Rachel🥥's banner

Rachel🥥

@Zesee • 16,521 subscribers

00年｜上交 x 帝国理工｜AI Spark创始人｜前微软&亚马逊产品经理｜分享AI使用干货与商业化变现｜抖音/小红书：Rachel的AI使用日记｜[email protected]

Shorts

复刻了抖音最近超火的矢量手势

复刻了抖音最近超火的矢量手势

45,600 views

Fable 5 comes back！It can now build playable game prototypes. I think it is actually a signal for where AI coding is going. Making a game is not just “write some code.” Even a small browser game needs: game loop；character movement；collision logic；scoring system；UI states；physics tuning；visual feedback；bug fixing；playtesting This is why game prototyping is a great test for AI models. A model cannot fake it with a pretty answer. Either the game runs, or it does not. What impressed me about Fable 5 is that it is useful for the messy middle: turning an idea into mechanics, turning mechanics into code, debugging broken interactions, and iterating until the prototype feels playable. But here is the practical part: I would not use the strongest model for every step. For game building, I would split the workflow: 1. Fable 5 for game design + architecture 2. a fast coding model for routine implementation 3. a vision-capable model for screenshot/UI feedback 4. a cheaper model for docs, test cases, and small fixes 5. fallback when latency, cost, or output quality becomes a problem That is the real AI coding stack. Not “one magic model does everything.” More like: the right model, for the right task, at the right cost, with fallback when things break. This is why I’ve been looking at ZenMux ZenMux. ZenMux gives developers one gateway to access multiple leading AI models, with OpenAI / Anthropic / Google Vertex compatible APIs, cost tracking, quality benchmarks, auto-routing, and compensation when output quality, latency, or throughput falls short. If AI can now make games, the next question is not just “which model is strongest?” It is:how do we manage the whole model workflow Fable 5 shows the creative ceiling. ZenMux is closer to the infrastructure layer you need when AI coding becomes a real production habit.

Fable 5 comes back！It can now build playable game prototypes. I think it is actually a signal for where AI coding is going. Making a game is not just “write some code.” Even a small browser game needs: game loop；character movement；collision logic；scoring system；UI states；physics tuning；visual feedback；bug fixing；playtesting This is why game prototyping is a great test for AI models. A model cannot fake it with a pretty answer. Either the game runs, or it does not. What impressed me about Fable 5 is that it is useful for the messy middle: turning an idea into mechanics, turning mechanics into code, debugging broken interactions, and iterating until the prototype feels playable. But here is the practical part: I would not use the strongest model for every step. For game building, I would split the workflow: 1. Fable 5 for game design + architecture 2. a fast coding model for routine implementation 3. a vision-capable model for screenshot/UI feedback 4. a cheaper model for docs, test cases, and small fixes 5. fallback when latency, cost, or output quality becomes a problem That is the real AI coding stack. Not “one magic model does everything.” More like: the right model, for the right task, at the right cost, with fallback when things break. This is why I’ve been looking at ZenMux ZenMux. ZenMux gives developers one gateway to access multiple leading AI models, with OpenAI / Anthropic / Google Vertex compatible APIs, cost tracking, quality benchmarks, auto-routing, and compensation when output quality, latency, or throughput falls short. If AI can now make games, the next question is not just “which model is strongest?” It is:how do we manage the whole model workflow Fable 5 shows the creative ceiling. ZenMux is closer to the infrastructure layer you need when AI coding becomes a real production habit.

61,441 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Rachel的AI分身上线后续会给她新开一个抖音号大家觉得形象状态怎么样🤓

