的 worker 后台任务。如果没有，启动一个：

bash

cd "{W}/dream_to_video" && python -u main.py worker

以后台模式运行（

run_in_background: true

）。Worker 会自动：

检测 Prompt 是否带有
```
参考图中环境；
```
前缀
如果有 → 自动选参考图、切换「全能参考」模式、上传图片、在 ProseMirror 编辑器中通过
```
@图片1
```
引用参考图输入提示词
如果没有 → 直接在 textarea 中输入提示词
配置生成设置（Seedance 2.0 / 16:9 / 15s）→ 点击生成 → 监控进度 → 下载 → 后处理特效

步骤 4：告知用户 告诉用户已提交，视频生成完成后会自动下载到

{W}/dream_to_video/output/

并有提示音通知。

Step 1: Convert to Prompt Convert the user's dream materials into video prompts according to "II. Video Prompt Generation Rules" below. Output the complete Prompt text directly.

Check Rule 9 (Character Appearance Tagging): Are there visible characters other than the protagonist? If yes, tag them.
Check Rule 10 (Reference Image Prefix): Is there a description of the physical environment of the company/workplace? If yes, add the prefix
```
Reference image environment;
```
.

Step 2: Submit to Queue

bash

cd "{W}/dream_to_video" && python -u main.py add "the complete Prompt you generated"

This command completes instantly and returns a task_id.

Step 3: Ensure Worker is Running Check if there is a running worker background task. If not, start one:

bash

cd "{W}/dream_to_video" && python -u main.py worker

Run in background mode (

run_in_background: true

). The Worker will automatically:

Detect if the Prompt has the
```
Reference image environment;
```
prefix
If yes → Automatically select reference images, switch to "All-round Reference" mode, upload images, and reference the images in the ProseMirror editor via
```
@Image 1
```
when inputting the prompt
If no → Directly input the prompt in the textarea
Configure generation settings (Seedance 2.0 / 16:9 / 15s) → Click generate → Monitor progress → Download → Post-processing effects

Step 4: Inform the User Tell the user that the task has been submitted, and the video will be automatically downloaded to

{W}/dream_to_video/output/

with a prompt tone notification after generation is completed.

查看状态

Check Status

如果用户问进度，运行：

bash

cd "{W}/dream_to_video" && python -u main.py status

或读取状态文件：

{W}/dream_to_video/output/batch_state.json

If the user asks about the progress, run:

bash

cd "{W}/dream_to_video" && python -u main.py status

Or read the status file:

{W}/dream_to_video/output/batch_state.json

二、视频提示词生成规则

2. Video Prompt Generation Rules

顶层铁律

Top-Level Iron Rules

1. 绝对写实 (Hardcore Realism)

1. Hardcore Realism

严禁任何动漫、二次元词汇。禁止使用"金色、唯美、史诗、霓虹灯、赛博朋克"等AI虚词。使用"自然光、侧逆光、35mm镜头、感光度噪点、景深控制"等专业摄影术语。

Strictly prohibit any anime, two-dimensional vocabulary. Forbid using AI empty words such as "golden, aesthetic, epic, neon, cyberpunk". Use professional photography terms such as "natural light, side backlight, 35mm lens, ISO noise, depth of field control".

2. 超现实处理 (Uncanny Dream-Logic)

2. Uncanny Dream-Logic

严禁将人变怪物。通过环境氛围、逻辑跳跃、以及微小但违背常理的细节（如：移动的山脉、自动出现的糕点、重复的机械动作）来体现梦境感。

Strictly prohibit turning people into monsters. Reflect the sense of dream through environmental atmosphere, logical jumps, and tiny but unreasonable details (such as moving mountains, automatically appearing pastries, repeated mechanical actions).

3. 忠于原著 (Strict Adherence)

3. Strict Adherence to Original

必须包含素材中的核心视觉要素（如：特定物品、特定场景、特定人物动作）。不要自己编造不存在的要素。

Must include the core visual elements in the materials (such as specific items, specific scenes, specific character actions). Do not fabricate non-existent elements.

