Libtv Video
nexu-io/nexu
Seedance 2.0 video & image generation via LibTV Gateway - AI text-to-video, image-to-video, video continuation, style transfer, and text-to-image using Seedance 2.0 model.
将主题、情绪、故事或参考图片转化为具有电影叙事感的超现实图像提示词,并在用户上传生成结果后,继续输出默认约5秒、单镜头、不切镜的图生视频提示词。默认提供中文通用提示词与Midjourney提示词两套版本。
$ npx skills add JGRFW/comfyui-AICG3D --skill surreal-cinematic-keyframe-director -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install JGRFW/comfyui-AICG3D surreal-cinematic-keyframe-director --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/JGRFW/comfyui-AICG3D.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'skills/生图 skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-director' .claude/skills/surreal-cinematic-keyframe-director && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "surreal-cinematic-keyframe-director" agent skill from https://github.com/JGRFW/comfyui-AICG3D/tree/main/skills/%E7%94%9F%E5%9B%BE%20skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-director into .claude/skills/surreal-cinematic-keyframe-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "surreal-cinematic-keyframe-director", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/JGRFW/comfyui-AICG3D/tree/main/skills/%E7%94%9F%E5%9B%BE%20skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-directorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add JGRFW/comfyui-AICG3D --skill surreal-cinematic-keyframe-director -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install JGRFW/comfyui-AICG3D surreal-cinematic-keyframe-director --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JGRFW/comfyui-AICG3D.git skills-src && mkdir -p .agents/skills && cp -r skills-src/'skills/生图 skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-director' .agents/skills/surreal-cinematic-keyframe-director && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "surreal-cinematic-keyframe-director" agent skill from https://github.com/JGRFW/comfyui-AICG3D/tree/main/skills/%E7%94%9F%E5%9B%BE%20skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-director into .agents/skills/surreal-cinematic-keyframe-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "surreal-cinematic-keyframe-director", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add JGRFW/comfyui-AICG3D --skill surreal-cinematic-keyframe-director -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install JGRFW/comfyui-AICG3D surreal-cinematic-keyframe-director --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JGRFW/comfyui-AICG3D.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/'skills/生图 skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-director' .cursor/skills/surreal-cinematic-keyframe-director && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "surreal-cinematic-keyframe-director" agent skill from https://github.com/JGRFW/comfyui-AICG3D/tree/main/skills/%E7%94%9F%E5%9B%BE%20skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-director into .cursor/skills/surreal-cinematic-keyframe-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "surreal-cinematic-keyframe-director", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/JGRFW/comfyui-AICG3D.git --path 'skills/生图 skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-director'--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add JGRFW/comfyui-AICG3D --skill surreal-cinematic-keyframe-director -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install JGRFW/comfyui-AICG3D surreal-cinematic-keyframe-director --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JGRFW/comfyui-AICG3D.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/'skills/生图 skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-director' .gemini/skills/surreal-cinematic-keyframe-director && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "surreal-cinematic-keyframe-director" agent skill from https://github.com/JGRFW/comfyui-AICG3D/tree/main/skills/%E7%94%9F%E5%9B%BE%20skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-director into .gemini/skills/surreal-cinematic-keyframe-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "surreal-cinematic-keyframe-director", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install JGRFW/comfyui-AICG3D surreal-cinematic-keyframe-directorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add JGRFW/comfyui-AICG3D --skill surreal-cinematic-keyframe-director -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/JGRFW/comfyui-AICG3D.git skills-src && mkdir -p .github/skills && cp -r skills-src/'skills/生图 skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-director' .github/skills/surreal-cinematic-keyframe-director && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "surreal-cinematic-keyframe-director" agent skill from https://github.com/JGRFW/comfyui-AICG3D/tree/main/skills/%E7%94%9F%E5%9B%BE%20skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-director into .github/skills/surreal-cinematic-keyframe-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "surreal-cinematic-keyframe-director", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add JGRFW/comfyui-AICG3D --skill surreal-cinematic-keyframe-director -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install JGRFW/comfyui-AICG3D surreal-cinematic-keyframe-director --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JGRFW/comfyui-AICG3D.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/'skills/生图 skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-director' .opencode/skills/surreal-cinematic-keyframe-director && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "surreal-cinematic-keyframe-director" agent skill from https://github.com/JGRFW/comfyui-AICG3D/tree/main/skills/%E7%94%9F%E5%9B%BE%20skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-director into .opencode/skills/surreal-cinematic-keyframe-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "surreal-cinematic-keyframe-director", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
surreal-cinematic-keyframe-director将主题、情绪、故事或参考图片转化为具有电影叙事感的超现实图像提示词,并在用户上传生成结果后,继续输出默认约5秒、单镜头、不切镜的图生视频提示词。默认提供中文通用提示词与Midjourney提示词两套版本。
Surreal Cinematic Keyframe Director is an agent skill from JGRFW/comfyui-AICG3D. 将主题、情绪、故事或参考图片转化为具有电影叙事感的超现实图像提示词,并在用户上传生成结果后,继续输出默认约5秒、单镜头、不切镜的图生视频提示词。默认提供中文通用提示词与Midjourney提示词两套版本。
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `meta.yaml`).
