两个角色的时候，会出现对白混乱的情况，请问有什么策略可优化
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.1k
- Forks
- 93
- Avg merge
- 1m
- Merged PRs (30d)
- 1
Description
两个角色的时候，会出现对白混乱的情况，请问有什么策略可优化
prompts：
角色1是左边蒙面、穿黑色紧身忍者服、背着短刀的男忍者。角色2是右边扎着高马尾、穿深蓝色网状护甲、腰间挂着苦无袋的女忍者。\n忍者村一处偏僻的瓦房楼顶，四周一片漆黑，只有远处的零星灯火和冷冽的月光。风轻轻吹过，屋瓦上结了一层薄霜，氛围紧张而压抑。\n分镜1：双人中景镜头。两名忍者蹲伏在瓦片上，男忍者（角色1）压低声音，警惕地环顾四周，侧头对女忍者（角色2）说道："目标出现了，行动！"\n分镜2：女忍者（角色2）的特写镜头。她眼神犀利，微微点头，低声回应道："明白，按计划行事。" 随后她伸手摸向腰间的苦无。\n分镜3：双人中景镜头。男忍者率先起身，身形一闪消失在夜色中，女忍者紧随其后，两人迅速消失在房顶。\n背景音乐是低沉、快速的太鼓和竹笛声，节奏紧凑，充满悬疑感。男忍者的声音低沉沙哑；女忍者的声音清脆干练。
结果视频：
https://github.com/user-attachments/assets/f3ada52c-1597-45a5-b109-4739900014dc
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the two-character prompt and the linked result video, then reproduce the dialogue-confusion behavior using the reported setup. The issue does not name a code entry point, test, or expected implementation; done would require an agreed strategy or change that reliably keeps each character's dialogue distinct.
Written by the indexing model from the issue text.
Assessment
- Domain
- ai, audio-video-rtc
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100