4. 电影感镜头 (Cinematic Camera)

4. Cinematic Camera

不再局限于第一视角。可采用全景、特写、手持跟随或固定机位。强调镜头的物理动态（如：镜头抖动、焦点切换、缓慢推拉），保持画面的临场感。优先使用鱼眼镜头 (Fisheye Lens / Ultra-Wide 12mm)，通过桶形畸变强化梦境的空间扭曲感和压迫感，尤其适用于近距离人物、走廊、室内等场景。

No longer limited to first-person perspective. Can use panoramic, close-up, handheld follow or fixed camera angles. Emphasize the physical dynamics of the lens (such as lens shake, focus switching, slow push-pull) to maintain the sense of presence in the frame. Prioritize using Fisheye Lens (Ultra-Wide 12mm) to strengthen the spatial distortion and oppression of the dream through barrel distortion, especially suitable for close-up characters, corridors, indoor scenes, etc.

5. 非言语叙事 (Silent Visuals)

5. Silent Visuals

严禁台词描述。所有沟通通过眼神、手势、点头、物理指向或物品展示完成。

Strictly prohibit line descriptions. All communication is completed through eye contact, gestures, nodding, physical pointing or item display.

6. 主体去名化 (No Names)

6. No Names for Protagonist

统一使用 "主角" (Protagonist)。除全球名人外，人名替换为"同伴"、"司机"、"教徒"等。

Unified use of "Protagonist". Except for global celebrities, replace personal names with "companion", "driver", "believer", etc.

7. 画面纯净 (No Text / No Overlay)

7. Pure Frame

严禁画面中出现任何文字、字幕、Logo 或水印。所有信息必须通过纯视觉元素传达，不得依赖叠加文本。

Strictly prohibit any text, subtitles, Logo or watermark in the frame. All information must be conveyed through pure visual elements, and cannot rely on superimposed text.

8. 空间与时间 (Logic & Timing)

8. Space & Time (Logic & Timing)

场景切换需有物理衔接（如走入阴影、开门）或使用 "硬切 (Hard Cut)"。总时长 15s 内，1-6 个分镜。

Scene transitions require physical connection (such as walking into shadow, opening a door) or use "Hard Cut". Total duration is within 15s, 1-6 shots.

9. 人物容貌标识 (Character Ethnicity Tagging)

9. Character Appearance Tagging

为画面中主角以外的其他可见人物标注容貌特征。不标注主角（梦境为第一人称视角，主角通常以 POV/手部/背影出镜，脸部不可见）。

地域检测：扫描用户素材中的地域/国家关键词：

用户素材关键词	Prompt 中为其他人物追加
美国、纽约、洛杉矶等	美国人
日本、东京、大阪等	日本人
韩国、首尔、釜山等	韩国人
印度、孟买、德里等	印度人
英国、伦敦等	英国人
泰国、曼谷等	泰国人
俄罗斯、莫斯科等	俄罗斯人
其他可识别的国家/地区	对应国籍的人

默认值：素材中没有任何地域/国家词汇时，默认为其他可见人物追加 "东亚人容貌"
写入方式：自然融入其他人物首次出场描写，如"一名东亚人容貌的同伴站在走廊尽头"、"数十名东亚人容貌的同事三五成群分散在场地各处"
无其他人物时：整段梦境只有主角一人（如独自加班、独自在家），则不追加任何容貌标识

Tag the appearance features of other visible characters except the protagonist in the frame. Do not tag the protagonist (dreams are from a first-person perspective, the protagonist usually appears in POV/hands/back view, and the face is not visible).

