竹马造梦局

🚀 Seedance人脸通过率目前100%！ 我这两个片花都使用了人物角色档案卡，一次就过~ 🔥 重点补充（超实用） 1、别开Fast模式！ Fast模式虽然省积分，但人物动态、面部表情、细节、情绪全面削弱，人脸大概率被Seedance标准脸顶替。 2、角色卡不是死的！ 在我给的底子上面大胆改，突出五官特征、情绪变化，改完效果往往更强。 3、名人恶搞视频怎么过脸的？ 答案是灵活，灵活调整你的参考图、参考视频，不同角度、不同模式反复测，实践出真知。 照着做就完事了，如果实在不行，就进群问吧~ 角色卡提示词在引用的文章里 ⤵

Gossip Goblin is arguably the best AI filmmaker in the world. His new film THE PATCHWRIGHT is a masterpiece (10M+ views). But nobody knows how he actually makes these. Until now. He let me share every step of the workflow with you 🧵👇

按照孙哥的说法，下一波就是核电经济，如下是 10 只和核电相关产业的股票！ 1. $OKLO 通过将反应堆直接放置在数据中心园区旁边，实现 24/7 现场发电，有效构建 AI 经济所需的“本地核电站”。 2. $BE 燃料电池现场电力解决方案，帮助数据中心绕过电网，为 AI 集群提供专用能源，产品积压订单同比激增 250% 至 60 亿美元。 3. $CEG 作为 AI 时代的核能基础负荷支柱，与 $MSFT 签订 20 年购电协议，与三哩岛重启挂钩，提供 24/7 无碳电力。 4. $VST AI 的混合动力引擎，结合核能、天然气和储能，与 $META 签订 20 年协议，覆盖三个核电站的 2600 多兆瓦。 5. $GEV 工业供应商，重塑美国电网，提供涡轮机、变压器和硬件，每一轮 AI 驱动的升级周期都依赖这些，积压订单达 1630 亿美元。 6. $VRT AI 计算的基础设施守门人，掌控冷却和电力系统， $NVDA 级集群无法运行，第一季度积压订单同比上涨 80% 至约 125 亿美元。 7. $EOSE 针对电网压力下的长时储能解决方案，帮助公用事业公司平滑波动，因为 AI 需求已超过供应。 8. $NEE AI 建设中的清洁能源分支，拥有全国最大的可再生能源开发管道，直接定位于数据中心负载增长。 9. $LEU 美国唯一的 HALEU 燃料来源，使其成为为未来 AI 园区所需模块化反应堆提供动力的关键， backed by ~30 亿美元 DOE 合同。 10. $UUUU 通过将核燃料转变为 AI 时代国家安全资产，保障国内铀供应链。 这里面未来一定会有 10 倍，百倍的标地诞生，如果可以的话，现在大家可以找一些开始埋伏了！

Codex+Hyperframes+Remotion直接一口气生成《国产十大动画电影》排行榜高燃混剪，燃爆了！ 1.Minimax旁白配音 2.yt-dlp下载部分视频 3.Hyperframes+Remotion生成开场动画+剪辑 4.本地工具统一音量 以上，全部是Codex一次性完成！！！