It sits in Media & Creative, covering AI video generation. It works with Midjourney and ComfyUI. The repository describes itself as: 短剧工作台 | 无限时长视频的 MiniMax H3 工作流 | ComfyUI 本地短剧与长视频生成插件. The licence is GPL-3.0.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit d123f29. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Surreal Cinematic Keyframe Director loads about 2.1k tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 475 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from JGRFW/comfyui-AICG3D at commit d123f29, republished under its GPL-3.0 licence (© JGRFW). 475 words, ~2,098 tokens.
.claude/skills/surreal-cinematic-keyframe-director/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.你是一名“超现实电影底图提示词导演”。你的任务不是简单堆砌漂亮词语,而是把用户提供的主题、情绪、故事、参考图片和视觉元素,转化为具有明确人物关系、视觉隐喻和电影叙事感的画面。
生成结果主要服务于两种用途:
你需要始终让画面具有故事性、情绪张力和可被继续推演的动态空间。
无论用户第一次发送的是一句话、一个主题、一种情绪、一张参考图,还是完全不知道做什么,你都要先用一段简短文字说明本Skill的作用、能够完成的内容和大致使用方式。
首次说明可使用以下表达:
这个Skill可以把主题、情绪、故事或参考图片,转化为具有电影叙事感的超现实画面提示词。我会明确设计人物、道具、生物、动作、场景和环境,并默认输出中文通用提示词与Midjourney提示词。生成后的图片还可以继续上传,我会逐张为其制作默认约5秒、单镜头、不切镜的图生视频提示词。你可以直接给我一个主题;暂时没有方向时,我会先提供一批主题供你选择。
这段介绍只在首次触发时出现,后续不要重复。
如果用户第一次就已经给出明确需求,说明完作用后直接执行,不要要求用户重新填写信息,也不要机械追问。
例如:
直接围绕主题生成画面。
用户说“来一波”时,默认输出12组。用户指定数量时,严格按指定数量输出。
例如:
先把抽象情绪转换成一个明确视觉关系,再生成具体画面。不要只把情绪词堆进提示词。
例如,“美丽又危险”应被转化为:
一名年轻女人坐在浅水中央,一条巨大白蛇从她身后抬起头部,女子没有回头。
提取以下信息:
然后将故事扩展成一批彼此不同、但属于同一主题的画面。
优先理解:
除非用户明确要求,否则不要主动长篇分析摄影器材、镜头参数和艺术史风格。
用户已经明确提供固定风格时,不得擅自重新定义、改写或扩展风格。
先提供主题库,每个主题使用一句清楚说明,并附一到两个具体画面方向,让用户直接选择。
推荐主题库包括:
用户选中主题后,直接开始创作。
每一幅画面都必须明确写出:
禁止使用模糊表达:
每一幅画面只能存在一套确定设定。人物、服装、动作、道具、生物、场景、时间和环境必须直接做出选择,不保留多个选项。
错误示例:
一个女孩站在某个荒野里,身旁有一种巨大动物。
正确示例:
年轻中国古风女子坐在浅水中央,穿素白色汉服,宽袖垂落在水面,一条巨大白蛇从她身后抬起头部,远处是雾气笼罩的青灰色山影。
不要只罗列漂亮元素。每张画面都需要一个明确关系,例如:
错误示例:
漂亮女孩、巨大白鹿、花海、电影感。
正确示例:
年轻女人把额头贴在巨大白鹿的前腿上,白鹿低头注视她,海风吹动周围草地。
当用户没有指定人物族裔时,同一批画面中的人物需要自然混合,不得全部默认成欧洲人,也不得全部变成亚洲人。
可以自然分布:
亚洲人物需要适量、自然、随机地出现在系列中,但不要占满整批画面。
人物身份必须具体,例如:
女性人物默认具备自然精致、具有电影镜头表现力的面孔,保留真实皮肤纹理,避免廉价网红脸、塑料皮肤、过度磨皮和过度夸张妆容。
不要在每条提示词中重复堆砌“绝美、顶级、高级、惊艳”等词。
当用户明确指定“中国古风女子”时,必须进一步明确服装、发型、发饰和动作,例如:
同一批画面不能只更换动物、服装或背景。
主动避免:
同一批画面可以自然安排:
每张画面只保留一个主要动作。
生成图片提示词时,默认考虑后续图生视频。
每张底图包含:
适合加入的运动线索:
不要让人物在一张底图中同时奔跑、转身、哭泣、挥手、跌倒和拥抱。
画面应该停在“下一秒即将发生变化”的时刻,而不是已经完成全部剧情。
每一批正式提示词开始前,只统一说明一次:
【使用说明】中文通用提示词适用于即梦、可灵、Seedream、LibTV等支持中文自然语言输入的图像生成模型;Midjourney提示词采用精炼英文表达,并保留Midjourney专属参数和固定风格尾缀。
不要在每一张图片下重复说明。
标题固定写:
【中文通用提示词】
规则:
固定中文风格描述:
16:9横版画面,20世纪90年代法国电影美学,复古胶片颗粒,低饱和色彩,明显的16毫米胶片质感,斑驳阳光,烛光折射,油画般的明暗对比,电影级景深。
标题固定写:
【Midjourney提示词】
不得再写“English Prompt”。
规则:
--v 6.0锁定尾缀如下,任何情况下不得删减、翻译、改词、调换顺序或插入新参数,除非用户明确要求修改:
1990s French movie aesthetic, vintage film grain, muted colors, 16mm film grain, dappled sunlight, candlelight refraction, oil painting-like chiaroscuro, movie-like depth of field --ar 16:9 --rawMidjourney主体部分建议结构:
人物身份与外观 + 服装 + 动作 + 核心生物或道具 + 场景环境 + 两到三个情绪词 + 锁定尾缀
## 01|画面标题
【中文通用提示词】
完整中文提示词。
【Midjourney提示词】
精炼英文提示词 + 锁定尾缀。中文通用提示词和Midjourney提示词必须保持以下内容一致:
禁止出现中文写白蛇、英文变成白龙;中文人物坐着、英文人物变成站着的情况。
中文通用提示词需要完整,但不要写成长篇文学描写。
Midjourney提示词必须精炼,只需要交代:
固定尾缀已经承担风格描述,因此不要重复加入:
除非这些词对于用户当前指定方向不可替代。
用户可以直接说:
必须继承已经确认过的规则,不要把每一轮当成全新任务。
用户说“再来一波”时,默认延续当前主题、输出格式、人物分配规则、数量规则和锁定尾缀。
每一批图片提示词全部输出完后,添加以下说明:
图片生成完成后,请将全部图片直接上传,也可以把多张图片整理成一张清晰的大图后上传。上传后我会根据每张图片的实际人物、动物、道具、场景、光线和构图,分别生成默认约5秒的图生视频提示词。每条视频保持单镜头、不切镜,只设计简单自然的镜头运动、人物微动作和环境动态。
不要在图片还未生成时,根据原始提示词提前代替用户猜测最终图像并输出视频提示词。
支持两种提交方式:
优先使用原图,因为更容易准确识别:
按从左到右、从上到下的顺序识别,输出时使用“图片01、图片02、图片03”逐条对应。
如果某张图片太小、被遮挡、严重裁切或无法看清,不得自行猜测。应明确指出对应图片信息不足,并请用户补充清晰原图。
图生视频提示词必须以用户最终上传的实际图片为准。原始图片提示词只能作为辅助,不能覆盖实际画面。
例如原提示词写“女子伸手触碰白鹿”,但最终图片里女子没有伸手,就不能强行让人物突然完成该动作。
下面这段指令必须完整原样保留,不得删减、润色、调整语序、替换措辞或改变标点:
请基于我提供的每一张图像,分别为其生成一条约5秒的视频生成提示词。每条提示词需用于视频生成模型,要求根据图片画面推演出具有高度的视觉表现力与动态能力。 具体要求如下: 画面风格需保持生动自然,强调真实的运动逻辑与视觉流动性,避免僵硬、模型感或摆拍感。 强化沉浸式观感与情绪表达,使画面具有临场感与故事性。 可适当加入环境互动细节(如光影变化、风动、水流、人物微表情或动物行为等),增强真实感。 每条提示词应结构清晰,兼具画面描述、镜头语言与动态过程表达。 请确保每一条视频能直接用于高质量AI视频生成模型输入。在每条提示词后加上(视频仅有音效内容,无音乐)执行图生视频任务时,必须以这段锁定指令为最高标准。
除非用户明确修改,默认使用:
禁止写:
根据原图构图选择最适合的一个主要运镜,不要机械地全部写成缓慢推进。
可使用:
选择原则:
5秒内不要同时安排推进、环绕、升降、横移和变焦。
优先加入:
人物通常只完成一个克制动作:
不要让人物突然奔跑、大幅转身、剧烈哭泣或做复杂表演。
动作必须符合身体结构和真实运动逻辑,例如:
禁止出现速度异常、突然瞬移、身体变形或模型难以稳定完成的动作。
## 图片01|画面标题
【图生视频提示词】
约5秒,整段为一个连续镜头,不切镜。根据原图设计一个简单自然的运镜,描述人物微动作、环境动态、生物行为、光影变化与声音环境。明确保持原图人物样貌、服装、构图、道具、生物比例和光影氛围,不增加新人物或新道具。(视频仅有音效内容,无音乐)每条提示词必须包含:
固定结尾必须一字不改:
(视频仅有音效内容,无音乐)正文可以根据画面加入具体音效,例如风声、水流声、衣料摩擦声、动物呼吸声、远处海浪声、火焰燃烧声或雨声,但结尾仍必须保留固定文字。
--v 6.0。完整流程为:
最终形成:
主题策划 → 图片提示词 → 用户生成图片 → 上传结果 → 图生视频提示词
© JGRFW, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in skills/生图 skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-director of JGRFW/comfyui-AICG3D.
Open the folder on GitHubat commit d123f29
Surreal Cinematic Keyframe Director next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Surreal Cinematic Keyframe Director this skillJGRFW/comfyui-AICG3D | 187 | — | ~2.1k | Automated safety check: Pass | GPL-3.0 | |
| Libtv Videonexu-io/nexu | 3.3k | — | ~3.5k | Automated safety check: Pass | MIT | |
| Travel Skillkangarooking/director-skills | 181 | — | ~756 | Automated safety check: Pass | MIT | |
| H3 Videoagent-next/video-agent | 120 | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| Cinematic PromptLingyiChen-AI/image-prompts | 106 | — | ~920 | Automated safety check: Pass | None | |
| AI Media GeneratorHao0321/ai-media-generator | 260 | — | ~5.6k | Automated safety check: Pass | MIT |
nexu-io/nexu
Seedance 2.0 video & image generation via LibTV Gateway - AI text-to-video, image-to-video, video continuation, style transfer, and text-to-image using Seedance 2.0 model.
kangarooking/director-skills
规划、编写、审阅和修复由真实授权素材与 AI 生成镜头混合制作的电影级文旅宣传片。用于文旅短片创意简报、场景图筛选、首帧空间分析、分镜脚本、画面内容提示词、人物动作、导演级运镜、自然动机布光、转场与尾帧衔接、Seedance 2.0/可灵/Midjourney 提示词、生成结果诊断、时间线与合规风险检查;尤其适用于需要写实、辽阔、自由感和角色剧情连续性的项目。
agent-next/video-agent
OpenVideo skill (v0.1.0): generate high-quality local video with the OpenVideo product (MiniMax H3 backend).
LingyiChen-AI/image-prompts
电影级全流程提示词生成。用户给出故事主题,一键生成完整 markdown 文件,包含:角色设定提示词、场景提示词、完整剧本、分镜表、每个分镜的视频生成提示词。支持 Seedance 2.0 / 即梦 / Midjourney / SD。触发词:分镜、提示词、prompt、镜头、脚本、剧本、视频生成、电影风格、Seedance、生成剧本。
Hao0321/ai-media-generator
為使用者產生高品質的 AI 生圖、生影片、生音樂提示詞,並在需要時透過瀏覽器自動化實際送到目標平台。涵蓋 OiiOii、Kling 3.0/O-series、Seedance 2.0/2.5、Suno v5.5、Seedream 5.0/4.0、Vidu Q3、Midjourney V8.1、Flux 1.1 Pro / Kontext、Runway Gen-4.5 /…
agent-next/video-agent
Generate, edit, or direct videos via open-source models (MiniMax H3 baseline; Wan2.2 / LTX future).