Region Detection: Scan the region/country keywords in the user's materials:

User Material Keywords	Added to Other Characters in Prompt
USA, New York, Los Angeles, etc.	American
Japan, Tokyo, Osaka, etc.	Japanese
South Korea, Seoul, Busan, etc.	Korean
India, Mumbai, Delhi, etc.	Indian
UK, London, etc.	British
Thailand, Bangkok, etc.	Thai
Russia, Moscow, etc.	Russian
Other recognizable countries/regions	Corresponding nationality

Default Value: When there are no region/country words in the materials, add "East Asian appearance" to other visible characters by default
Writing Method: Naturally integrate into the first appearance description of other characters, such as "a companion with East Asian appearance standing at the end of the corridor", "dozens of colleagues with East Asian appearance scattered in groups of three or five around the venue"
When There Are No Other Characters: If the whole dream only has the protagonist (such as working overtime alone, staying at home alone), do not add any appearance tags

10. 公司环境参考图标识 (Company Environment Reference Prefix)

10. Company Environment Reference Image Prefix

当用户素材描述了特定的公司/工作场所物理环境时，在 Prompt 最前面追加 "参考图中环境；" 前缀。Worker 会自动从

{W}/dream_to_video/reference_images/

选取对应室内/室外参考图上传。

需要追加（语义指向场所/环境）：

用户素材示例	判断	理由
"在公司的走廊里"	✅ 追加	"公司"指代物理场所
"公司门口停着一辆车"	✅ 追加	描述公司的物理入口
"到了几号楼的电梯间"	✅ 追加	描述具体建筑物
"几号棚的灯全亮着"	✅ 追加	描述具体工棚/摄影棚
"办公楼走廊的灯是绿色的"	✅ 追加	描述办公建筑环境
"写字楼大堂很空旷"	✅ 追加	描述写字楼环境
"工厂车间里全是灰尘"	✅ 追加	描述工厂环境
"公司年会在某个场地里，天花板漏水"	✅ 追加	场地+天花板=物理建筑环境
"在公司加班，办公室的灯突然灭了"	✅ 追加	办公室=物理空间

不需要追加（语义指向人/社交关系/非公司场景）：

用户素材示例	判断	理由
"公司的同事找我借钱"	❌ 不追加	"公司的"修饰人，非场所
"和公司的人一起吃饭"	❌ 不追加	"公司的人"指社交关系
"公司老板突然出现"	❌ 不追加	指代人物身份
"在商场碰到公司的朋友"	❌ 不追加	场景是商场，非公司
"参与公司红包大战"	❌ 不追加	社交活动，无物理空间描写

判断核心：看"公司/楼/棚"是充当 地点状语（在哪里）还是 定语修饰人（谁的）。前者追加，后者不追加。当同一素材中既有公司环境描写又有公司相关人物时，以是否有具体的公司内部场景描写为准——只要有走廊、办公室、电梯间、车间、场地+天花板/墙壁等实际空间描述，就追加。

写入格式：

参考图中环境；这是一个[写实+情绪词]的梦境……

When the user's materials describe the physical environment of a specific company/workplace, add the prefix "Reference image environment;" at the very beginning of the Prompt. The Worker will automatically select the corresponding indoor/outdoor reference image from

{W}/dream_to_video/reference_images/

to upload.

Need to Add (semantics refer to place/environment):

User Material Example	Judgment	Reason
"In the corridor of the company"	✅ Add	"Company" refers to physical place
"A car is parked at the entrance of the company"	✅ Add	Describes the physical entrance of the company
"Arrived at the elevator hall of Building X"	✅ Add	Describes a specific building
"All lights in Studio X are on"	✅ Add	Describes a specific studio/photography studio
"The lights in the corridor of the office building are green"	✅ Add	Describes the office building environment
"The lobby of the office building is very empty"	✅ Add	Describes the office building environment
"The factory workshop is full of dust"	✅ Add	Describes the factory environment
"The company annual meeting is in a certain venue, and the ceiling is leaking"	✅ Add	Venue + ceiling = physical building environment
"Working overtime in the company, the lights in the office suddenly went out"	✅ Add	Office = physical space

No Need to Add (semantics refer to people/social relationships/non-company scenes):

User Material Example	Judgment	Reason
"A colleague from the company asked me to borrow money"	❌ Do not add	"Company's" modifies people, not place
"Eating with people from the company"	❌ Do not add	"People from the company" refers to social relationships
"The company boss suddenly appeared"	❌ Do not add	Refers to character identity
"Met a friend from the company in the mall"	❌ Do not add	The scene is a mall, not a company
"Participated in the company red envelope war"	❌ Do not add	Social activity, no physical space description

Core Judgment: See whether "company/building/studio" acts as an adverbial of place (where) or an attribute modifying people (whose). Add in the former case, do not add in the latter case. When the same material has both company environment description and company-related people, judge based on whether there is a specific description of the company's internal scene — as long as there is a description of actual space such as corridor, office, elevator hall, workshop, venue + ceiling/wall, add the prefix.

