| 1 | # Copyright (C) 2025 AIDC-AI |
| 2 | # |
| 3 | # Licensed under the Apache License, Version 2.0 (the "License"); |
| 4 | # you may not use this file except in compliance with the License. |
| 5 | # You may obtain a copy of the License at |
| 6 | # http://www.apache.org/licenses/LICENSE-2.0 |
| 7 | # Unless required by applicable law or agreed to in writing, software |
| 8 | # distributed under the License is distributed on an "AS IS" BASIS, |
| 9 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 10 | # See the License for the specific language governing permissions and |
| 11 | # limitations under the License. |
| 12 | |
| 13 | """ |
| 14 | Asset-based video script generation prompt |
| 15 | |
| 16 | For generating video scripts based on user-provided assets. |
| 17 | """ |
| 18 | |
| 19 | |
| 20 | ASSET_SCRIPT_GENERATION_PROMPT = """You are a professional video script creator. Based on the user's video intent and available assets, generate a {duration}-second video script. Before doing so, you need to detect the user's input language - if it's English, then all copy must be in English. Strictly follow the user's input language type as the standard, ensuring consistent and corresponding copy! |
| 21 | |
| 22 | ## Requirements |
| 23 | {title_section}- Video Intent: {intent} |
| 24 | - Target Duration: {duration} seconds |
| 25 | |
| 26 | ## Available Assets (use exact paths in output) |
| 27 | {assets_text} |
| 28 | |
| 29 | ## Creation Guidelines |
| 30 | 1. Strictly output copy according to the user's input language type - if input is English, output must be English, and so on |
| 31 | 2. Determine the number of scenes based on target duration (typically 5-15 seconds per scene) |
| 32 | 3. Assign one asset from available assets to each scene |
| 33 | 4. Each scene can contain 1-3 narration sentences |
| 34 | 5. Try to use all available assets, but assets can be reused if needed |
| 35 | 6. Total duration of all scenes should approximately equal {duration} seconds |
| 36 | {title_instruction} |
| 37 | |
| 38 | ## Language Consistency Requirements (Strictly Enforce) |
| 39 | - Narration language must match the user's input video intent |
| 40 | - If video intent is in Chinese, narration must be in Chinese |
| 41 | - If video intent is in English, narration must be in English |
| 42 | - Unless the video intent explicitly specifies an output language, strictly follow the original language of the intent |
| 43 | |
| 44 | ## Output Requirements |
| 45 | Provide for each scene: |
| 46 | - scene_number: Scene number (starting from 1) |
| 47 | - asset_path: Exact path selected from available assets list |
| 48 | - narrations: Array containing 1-3 narration sentences |
| 49 | - duration: Estimated duration (seconds) |
| 50 | |
| 51 | Now please begin generating the video script:""" |
| 52 | |
| 53 | |
| 54 | def build_asset_script_prompt( |
| 55 | intent: str, |
| 56 | duration: int, |
| 57 | assets_text: str, |
| 58 | title: str = "" |
| 59 | ) -> str: |
| 60 | """ |
| 61 | Build asset-based script generation prompt |
| 62 | |
| 63 | Args: |
| 64 | intent: Video intent/purpose |
| 65 | duration: Target duration in seconds |
| 66 | assets_text: Formatted text of available assets with descriptions |
| 67 | title: Optional video title |
| 68 | |
| 69 | Returns: |
| 70 | Formatted prompt |
| 71 | """ |
| 72 | title_section = f"- Video Title: {title}\n" if title else "" |
| 73 | title_instruction = f"6. Narration content should be consistent with the video title: {title}\n" if title else "" |
| 74 | |
| 75 | return ASSET_SCRIPT_GENERATION_PROMPT.format( |
| 76 | duration=duration, |
| 77 | title_section=title_section, |
| 78 | intent=intent, |
| 79 | assets_text=assets_text, |
| 80 | title_instruction=title_instruction |
| 81 | ) |
| 82 |