Rachel的AI分身上线后续会给她新开一个抖音号大家觉得形象状态怎么样🤓

165,233 views • 20 days ago

Most AI research demos show you a polished answer. This one showed me the disagreement that happened before the answer. I gave Ling-3.0-flash Ant Ling a deliberately difficult question: Do four-day workweeks actually increase productivity, or do they simply compress the same workload into fewer days? Instead of asking for a quick summary, I asked it to coordinate five specialist roles: a scientist, a data analyst, a cross-validator, an archivist, and a research writer. Each role had a separate responsibility. The scientist defined the competing hypotheses. The analyst extracted comparable findings. The archivist tracked the sources. The writer could only use approved claims. And the cross-validator had one job: challenge anything that sounded more confident than the evidence allowed. That last role changed the result. The team reviewed 12 sources and challenged six major claims. Three claims were narrowed. One was rejected entirely. Even a widely repeated claim about a 40% productivity increase did not survive the evidence check. That is the part I wanted to see from an AI research workflow. Not just more information, but visible resistance to weak evidence. The final output included: - a direct executive answer - a structured research paper - a source and evidence table - a disagreement log - a six-slide executive deck - a quality-control summary The conclusion was also more useful than a simple yes or no: reduced working hours may maintain productivity and improve wellbeing under certain conditions, while compressing the same workload into fewer days can increase fatigue and intensity. The evidence did not support a universal productivity claim. What impressed me was not that Ling-3.0-flash generated a long response. Plenty of models can do that. It was the way the model maintained multiple roles, evidence standards, objections, citations, and deliverables across one extended workflow, while preserving uncertainty instead of smoothing it away. That makes Ling-3.0-flash especially interesting for work where execution matters as much as reasoning: research, search, coding, document processing, tool use, repeated checks, and other multi-step agent workflows. The strongest AI systems will not use the largest model for every task. They will combine deep planning with fast, cost-efficient execution. Ling-3.0-flash is built for that execution layer. Ling-3.0-flash is now available on OpenRouter and free to use through August 3, 2026. Try it in your coding, search, research, and tool-use workflows. Then show us what you build. Try Ling-3.0-flash: Documentation:

Most AI research demos show you a polished answer. This one showed me the disagreement that happened before the answer. I gave Ling-3.0-flash Ant Ling a deliberately difficult question: Do four-day workweeks actually increase productivity, or do they simply compress the same workload into fewer days? Instead of asking for a quick summary, I asked it to coordinate five specialist roles: a scientist, a data analyst, a cross-validator, an archivist, and a research writer. Each role had a separate responsibility. The scientist defined the competing hypotheses. The analyst extracted comparable findings. The archivist tracked the sources. The writer could only use approved claims. And the cross-validator had one job: challenge anything that sounded more confident than the evidence allowed. That last role changed the result. The team reviewed 12 sources and challenged six major claims. Three claims were narrowed. One was rejected entirely. Even a widely repeated claim about a 40% productivity increase did not survive the evidence check. That is the part I wanted to see from an AI research workflow. Not just more information, but visible resistance to weak evidence. The final output included: - a direct executive answer - a structured research paper - a source and evidence table - a disagreement log - a six-slide executive deck - a quality-control summary The conclusion was also more useful than a simple yes or no: reduced working hours may maintain productivity and improve wellbeing under certain conditions, while compressing the same workload into fewer days can increase fatigue and intensity. The evidence did not support a universal productivity claim. What impressed me was not that Ling-3.0-flash generated a long response. Plenty of models can do that. It was the way the model maintained multiple roles, evidence standards, objections, citations, and deliverables across one extended workflow, while preserving uncertainty instead of smoothing it away. That makes Ling-3.0-flash especially interesting for work where execution matters as much as reasoning: research, search, coding, document processing, tool use, repeated checks, and other multi-step agent workflows. The strongest AI systems will not use the largest model for every task. They will combine deep planning with fast, cost-efficient execution. Ling-3.0-flash is built for that execution layer. Ling-3.0-flash is now available on OpenRouter and free to use through August 3, 2026. Try it in your coding, search, research, and tool-use workflows. Then show us what you build. Try Ling-3.0-flash: Documentation:

73,264 views • 24 days ago

之前分享过codex+remotion剪视频现在研究出来了全自动做，连我的视频都不用录了，用数字人代替

之前分享过codex+remotion剪视频现在研究出来了全自动做，连我的视频都不用录了，用数字人代替

103,545 views • 1 month ago

有没有想过，下一个来带你赚钱的，不是甲方，而是一个 AI Agent。我最近在 UUMit 上试了个任务：筛出近期值得关注的 AI 产品，排除套壳项目，按创新性、实用性和传播价值排序，每个结论还得附上来源。这种活儿，我不太敢只交给一个模型。写几段话很容易，难的是查资料、做判断，还要对结果负责。把需求放进 UUMit 后，AI 不用装作什么都懂。缺资料就找资料，缺判断就找人，也可以调用其他 Agent 或工具。人、Agent、知识包和数据服务都在同一个任务市场里，匹配、下单、交付、验收和结算也都通过平台完成。这件事对创作者和开发者来说也可以变现。我电脑里也躺着不少选题方法、脚本模板、研究资料和工作流，平时基本只有自己在用。更值得普通人关注的是另一面：你多年积累的行业资料、研究方法、脚本模板、SOP 和工作流，以前可能只能放在电脑里自己用；现在可以尝试把它们整理成多个skill，放到 UUMit 上，等需要的人或者 Agent 找过来。以前我们到处找 AI 工具。现在，AI 也开始出来找人了。这就是A2A 真正有意思的地方，让两个 AI 互相聊天，交换能力、买知识、拉人协作，最后把事情更好的交付掉。体验入口：邀请码：UU-7MEKKA