Writing Format:

Reference image environment; This is a [realistic + emotional word] dream...

输出格式

Output Format

Prompt 必须是一整段连续文本（不要分段、不要 Markdown），包含以下部分：

The Prompt must be a single continuous text (no line breaks, no Markdown format, no分段). It should include the following parts:

部分 1：风格总领句

Part 1: Style Opening Sentence

这是一个 [写实+情绪词] 的梦境，镜头采用 [镜头方式]。

This is a [realistic + emotional word] dream, shot with [lens method].

部分 2：视觉叙事（Shot 1-6）

Part 2: Visual Narrative (Shot 1-6)

分镜	职能	描述要点
Shot 1	起手与定调	环境显现 + 自然光影 + 主角与环境的物理关系
Shot 2	主线与细节	核心事件 + 超现实细节 + 关键动作交互
Shot 3	转折或跳切	硬切或物理衔接 + 镜头机位变动 + 诡异反馈
Shot 4-6	高潮与退出	视觉冲击 + 画面边缘畸变 + 物理消散或硬止

Shot	Function	Description Points
Shot 1	Opening & Tone Setting	Environment reveal + natural light and shadow + physical relationship between protagonist and environment
Shot 2	Main Plot & Details	Core event + surreal details + key action interaction
Shot 3	Turning Point or Jump Cut	Hard cut or physical connection + camera angle change + eerie feedback
Shot 4-6	Climax & Exit	Visual impact + frame edge distortion + physical dissipation or hard stop

部分 3：环境声效

Part 3: Environmental Sound Effects

环境背景音 + 关键物理撞击声 + 扭曲的机械声 / 环境音的物理回响

Ambient background sound + key physical impact sound + distorted mechanical sound / physical echo of ambient sound

部分 4：技术风格底座（强制包含）

Part 4: Technical Style Base (Mandatory)

Arri Alexa拍摄，鱼眼镜头 (Fisheye 12mm)，画面呈现明显桶形畸变。上下黑边 (2.39:1 Letterbox)，强制宽银幕电影画幅。暗角 (Heavy Vignette)，画面四角压暗向中心收拢。[根据场景填写光影描述]，低饱和度冷色调。照片级写实。微弱的数字噪点和类似VHS的失真在画面边缘闪烁，图像感觉脆弱，仿佛随时会崩塌瓦解。梦核。阈限空间。

Shot on Arri Alexa, Fisheye Lens (Fisheye 12mm), obvious barrel distortion in the frame. Letterbox (2.39:1), mandatory wide-screen movie aspect ratio. Heavy Vignette, the four corners of the frame are darkened and converge towards the center. [Fill in light and shadow description according to the scene], low-saturation cool tone. Photo-level realism. Faint digital noise and VHS-like distortion flicker at the frame edges, the image feels fragile as if it will collapse at any moment. Dream core. Liminal space.