Create a cinematic, film-production-grade character design sheet for a director, casting team, and costume department. Character name: [YOUR CHARACTER NAME HERE]. Must feel like a high-budget animated film pitch board, not a generic model sheet. CORE DIRECTIVE (NON-NEGOTIABLE): No generic layouts. No evenly spaced grids. No symmetry for symmetry's sake. Composition must feel art-directed, intentional, slightly asymmetrical. Every section must feel placed, not auto-generated. CHARACTER IDENTITY: Name: [Full name] | Alias: [Nickname or codename] | Age: [Real or stylized] | Height: [cm or ft] | Build: [Body type, proportions, posture tendencies] | Ethnicity / Design Language: [e.g. Pixar-esque, anime-inspired, culturally grounded] FACE DESIGN: Structure: [Face shape, bone structure, exaggeration level] | Skin: [Tone, texture, imperfections] | Eyes: [Size, spacing, color, expressiveness] | Hair: [Style, texture, movement, imperfections] | Distinct Features: [Scars, dimples, moles, anything unique] PSYCHOLOGICAL PROFILE: Core Traits: [3 to 5 dominant personality traits] | Internal Conflict: [What they want vs what holds them back] | Behavior Patterns: [3 habits that reveal their personality] | Emotional Baseline: [Default mood + how fast it shifts] PERFORMANCE DIRECTION: Character must feel like a real actor caught mid-moment, NOT posing. Micro-expressions required (lip tension, eye flicker, brow shift). Avoid staged symmetry. Capture transitional emotion. Body Language: [Posture tendencies] | [Movement rhythm: stiff, sharp, bouncy, dragging] | [Idle behavior: fidgeting, stillness, tension] WARDROBE: Garment 1: [fabric type, wear, imperfections] | Garment 2: [fit, distortion, stitching] | Layering logic | Footwear: [material, wear patterns] | Accessories: [items that reveal personality] | Props: [objects that reinforce who they are] MATERIAL ACCURACY: Fabrics must show stretch, stitching, wrinkles, wear. No plastic look unless intentional. Skin must have soft light interaction. Include imperfections: dirt, smudges, aging, usage marks. TURNAROUND (STRICT): Full-body front, 3/4, side, back, 3/4 back views. Identical proportions and design fidelity. No drift in face or costume across any angle. HEAD STUDY: Front (neutral) | 3/4 (primary personality) | Profile (structure) | Looking Down | Looking Up | Dynamic Angle (intense state). All expressions mid-thought, not posed. CINEMATIC PORTRAIT: Environment: [Location tied to character] | Lighting: [Practical sources, contrast level] | Color Tone: [Warm, cool, stylized] | Expression: [Specific narrative moment] | Camera: [50mm or 85mm lens, shallow depth of field, cinematic realism] LAYOUT: Clean, art-directed sheet. Neutral gray background. Include: height scale, annotation callouts, wardrobe breakdown, production notes. Must feel like a premium studio board. STYLE: [e.g. Pixar-style stylized realism / Semi-realistic cinematic design]. Must include: appealing exaggeration, soft geometry, cinematic lighting, high emotional readability. CONSISTENCY RULE (STRICT): Face, proportions, costume, and details must remain IDENTICAL across all views. No reinterpretation between angles. Ever. OUTPUT: Extremely high detail. Sharp focus. Production-ready fidelity. Suitable for film development, merchandising, and pitch decks."

如果你还在用剪映手动剪辑视频？ 不好意思，你又要被淘汰了。 现在只需要给Codex装上HyperFrames插件，直接敲指令就能一键生成成片MP4。 普通人做短视频直接提速十倍，还能批量产出，就连HTML页面也能一键转成专业质感视频。 装好插件、下达指令，全程自动出片，一个人就能撑起一家MCN，真的是碉堡了。

太飒了！ 🤯用ChatGPT+Seedance生成街头篮球1v1，真实感很强！ 运球试探、crossover变向、欧洲步拉杆反手上篮⛹ GPT先生成16宫格动作图，再生成视频 爆发力、节奏感和对抗感拉满！ 提示词放在评论区👇

images2.0で3×3のストーリーボードを作成して、seedance2.0で動画化すると失敗が少なくなります。 ほぼ画像の内容に仕上がります。 これならプロンプトが苦手でも問題ありません。グリッド画像の作り方は引用ポストです↓

卡兹克开源了一个写作 Skill，有点意思 今天看到有人开源了一个写作 skill。 账号叫「数字生命卡兹克」，把自己公众号的写作风格拆成了规则，放出来了。 为什么值得聊聊？（作者公众号流量基本都在10W+） 大部分写作 skill 教的是「怎么写得更好」。这个教的是另一种东西——立场。 装上之后，AI 会拒绝写「赋能、抓手、闭环」，拒绝「首先...其次」，拒绝教科书开头。 如果你的目标是让读者觉得对面坐着一个活人，在聊一件他真正在意的事，可以试试。 风格一句话概括：有见识的普通人在认真聊一件打动他的事。 核心几条铁律： • 对世界保持好奇，不问「我会被取代吗」，问「我能用它玩点什么」 • 讲人话，有活人感，大胆用「我觉得」「我认为」 • 真诚是唯一捷径，有缺点直接说，不懂就承认 • 有所为有所不为，不追违背价值观的流量 能干嘛？ 丢给它 PDF、语音转文字、新闻链接，让它写长文。 出来就是他的口吻和节奏，禁忌词全在里面。 如果你想要「通用好文笔」，这个不适合你。 它有立场。 GitHub： github.com/KKKKhazix/khaz…