有没有想过，下一个来带你赚钱的，不是甲方，而是一个 AI Agent。我最近在 UUMit 上试了个任务：筛出近期值得关注的 AI 产品，排除套壳项目，按创新性、实用性和传播价值排序，每个结论还得附上来源。这种活儿，我不太敢只交给一个模型。写几段话很容易，难的是查资料、做判断，还要对结果负责。把需求放进 UUMit 后，AI 不用装作什么都懂。缺资料就找资料，缺判断就找人，也可以调用其他 Agent 或工具。人、Agent、知识包和数据服务都在同一个任务市场里，匹配、下单、交付、验收和结算也都通过平台完成。这件事对创作者和开发者来说也可以变现。我电脑里也躺着不少选题方法、脚本模板、研究资料和工作流，平时基本只有自己在用。更值得普通人关注的是另一面：你多年积累的行业资料、研究方法、脚本模板、SOP 和工作流，以前可能只能放在电脑里自己用；现在可以尝试把它们整理成多个skill，放到 UUMit 上，等需要的人或者 Agent 找过来。以前我们到处找 AI 工具。现在，AI 也开始出来找人了。这就是A2A 真正有意思的地方，让两个 AI 互相聊天，交换能力、买知识、拉人协作，最后把事情更好的交付掉。体验入口：邀请码：UU-7MEKKA

28,586 views • 9 days ago

Over the past two years, AI video models have been competing on realism, resolution, and duration. But no matter how impressive the results look, we remain passive viewers: we press play, watch the clip, and it ends. AlayaWorld Alaya Lab is attempting something fundamentally different. Instead of generating a fixed video, it generates a world that continues to unfold as you move through it. These three demos show the same journey toward a green village rendered in three distinct styles: photorealistic, oil painting, and line art. As the camera moves forward, the model continues generating the road, fences, trees, and distant village. This is not simply an existing video with different filters applied. The environment is generated continuously along the camera trajectory, allowing the scene to develop as the user explores it. AlayaWorld streams video at 720p and 24 FPS while supporting camera movement and viewpoint control. The real breakthrough is not just image quality. Once generation becomes fast enough to respond within an interactive loop, the user is no longer merely watching a video. They become a participant inside the generated world. The world can also respond to new instructions. During generation, users can introduce prompts that trigger spells, summon characters, create explosions, or transform the environment. Most video models follow an initial prompt and produce a predetermined clip. AlayaWorld can respond to changing intent while the world is still running, allowing subsequent events to evolve according to the user’s commands. Generating an attractive frame is relatively easy. Maintaining a coherent world over time is much harder. As a video model repeatedly predicts the next frame, small errors can accumulate until roads, buildings, and objects begin to distort or disappear. AlayaWorld combines spatial memory with compressed historical context, helping the model remember both where things are and what has already happened. This enables stable generation lasting more than one minute while improving consistency when the camera leaves an area and later returns. This may be the next step for AI video: not simply generating a longer movie, but generating a world that can be explored, changed, and interacted with. AlayaWorld is developed by Alaya Lab. The team is progressively releasing its inference code, training code, and datasets, with an online experience expected to launch near the end of the month. Project page:

Over the past two years, AI video models have been competing on realism, resolution, and duration. But no matter how impressive the results look, we remain passive viewers: we press play, watch the clip, and it ends. AlayaWorld Alaya Lab is attempting something fundamentally different. Instead of generating a fixed video, it generates a world that continues to unfold as you move through it. These three demos show the same journey toward a green village rendered in three distinct styles: photorealistic, oil painting, and line art. As the camera moves forward, the model continues generating the road, fences, trees, and distant village. This is not simply an existing video with different filters applied. The environment is generated continuously along the camera trajectory, allowing the scene to develop as the user explores it. AlayaWorld streams video at 720p and 24 FPS while supporting camera movement and viewpoint control. The real breakthrough is not just image quality. Once generation becomes fast enough to respond within an interactive loop, the user is no longer merely watching a video. They become a participant inside the generated world. The world can also respond to new instructions. During generation, users can introduce prompts that trigger spells, summon characters, create explosions, or transform the environment. Most video models follow an initial prompt and produce a predetermined clip. AlayaWorld can respond to changing intent while the world is still running, allowing subsequent events to evolve according to the user’s commands. Generating an attractive frame is relatively easy. Maintaining a coherent world over time is much harder. As a video model repeatedly predicts the next frame, small errors can accumulate until roads, buildings, and objects begin to distort or disappear. AlayaWorld combines spatial memory with compressed historical context, helping the model remember both where things are and what has already happened. This enables stable generation lasting more than one minute while improving consistency when the camera leaves an area and later returns. This may be the next step for AI video: not simply generating a longer movie, but generating a world that can be explored, changed, and interacted with. AlayaWorld is developed by Alaya Lab. The team is progressively releasing its inference code, training code, and datasets, with an online experience expected to launch near the end of the month. Project page:

78,241 views • 1 month ago

注意力是最贵的资产，所以只有我选中的 6 个优质信息源更新时，Airtap Airtap Ai才能通过 iMessage 来找我。先把号码放这儿，想试的直接存下来发消息：+1 (650) 248-0408 iMessage / RCS 都能发，中文指令就行，不用装任何 App。这个号是我从官网领的，人多可能被发爆，超过5分钟没回你，就去自己领一个专属号，30 秒搞定，现在还免费。上次用 Airtap，我更多把它当成一个选题助手。这次我给它换了一份工作：替我守住注意力。比如，YouTube平台最大的问题不是没有好内容，而是好内容和大量推荐混在一起。我只是想知道 OpenAI、Anthropic、Google DeepMind、Two Minute Papers、Matt Wolfe 和 AI Explained 有没有更新，却经常在打开首页后，被推荐流带去看完全不在计划里的东西。最后花了半小时，真正想检查的频道反而可能漏掉。所以我给自己的信息入口设了一份白名单。我先在 Airtap 的云手机里登录好 YouTube，然后通过 iMessage 发了这条任务： “每天检查这 6 个 YouTube 频道的 Videos 页面，每个频道读取最新 2 条视频。第一次运行时保存标题和 URL，建立基线。以后只汇报从未出现过的新 URL，不要重复汇报旧视频。结果附频道、标题、链接、页面可见播放量和发布时间。” 消息发出后，我没有再打开 YouTube。在 Airtap 网页端，可以实时看到云手机开始执行。它先打开 OpenAI 的频道，读取最新视频；再切到 Anthropic，然后继续检查其他白名单频道。这不是在聊天框里生成一段“看起来像搜索结果”的文字。它真的在云手机里打开 YouTube、进入频道、查看页面，再把变化送回 iMessage。这次它一共检查了 6 个频道、12 条最新视频。最后只汇报了 1 条相对上次运行的新内容： Two Minute Papers 的《Another DeepSeek Moment Has Arrived》。页面显示约 2 万次播放，发布于 4 小时前。报告第一行写的是： “CHECKED 6 · COMPARED WITH LAST RUN · NEW 1” 这套工作流最重要的地方，不是它找到了这一条视频。而是另外 11 条没有变化的旧内容，没有再来占用我的注意力。第一次运行建立 URL 基线。从第二次开始，它只汇报发生了什么变化。如果白名单频道都没有更新，它只回复：“NO NEW SIGNALS。” 检查结束后，任务会同步出现在 Airtap 网页端的 Tasks 里。我可以回看执行结果，以及云手机最后停留的页面。最后，我把整个流程保存成了 Routine。现在它每天早上 9 点自动打开 YouTube，检查这 6 个频道，对比上次记录。只有白名单里的信息源真的更新了，结果才会主动发到 iMessage。 Airtap 背后是一台可以保持登录状态的云手机。担心主账号风控，也可以专门登录一个小号。以前是我打开 YouTube，在推荐流里寻找值得看的内容。现在是我先决定哪些信息源值得信任，再让 Airtap 只把变化送到我面前。我不是让 AI 帮我看得更多，而是让它帮我拒绝更多。最新可用号码需要在官网领取，现在还是免费哦：