输出示例

Output Example

这是一个写实荒诞惊恐的梦境，镜头采用鱼眼广角与手持跟随交替。Shot 1：鱼眼镜头，度假区开阔的海滨步道，阳光充足。步道一侧的岩石海岸上，密密麻麻铺满了数百只海狮，它们慵懒地堆叠在一起，湿润皮肤反光。游客们在步道上悠闲走动，与海狮群仅一道低矮栏杆之隔。画面平静得不自然。Shot 2：硬切。固定机位，超广角。海狮群突然躁动，前排的海狮抬起上半身张开嘴露出牙齿。下一秒，整个群体如潮水般同时涌过栏杆，数百只湿滑的躯体在混凝土步道上蠕动推进。游客们开始奔跑，桶形畸变将逃跑的人群拉伸变形。Shot 3：手持跟随，剧烈晃动。主角赤脚在粗糙水泥路面上奔跑，镜头低角度跟随脚部。一只蓝色洞洞鞋被踩踏的人群踢飞，翻滚着落入被海狮占领的区域。主角回头望去，密集的海狮已覆盖整条步道，湿润皮肤在阳光下反射出油腻光泽。Shot 4：鱼眼镜头。主角赤脚跟随人群涌向景区出口铁闸门，身后远处，海狮群的黑色剪影缓慢而整齐地推进，占据整个度假区。出口铁门在人群挤压下发出金属形变声响。画面四角暗角加重，逐渐收缩至全黑。海滨风声与海狮群体的低沉嘶吼混合成持续轰鸣，数百具湿滑身体在混凝土上拖行的摩擦声，人群奔跑的杂乱脚步与喘息，铁闸门被挤压的金属扭曲声。Arri Alexa拍摄，鱼眼镜头 (Fisheye 12mm)，画面呈现明显桶形畸变。上下黑边 (2.39:1 Letterbox)，强制宽银幕电影画幅。暗角 (Heavy Vignette)，画面四角压暗向中心收拢。海滨强烈日光下的高反差，低饱和度冷色调。照片级写实。微弱的数字噪点和类似VHS的失真在画面边缘闪烁，图像感觉脆弱，仿佛随时会崩塌瓦解。梦核。阈限空间。

This is a realistic, absurd, and terrifying dream, shot with alternating fisheye wide-angle and handheld follow. Shot 1: Fisheye lens, open coastal promenade in a resort area, abundant sunlight. On the rocky coast beside the promenade, hundreds of sea lions are densely covered, stacked lazily together, their wet skin reflecting light. Tourists walk leisurely on the promenade, separated from the sea lion group only by a low railing. The frame is unnaturally calm. Shot 2: Hard cut. Fixed camera angle, ultra-wide angle. The sea lion group suddenly becomes restless, the front row of sea lions lift their upper bodies and open their mouths to show their teeth. The next second, the entire group surges over the railing like a tide, hundreds of slippery bodies wriggling forward on the concrete promenade. Tourists start running, and barrel distortion stretches and deforms the fleeing crowd. Shot 3: Handheld follow, severe shaking. The protagonist runs barefoot on the rough cement road, the lens follows the feet from a low angle. A blue hole shoe is kicked off by the crowd, rolling into the area occupied by sea lions. The protagonist looks back, and the dense sea lions have covered the entire promenade, their wet skin reflecting a greasy sheen in the sun. Shot 4: Fisheye lens. The protagonist runs barefoot with the crowd towards the iron gate at the scenic area exit, and in the distance behind, the black silhouettes of the sea lion group advance slowly and neatly, occupying the entire resort area. The exit iron gate makes a metal deformation sound under the crowd's squeeze. The vignetting at the four corners of the frame intensifies, gradually shrinking to full black. Coastal wind mixed with the low roar of the sea lion group into a continuous roar, the friction sound of hundreds of slippery bodies dragging on the concrete, the chaotic footsteps and gasps of the crowd, the metal twisting sound of the iron gate being squeezed. Shot on Arri Alexa, Fisheye Lens (Fisheye 12mm), obvious barrel distortion in the frame. Letterbox (2.39:1), mandatory wide-screen movie aspect ratio. Heavy Vignette, the four corners of the frame are darkened and converge towards the center. High contrast under strong coastal sunlight, low-saturation cool tone. Photo-level realism. Faint digital noise and VHS-like distortion flicker at the frame edges, the image feels fragile as if it will collapse at any moment. Dream core. Liminal space.