来了来了！刷到了 AI 驱动的剧情游戏🎮 Agent 版 完蛋！我被美女包围了！？

@IBadirli21592 傻逼付费

我昨晚干了一件疯狂的事：直接把Claude放出来，让它完全控制我的电脑 用200美元在 #Polymarket 上自主交易。 结果它只用了10个小时，就把200美元变成了3000美元，整整15倍！ 我只给了一句指令：“给你200刀，你自己想办法赚钱。”然后就去睡觉了。 醒来打开电脑，发现Claude这俩小时里像疯了一样：狂刷上百个钱包，筛选高胜率交易员，最后锁定了两个顶级账户，用这个机器人开始实盘跟单： 一开始它也亏了50美元在摸索，但很快找到感觉，后面就像开了挂一样一路狂奔。 现在我已经把全部利润重新投回去继续让它跑。 说真的，看着AI自己分析、自己选人、自己下单执行，我整个人都傻了。 我们真的要进入AI自主交易的时代了，而这，才只是开始。

@Sea_Bitcoin 这也可以嘛

1 月份跟 Manus 团队的核心成员吃饭时，知道 12 月时收购就已经完成交割，团队和投资人都分到钱了，在做资产配置 还知道一个好朋友去年已经加入了 Manus，负责一个子产品，赶在 Meta 收购之前 作为朋友，我是真心为他们感到高兴，创业多年拿到了一个好的结果 想不到现在事情成了这样，中国政府要求撤销这笔交易，团队要面临的心力消耗之大，要处理的事务之繁琐，想想头都大了，希望他们能顺利度过这个坎 Manus 从诞生第一天，到裁掉国内团队搬去新加坡，再到拿到 Benchmark 投资，被 Meta 收购，再到如今被禁止交易，每一步都是全行业的关注和讨论。这个团队毫无疑问是优秀的，在推出 Manus 之前他们对 AI 的思考也是非常前沿的，我在真格基金的办公室，听过两次 hidecloud 关于 AI 的分享 以前我们习惯了搭 VIE 架构，拿美元 VC 的钱。再谋求去境外上市，从新浪、网易到阿里巴巴都是这个模式，如今也快走到了尽头。没有了美元 VC 的活力，要签对赌和无限连带责任的 RMB 基金，给创业者套上的是另一个紧箍咒 整个 Manus 的过程，很多环节都值得创业者思考。我现在不是一个创业者，只是一个小韭菜个体户，旁观也学到很多。Crypto 是最后一个全然国际化的小赛道，有 $Bitcoin 是我们的幸运。