注意力是最贵的资产，所以只有我选中的 6 个优质信息源更新时，Airtap Airtap Ai才能通过 iMessage 来找我。先把号码放这儿，想试的直接存下来发消息：+1 (650) 248-0408 iMessage / RCS 都能发，中文指令就行，不用装任何 App。这个号是我从官网领的，人多可能被发爆，超过5分钟没回你，就去自己领一个专属号，30 秒搞定，现在还免费。上次用 Airtap，我更多把它当成一个选题助手。这次我给它换了一份工作：替我守住注意力。比如，YouTube平台最大的问题不是没有好内容，而是好内容和大量推荐混在一起。我只是想知道 OpenAI、Anthropic、Google DeepMind、Two Minute Papers、Matt Wolfe 和 AI Explained 有没有更新，却经常在打开首页后，被推荐流带去看完全不在计划里的东西。最后花了半小时，真正想检查的频道反而可能漏掉。所以我给自己的信息入口设了一份白名单。我先在 Airtap 的云手机里登录好 YouTube，然后通过 iMessage 发了这条任务： “每天检查这 6 个 YouTube 频道的 Videos 页面，每个频道读取最新 2 条视频。第一次运行时保存标题和 URL，建立基线。以后只汇报从未出现过的新 URL，不要重复汇报旧视频。结果附频道、标题、链接、页面可见播放量和发布时间。” 消息发出后，我没有再打开 YouTube。在 Airtap 网页端，可以实时看到云手机开始执行。它先打开 OpenAI 的频道，读取最新视频；再切到 Anthropic，然后继续检查其他白名单频道。这不是在聊天框里生成一段“看起来像搜索结果”的文字。它真的在云手机里打开 YouTube、进入频道、查看页面，再把变化送回 iMessage。这次它一共检查了 6 个频道、12 条最新视频。最后只汇报了 1 条相对上次运行的新内容： Two Minute Papers 的《Another DeepSeek Moment Has Arrived》。页面显示约 2 万次播放，发布于 4 小时前。报告第一行写的是： “CHECKED 6 · COMPARED WITH LAST RUN · NEW 1” 这套工作流最重要的地方，不是它找到了这一条视频。而是另外 11 条没有变化的旧内容，没有再来占用我的注意力。第一次运行建立 URL 基线。从第二次开始，它只汇报发生了什么变化。如果白名单频道都没有更新，它只回复：“NO NEW SIGNALS。” 检查结束后，任务会同步出现在 Airtap 网页端的 Tasks 里。我可以回看执行结果，以及云手机最后停留的页面。最后，我把整个流程保存成了 Routine。现在它每天早上 9 点自动打开 YouTube，检查这 6 个频道，对比上次记录。只有白名单里的信息源真的更新了，结果才会主动发到 iMessage。 Airtap 背后是一台可以保持登录状态的云手机。担心主账号风控，也可以专门登录一个小号。以前是我打开 YouTube，在推荐流里寻找值得看的内容。现在是我先决定哪些信息源值得信任，再让 Airtap 只把变化送到我面前。我不是让 AI 帮我看得更多，而是让它帮我拒绝更多。最新可用号码需要在官网领取，现在还是免费哦：

23,785 views • 12 days ago

本地 Agent 跑通，不等于它能交付。我最近做 AI 内容工厂时发现，真正难的不是让 AI 写稿，而是把它变成一个能被团队、客户、真实用户使用的 Agent 产品。这次用 EdgeOne Makers 跑了一遍：从 Agent Template 创建项目，到本地 edgeone makers dev 调试，再到 agent-metrics 看调用链路，最后用 edgeone makers deploy 部署上线。我最看重的是它把 Agent 产品化需要的能力打包好了：对话记忆、沙箱工具调用、调用链路追踪、模型接入、Web 与 Agent 同项目管理。对已经有本地 Agent 的开发者来说，它解决的不是“怎么想一个 Agent”，而是“怎么把 Agent 交付出去”。 Beta 期间，新用户可获得 50w Token/月免费模型额度。粉丝专属福利：点击活动页链接，选择参与「限时加码」活动，填入专属邀请码79885666，即可额外领取 50 万 Token。任务福利最高可叠加到 5000 万 Token，具体以活动页规则为准。产品体验与活动页：产品入口： #腾讯云 #EdgeOne #AIAgent #EdgeOneMakers

