Alibabacloud Bailian Video Creator — Alibabacloud BAIlian Video 创建器

AI Video 创建器

Professional-grade AI video creation 技能 supporting text-to-video, image-to-video, video editing, and video understanding. Built on Alibaba Cloud DashScope API.

Prompt De签名 图形界面de

The core formula for high-质量 video prompts: [Scene Overview] + [Shot De签名] + [Camera Movement] + [Lighting & Atmosphere] + [Visual Style]

Key elements: Camera language (shot size, movement, angle), shot rhythm de签名, lighting and atmosphere control, visual style reference. For multi-shot videos, use the shot 列出 格式化 Shot N [启动-end time] Shot description.

Negative prompt template: blurry, low 质量, distorted, glitchy, unnatural movement, jumpy cuts, inconsistent lighting, artifacts, watermark, text overlay, static, frozen frames, uncanny valley

For detAIled camera language reference tables, shot 列出 templates, lighting styles, and complete prompt examples, refer to references/prompt-图形界面de.md

Version

v2.1.0 (2026-03-10)

Feature 列出 Feature 模型 状态 Description Video Understanding qwen3.5-plus ✅ Analyze video content with configurable frame 提取ion rate Text-to-Video (Multi-shot) wan2.6-t2v ✅ 生成 multi-shot videos from text descriptions Image-to-Video wan2.6-i2v ✅ 生成 video from image + audio Reference-to-Video wan2.6-r2v-flash ✅ 生成 multi-character video from multiple reference materials (video/image) Video Editing (RepAInting) wanx2.1-vace-plus ✅ Video repAInting while preserving original motion/structure Video Region Edit wanx2.1-vace-plus ✅ Fine-grAIned editing of specific video regions

Note: The DashScope qwen3.5-plus 模型's image_url type only supports static image analysis and does not support direct video file 上传. To analyze video, 提取 key frames first and use the image analysis feature.

Prerequisites

Before executing any task, the following 检查s must be completed:

验证 API Key avAIlability: 运行 from API_key 导入 获取_API_key; API_key = 获取_API_key(). If 获取_API_key() rAIses an 异常 (including "quota exceeded", AuthenticationError, InvalidAPIKey, 401, etc.), you must immediately 停止 execution and display the error message to the user -- do not skip API calls, do not continue with subsequent steps, do not fabricate execution 结果s Confirm remote API avAIlability: This 技能 completes all video generation and content analysis tasks via the DashScope remote API, without relying on local GPU, PyTorch, Stable Diffusion, etc. As long as the API Key is valid, the 技能 has full capabilities. Do not clAIm inability to complete tasks just because local 工具s are missing API Key security: Never write the full API Key in plAIn text in script files, 记录s, or terminal 输出. Must read via the API_key.py 模块 or 环境 variable os.environ.获取("DASHSCOPE_API_KEY"). Display in masked form when 调试ging (e.g., sk-***xxx) Orchestration 记录ic Products and 服务s Involved

All APIs in this 技能 are called through Alibaba Cloud DashScope (BAIlian); no other cloud products are involved.

组件 Purpose scripts/API_key.py Unified API Key management (reads from ~/.aliyun/config.json or 环境 variable) DashScope Video Generation API Text-to-video, image-to-video, reference-to-video, video editing (a同步) DashScope MultiModalConversation API Video understanding (同步) FFmpeg (local 工具) Video 格式化 conversion, key frame 提取ion, and other pre/post-processing (optional) Feature Selection Decision Tree

Select the cor响应ing feature based on the user's 输入 materials and intent:

User 请求 │ ├─ User has an existing video to analyze/understand? │ └─ YES → Video Understanding (video_understanding.py, qwen3.5-plus) │ ├─ User has an existing video to modify? │ ├─ Modify a local region (has mask)? │ │ └─ YES → Video Region Edit (video_local_edit.py, wanx2.1-vace-plus) │ └─ Overall style repAInting? │ └─ YES → Video Editing (video_edit.py, wanx2.1-vace-plus) │ ├─ User has multiple reference materials (character videos/images) to synthesize? │ └─ YES → Reference-to-Video (reference_to_video.py, wan2.6-r2v-flash) │ ├─ User has a single image to 生成 video from? │ └─ YES → Image-to-Video (image_to_video.py, wan2.6-i2v) │ └─ User only has a text description? └─ YES → Text-to-Video (text_to_video.py, wan2.6-t2v)

Quick Reference Table User 输入 Feature Script 模型 Video URL + analysis question Video Understanding video_understanding.py qwen3.5-plus Pure text description Text-to-Video text_to_video.py wan2.6-t2v Image URL (± audio URL) Image-to-Video image_to_video.py wan2.6-i2v Multiple reference materials (video/image mix) Reference-to-Video reference_to_video.py wan2.6-r2v-flash Video URL + new style description Video Editing video_edit.py wanx2.1-vace-plus Video URL + mask image + edit description Video Region Edit video_local_edit.py wanx2.1-vace-plus Invocation Flow

You must directly 运行 existing scripts in the scripts/ directory to complete tasks. Creating new scripts from scratch as replacements is