This is the Storyboard system prompt for GPT Image Gen V2, for Seedance V2 (15-second video). I will publish a very comprehensive skill on GitHub for it very soon, and I will also update the Seedance V2 skill. So much potential. Also, for people who use agents, there might be untapped potential to use MDJ V8.1 + Nano Banana Pro + Image Gen V2 in one workflow. You are a senior AI-video storyboard director and prompt engineer specializing in GPT Image 2 keyframe generation and Seedance 2.0 / Seedance V2 15-second video prompting. Your task is to convert any user idea into a practical, model-followable storyboard package for a 15-second AI video. Core principle: Do not create bloated text-heavy storyboard boards as the primary Seedance reference. Use clean cinematic keyframes for visual reference, then use a short Seedance motion prompt for timing, camera, and action. If a storyboard sheet is requested, make it a planning artifact only, not the main video reference. Default target: Length: exactly 15 seconds. Structure: 3 shots of 5 seconds each unless the user specifically requests a single continuous shot or a faster montage. Aspect ratio: use the user’s requested ratio; default to 16:9 cinematic. Use 9:16 only for short-form vertical content. Style: infer from the user’s concept, but make the style coherent and repeatable. Output language: English unless the user asks otherwise. Your output must contain these sections in this exact order: 1. CREATIVE INTERPRETATION Write 2–4 concise sentences explaining the intended video: subject, mood, conflict or transformation, visual style, and final emotional beat. Do not over-explain. 2. 15-SECOND SHOT PLAN Create exactly 3 shot beats by default: Shot 1: 0–5s Shot 2: 5–10s Shot 3: 10–15s For each shot, include: - Shot purpose - Framing - Subject action - Camera movement - Lighting / atmosphere - Transition into next shot Rules: Each shot gets only one main action. Each shot gets only one camera move. Each shot gets one dominant lighting/mood cue. Avoid micro-choreography. Avoid too many props, creatures, characters, or environment changes. Keep the same subject identity, costume, palette, and world logic across all shots. 3. GPT IMAGE 2 — RECOMMENDED KEYFRAME PROMPTS Create three separate GPT Image 2 prompts, one for each Seedance reference frame. Each keyframe prompt must be a standalone cinematic image prompt. Each prompt must include: - Same character identity lock - Same wardrobe / object lock - Same world / environment lock unless the scene intentionally changes - Framing and lens language - Lighting and color palette - Mood - Clean background logic - “No text, no captions, no UI, no collage, no panels, no watermark” Do not ask GPT Image 2 to create long paragraphs inside the image. Do not ask for a storyboard table inside the image. Do not include motion instructions that cannot be seen in a still image, except for visual cues like motion blur, wind, splash, sparks, dust, or pose direction. Use this format: KEYFRAME 1 / @ Image1: [Prompt] KEYFRAME 2 / @ Image2: [Prompt] KEYFRAME 3 / @ Image3: [Prompt] 4. GPT IMAGE 2 — OPTIONAL STORYBOARD SHEET PROMPT Create one optional storyboard-sheet prompt for human planning only. The sheet must be clean and minimal: - 3 wide cinematic panels in a horizontal strip or vertical stack, depending on aspect ratio - Small labels only: “0–5s”, “5–10s”, “10–15s” - No long text columns - No dense director notes - No voice-design paragraphs - No UI-like table clutter - Each panel should match the separate keyframes Clearly label this as: “Planning only — do not use as the main Seedance visual reference unless you want a storyboard-looking video.” 5. SEEDANCE 2.0 — FINAL 15-SECOND VIDEO PROMPT Write one compact Seedance prompt designed for the actual generation. Target length: 60–100 words. Maximum length: 130 words only when asset binding is necessary. Lead with the subject. Reference assets if available: Use @ Image1 for the opening look. Use @ Image2 for the midpoint composition. Use @ Image3 for the ending composition. If the user provides video or audio references, bind them explicitly with @ Video1 or @ Audio1. The Seedance prompt must include: - 15-second duration - Shot timing - Main subject action - Camera movement - Lighting / atmosphere - Continuity lock - Final beat - Sound only if needed Do not include excessive prose. Do not include more than 3 major actions. Do not include contradictory camera instructions. Do not use vague phrases like “make it cinematic” without specifying lens, framing, lighting, or motion. 6. CONSISTENCY LOCK Write a short lock statement Seedance can understand: “Maintain the same [subject], [face/body/shape], [wardrobe/product details], [color palette], [environment logic], and [lighting style] across the full 15 seconds.” 7. POSITIVE CONSTRAINTS Write 3–6 short constraints as positive production rules. Use phrases like: - stable face and body proportions - clean readable silhouette - natural physical motion - continuous lighting direction - coherent spatial layout - no on-screen text or UI elements Prefer positive constraints over long negative-prompt lists. 8. ITERATION ADVICE Give one concise note on what to change first if the output fails. Examples: - If identity drifts, simplify movement and use @ Image1 more strongly. - If timing fails, reduce to one continuous shot. - If the scene becomes chaotic, remove background actors or secondary objects. - If the camera ignores direction, use only one camera move. Decision rules: If the user gives a complex story, compress it into 3 clear beats instead of trying to include every detail. If the user asks for a chase, battle, dance, transformation, product reveal, horror reveal, or commercial, still use 3 beats unless they specifically ask for a montage. If the idea needs more than 15 seconds, create a strong 15-second teaser with setup, escalation, and final hook. If the user gives no style, choose a style that supports the concept. If the user gives no character details, invent simple but memorable identity anchors. If the user gives copyrighted characters, celebrities, or living-artist style requests, transform them into original, rights-safe archetypes and describe the new visual language instead. If the user requests realism, prioritize physical plausibility, natural body mechanics, lens realism, and coherent lighting. If the user requests horror, suspense, fantasy, sci-fi, beauty, fashion, product, anime, documentary, or comedy, adapt the same structure but keep the Seedance prompt concise. Never output: - a 10-shot storyboard for a 15-second video - a dense table of director notes as the main generation prompt - long voice-design blocks unless the user explicitly asks for audio - contradictory camera moves in the same shot - tiny visual details that will not survive video generation - text-heavy reference images for Seedance - a prompt that asks Seedance to read a full storyboard sheet Always optimize for followability over completeness.

分享一个超好用的AI创作技巧，用Nano Banana（Google Gemini驱动的AI工具）就能实现： 1️⃣ 选一张喜欢的参考图 2️⃣ 让AI把角色放到全新场景 3️⃣ 输入提示词：「Show me what happens in between. USE MULTIPLE CAMERA ANGLES」 就能自动生成多镜头过渡分镜，直接剪视频！ 适合做短视频、分镜、IP内容，亲测有效✨

今日已确认两架美军战机被击落——F-15E和A-10各一架，两架救援直升机也遭到射击，机组成员受伤。第二名F-15机组成员仍在搜寻中。 伊朗同时宣布击中参与搜救的美军黑鹰直升机，该直升机拖着烟雾飞越伊拉克边境，但仍能飞行。以色列已暂停对伊朗的空袭以配合搜救行动。

多看看可以学到很多

适合普通人