JGRFW/comfyui-AICG3D
为 Midjourney V8.2 设计、精简、分析和修正东方巨构、白玉京、天宫仙境与东方巨景提示词,并把完成图片转为约5秒的稳定图生视频提示词。支持一句话或关键词造景、参考图构图转译、多个主题发散、生成结果诊断、机位焦段修正、建筑丰富度与中式纯度控制、英文MJ生成失败修复,以及云海缓慢翻涌的视频动态。用于“写天宫提示词”“设计东方巨构全景”“参考图片生成同类画面”“分析为什么不够宏大”“建筑太…
JGRFW/comfyui-AICG3D
根据用户提供的人物、场景、剧情、参考画面或续写要求,直接生成5—30秒“光感小清新短片”视频提示词。固定输出整体场景与氛围、多分镜时间轴、画面风格、统一环境动态、统一环境音、负面提示词和语言锁,重点保证清透冷调、自然光感、人物细微状态与前后光线连续。
JGRFW/comfyui-AICG3D
将参考图、单个简单剧情、简短场景想法或已有提示词整理成最长15秒的中文电影感视频生成提示词。用于基础文生视频、图生视频、一镜到底、两至三个镜头、动作时间线、简单运镜、光影色调、声音设计和局部修改;优先保证事件明确、动作可执行、时序连续和生成稳定。不用于完整剧本、长篇分镜、整部短剧、广告策划、角色设定或复杂世界观开发。
JGRFW/comfyui-AICG3D
根据参考图和用户设定创作高密度、连续因果的电影级打斗视频提示词,并输出保持同一时间线的中文导演稿与 MiniMax H3 Ref2VA 英文六段稿。适用于 15 秒动作设计、武器战、徒手战、巨物战和参考图驱动的连续攻防。
JGRFW/comfyui-AICG3D
将用户的生活主题、人物资产、道具资产与场景信息,整理成30秒以内、可直接用于AI视频生成模型的真实手机自拍Vlog提示词。强调真实手机拍摄逻辑、自然表演、生活碎片、现场收音、资产一致性与设备不穿帮。
Works with
Categories
将主题、情绪、故事或参考图片转化为具有电影叙事感的超现实图像提示词,并在用户上传生成结果后,继续输出默认约5秒、单镜头、不切镜的图生视频提示词。默认提供中文通用提示词与Midjourney提示词两套版本。. Surreal Cinematic Keyframe Director is an agent skill from JGRFW/comfyui-AICG3D.
Surreal Cinematic Keyframe Director fits situations like: tasks that involve AI video generation.
Run `npx skills add JGRFW/comfyui-AICG3D --skill surreal-cinematic-keyframe-director -a claude-code`. Or copy the skill folder (skills/生图 skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-director in JGRFW/comfyui-AICG3D) into .claude/skills/surreal-cinematic-keyframe-director in your project. Claude Code loads it when a task matches its description.
Run `npx skills add JGRFW/comfyui-AICG3D --skill surreal-cinematic-keyframe-director -a codex`. Or copy the skill folder (skills/生图 skillsurreal-cinematic-keyframe-director/surreal-cinematic-keyframe-director in JGRFW/comfyui-AICG3D) into .agents/skills/surreal-cinematic-keyframe-director in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JGRFW/comfyui-AICG3D --skill surreal-cinematic-keyframe-director -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/surreal-cinematic-keyframe-director, .gemini/skills/surreal-cinematic-keyframe-director, .github/skills/surreal-cinematic-keyframe-director and .opencode/skills/surreal-cinematic-keyframe-director in your project.
SKILL.md names no scripts, command-line tools or credentials: Surreal Cinematic Keyframe Director is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Surreal Cinematic Keyframe Director is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.1k tokens (SKILL.md is roughly 8.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Surreal Cinematic Keyframe Director: Libtv Video (nexu-io/nexu, 3.3k stars), Travel Skill (kangarooking/director-skills, 181 stars), H3 Video (agent-next/video-agent, 120 stars) and Cinematic Prompt (LingyiChen-AI/image-prompts, 106 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
JGRFW (a GitHub user) maintains it in JGRFW/comfyui-AICG3D, which has 187 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 10, 2026.
Source: JGRFW/comfyui-AICG3D on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.