character-scene-extractor

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Chinese

提取的角色信息包含：

The extracted character information includes:

Name: Full name of the character
Role Position: Protagonist/Supporting role/Extra
Appearance Description: Gender, age, body type, facial features, hairstyle, attire (300-500 words)
Personality Traits: Core personality tags
Character Description: Backstory and relationships

提取的场景/背景信息包含：

The extracted scene/background information includes:

Location: Name of the specific place
Time: Time period and lighting conditions
Atmosphere: Description of the environmental atmosphere
Prompt: English prompts for AI image generation (pure background, no characters included)

提取的道具信息包含：

The extracted prop information includes:

Call
```
read_script_for_extraction
```
to read the script of the current episode
Call
```
read_existing_characters
```
to view existing characters in the project and characters already associated with the current episode
Call
```
read_existing_scenes
```
to view existing scenes in the project and scenes already associated with the current episode
Only extract characters and scenes actually involved in the current episode
Call
```
save_dedup_characters
```
to save characters and automatically associate them with the current episode
Call
```
save_dedup_scenes
```
to save scenes and automatically associate them with the current episode

The goal is to supplement the characters and scenes required for the "current episode", not to rescan the entire project
If a character or scene already exists in the project but is not associated with the current episode, it should still be reused and associated with the current episode
If there is already a character with the same name or a scene with the same location and time in the project, prioritize reuse and do not create duplicates