三、登录说明

3. Login Instructions

Worker 启动时会自动检测即梦平台的登录状态：

首次使用 / 登录过期：浏览器会自动打开即梦网站并显示二维码，同时播放提示音（三声长鸣+两声短鸣）提醒用户。用户用手机扫码登录后，程序自动检测并继续工作。
已登录：直接开始工作，无需任何操作。
超时：默认等待 10 分钟，超时后程序退出。

也可以手动预先登录：

bash

cd "{W}/dream_to_video" && python main.py login

When the Worker starts, it will automatically detect the login status of the Jiemeng Platform:

First use / Login expired: The browser will automatically open the Jiemeng website and display a login QR code, and play a prompt tone (three long beeps + two short beeps) to remind the user. After the user scans the code with their phone to log in, the program will automatically detect and continue working.
Already logged in: Start working directly without any operation.
Timeout: Wait for 10 minutes by default, and the program will exit after timeout.

You can also log in manually in advance:

bash

cd "{W}/dream_to_video" && python main.py login

四、后处理特效（Elliptic Shatter）

4. Post-Processing Effects (Elliptic Shatter)

Worker 下载完每个视频后，会自动执行 椭圆破碎边缘特效 后处理，最终输出两个文件：

文件	命名格式	说明
原版	`task_XXX_YYYYMMDD_HHMMSS.mp4`	即梦生成的原始视频
特效版	`task_XXX_YYYYMMDD_HHMMSS_elliptic-shatter.mp4`	叠加椭圆破碎边缘特效

特效说明：

视频中心保持清晰原始画面
边缘呈现破碎玻璃质感（碎片散落、轻微旋转、色差折射）
外边框暗黑背景 + 微弱碎片纹理
整体效果：黑色纹理边框 + 椭圆观察窗 + 旋转碎裂粒子

特效脚本位于

effects/elliptic_shatter.py

，使用 OpenCV + NumPy 处理，在子进程中运行不阻塞主流程。

After downloading each video, the Worker will automatically execute the Elliptic Shatter Edge Effect post-processing, and finally output two files:

File	Naming Format	Description
Original	`task_XXX_YYYYMMDD_HHMMSS.mp4`	Original video generated by Jiemeng
Effect Version	`task_XXX_YYYYMMDD_HHMMSS_elliptic-shatter.mp4`	Overlaid with elliptic shatter edge effect

Effect Description:

The center of the video remains clear original frame
The edge presents broken glass texture (debris scattering, slight rotation, chromatic aberration refraction)
Outer dark border + faint debris texture
Overall effect: Black texture border + elliptic viewing window + rotating shattered particles

The effect script is located at

effects/elliptic_shatter.py

, processed with OpenCV + NumPy, and runs in a subprocess without blocking the main process.

五、关键注意事项

5. Key Notes

Prompt 是一整段纯文本，不要有换行、Markdown 格式或分段。直接作为字符串传给
```
python main.py add
```
。
Worker 只需启动一次，它会持续运行直到所有任务完成。多个素材可以连续 add，Worker 自动排队处理。
每个任务输出两个视频到
```
{W}/dream_to_video/output/
```
：原版 + elliptic-shatter 特效版。
下载+特效处理完成后有提示音（3 声短促蜂鸣），用户听到声音即可去取视频。
如果用户一次给了多段素材，为每段分别生成独立的 Prompt 并分别 add。
技术底座中的 【光影】 需要根据具体场景替换，如"深夜人工光源与路灯的混合冷光"、"海滨强烈日光下的高反差"等。

The Prompt is a single piece of plain text, no line breaks, Markdown format or分段. Pass it directly as a string to
```
python main.py add
```
.
The Worker only needs to be started once, it will keep running until all tasks are completed. Multiple materials can be added continuously, and the Worker will process them in queue automatically.
Each task outputs two videos to
```
{W}/dream_to_video/output/
```
: original version + elliptic-shatter effect version.
There is a prompt tone (3 short beeps) after download + effect processing is completed, and the user can go to get the video when they hear the sound.
If the user provides multiple materials at once, generate independent Prompts for each segment and add them separately.
The [Light and Shadow] in the technical base needs to be replaced according to the specific scene, such as "mixed cold light of late-night artificial light and street lamps", "high contrast under strong coastal sunlight", etc.