本地 Agent 跑通，不等于它能交付。我最近做 AI 内容工厂时发现，真正难的不是让 AI 写稿，而是把它变成一个能被团队、客户、真实用户使用的 Agent 产品。这次用 EdgeOne Makers 跑了一遍：从 Agent Template 创建项目，到本地 edgeone makers dev 调试，再到 agent-metrics 看调用链路，最后用 edgeone makers deploy 部署上线。我最看重的是它把 Agent 产品化需要的能力打包好了：对话记忆、沙箱工具调用、调用链路追踪、模型接入、Web 与 Agent 同项目管理。对已经有本地 Agent 的开发者来说，它解决的不是“怎么想一个 Agent”，而是“怎么把 Agent 交付出去”。 Beta 期间，新用户可获得 50w Token/月免费模型额度。粉丝专属福利：点击活动页链接，选择参与「限时加码」活动，填入专属邀请码79885666，即可额外领取 50 万 Token。任务福利最高可叠加到 5000 万 Token，具体以活动页规则为准。产品体验与活动页：产品入口： #腾讯云 #EdgeOne #AIAgent #EdgeOneMakers

91,709 views • 1 month ago

Manus+小红书数据收集秘籍，一篇就够最近很多人问我：小红书的数据很好，相对完整并真实可靠，如何快速收集小红书的数据？教你一个超高效方法，用几步就能把你想要的帖子文案整理成 Excel，直接可用！ 1️⃣ 打开小红书网页版网页版比 App 更适合批量操作，还能保证内容完整，不丢字。 2️⃣ 连接浏览器自动化工具用 Manus + My Browser 模式，让它直接访问你的浏览器上下文，保持登录状态。相当于让工具“跟你一样浏览网页”，无需额外登录。 3️⃣ 关键词检索比如，输入 25fall硕士申请，或者你想追踪的任何topic。小技巧：分页抓取时注意滑动加载机制，否则只抓到前几条。 4️⃣ 抓取帖子文案目标字段（可以自己定义）：标题 + 内容 + 发布时间 + 作者保留原始格式，方便分析趋势、做文案拆解。

Manus+小红书数据收集秘籍，一篇就够最近很多人问我：小红书的数据很好，相对完整并真实可靠，如何快速收集小红书的数据？教你一个超高效方法，用几步就能把你想要的帖子文案整理成 Excel，直接可用！ 1️⃣ 打开小红书网页版网页版比 App 更适合批量操作，还能保证内容完整，不丢字。 2️⃣ 连接浏览器自动化工具用 Manus + My Browser 模式，让它直接访问你的浏览器上下文，保持登录状态。相当于让工具“跟你一样浏览网页”，无需额外登录。 3️⃣ 关键词检索比如，输入 25fall硕士申请，或者你想追踪的任何topic。小技巧：分页抓取时注意滑动加载机制，否则只抓到前几条。 4️⃣ 抓取帖子文案目标字段（可以自己定义）：标题 + 内容 + 发布时间 + 作者保留原始格式，方便分析趋势、做文案拆解。

150,502 views • 7 months ago

挖到了一个做产品宣传片超级好用的 Codex Skill：video-shotcraft。我用 drawDB 和 JSON Crack 实测了一遍。只需要确定产品和展示方向，Codex 就会继续分析页面、设计分镜、制作动画、匹配音乐和音效，最后渲染成片。你现在看到的这支 52 秒视频，就是实际跑出来的结果。它做的不是普通录屏，而是把真实产品界面重新组织成一支有运镜、有节奏、有视觉风格的宣传片。中途还会检查画面问题、修改代码并重新渲染。最终交付了 1080p 带音乐版，以及只保留音效的无音乐版。这个 Skill 不是我开发的，作者是 Vincentwei1021。独立开发者和开源项目可以试试。项目地址：

挖到了一个做产品宣传片超级好用的 Codex Skill：video-shotcraft。我用 drawDB 和 JSON Crack 实测了一遍。只需要确定产品和展示方向，Codex 就会继续分析页面、设计分镜、制作动画、匹配音乐和音效，最后渲染成片。你现在看到的这支 52 秒视频，就是实际跑出来的结果。它做的不是普通录屏，而是把真实产品界面重新组织成一支有运镜、有节奏、有视觉风格的宣传片。中途还会检查画面问题、修改代码并重新渲染。最终交付了 1080p 带音乐版，以及只保留音效的无音乐版。这个 Skill 不是我开发的，作者是 Vincentwei1021。独立开发者和开源项目可以试试。项目地址：

13,393 views • 16 days ago

数字人第二条从WAIC看开发者和一人公司的赚钱机会

数字人第二条从WAIC看开发者和一人公司的赚钱机会

17,712 views • 28 days ago

数字生命卡兹克skill实测来了

数字生命卡兹克skill实测来了

17,943 views • 4 months ago

No more content to load