video-genGenerate a video from a story-telling narration script plus the author's photos, using Seedance 2.0 image-to-video via OpenRouter's asynchronous video API: pre-render gates (face-scan, narrative order, risk-POC), then per-clip submit -> poll -> download, then ffmpeg assembly. Multi-clip projects default to silent clips plus one continuous soundtrack (synthesized or royalty-free/PD); subtitle voiceover is the fallback (no OpenRouter TTS). Verified working 2026-08-15 (POC: 4s 480p clip, $0.28, ~3 min). Use when the user asks to render a narration script into a video, generate a 视频, or run the death-in-Mexico project's video pipeline. Related terms: Seedance, 视频生成, OpenRouter, image-to-video.
ai-image-genAI 图像生成专业版,通过执行脚本调用 Gemini Flash Image API 完成图像生成与编辑。 核心能力: - 文生图: 文本提示词生成图像,支持主体/场景/光线/风格/色调/构图等维度描述 - 图生图(图+文): 基于参考图像与文本提示进行二次创作 - 风格转换: 将图片转换为水彩/油画/赛博朋克/...
finance-report-analyzer分析Excel/PDF财务数据，生成含趋势迷你图的交互式报告，支持预测标记、差异着色及多场景应用。