菜单
Use when applying open-source warm cinematic portrait filters to Dasheng talking-head videos after rough cut.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when Dasheng Publish needs to route Xiaohongshu publishing or content access through API-first CLI, MCP, or browser fallback bridges.
Use when Dasheng Publish needs to prepare, upload, or package Bilibili video submissions from completed transwrite video channel packs.
Use when running Stage 3 Draft from approved Brief topics and producing Reasoning Sheets, standard drafts, and draft quality gates.
Use when the workflow enters Postmortem after Publish and published content needs to be evaluated with performance data, Publish Guard status, accuracy checks, and knowledge-base writeback suggestions.
Use when Dasheng draft or transwrite needs HTML Anything templates, editable article HTML, social cards, posters, or visual HTML references.
Use when Dasheng transwrite needs no-human or human-material talking-head videos rendered through the local html-video project.
| name | dasheng-video-open-filter |
| description | Use when applying open-source warm cinematic portrait filters to Dasheng talking-head videos after rough cut. |
这是 transwrite -> talking_head_video 的可选后处理子环节，用于粗剪后给真人口播视频做低风险视觉增强。
默认不再额外生成字幕，适合原视频已经烧录大字幕的场景。
hqdn3d：全局降噪柔化bilateral：亮度平面轻磨皮colorbalance / colorlevels / eq：暖光电影调色、增白、对比度与饱和度gradfun：减轻色带unsharp：柔化后轻锐化vignette：轻电影暗角scale / pad：低风险轻拉瘦afftdn -> dynaudnorm -> acompressor -> loudnorm -> alimitercd "${DASHENG_WORKSPACE:-/Volumes/PSSD/Projects/公众号文章}"
.venv_media/bin/python scripts/video_open_filter.py \
--input-video "/path/to/roughcut_hardsub.mp4" \
--output-dir "产物/06_转写生产/<run_id>/talking_head_video/open_filter" \
--preset warm_cinema \
--strength medium
先看 15 秒预览：
.venv_media/bin/python scripts/video_open_filter.py \
--input-video "/path/to/roughcut_hardsub.mp4" \
--output-dir "tmp/video_filter_preview" \
--preset warm_cinema \
--strength medium \
--preview-only
soft：轻暖光、轻柔化，最不容易塑料感。medium：默认交付强度，暖光明显，人物更白，画面更电影。strong：仅用于灰暗、噪点重、人物太暗的视频；容易让字幕边缘和皮肤质感变假。slim-factor 不低于 0.94；推荐 0.982-0.988。