持续折腾中，用 AI 解决实际问题，管用的、翻车的都记下来。不教课，只分享我正在学的东西 Homepage： https://xitter.cf/t.co/LBxofFBqqE
Joined April 2020
- Tweets1.4K
- Following172
- Followers143
- Likes910
Pinned Tweet
用 ComfyUI 一步一步捏出的角色，迭代了 20 多个版本，生图还是喜欢固定角色，不太喜欢随机生成，所以隆重介绍一下我的新角色，Nova
借用鱼哥@MrGafish 的礼服闪亮登场
🤖 Made with AI
GPT Image 生成极具未来感的高级定制礼服
Prompt:
生成一件极具未来感的高级定制礼服，采用独立悬浮式三维服装产品展示。
服装结构： 礼服完全独立存在，不穿在任何人体上。领口、袖口及裙身内部均为空心结构，依靠服装自身的立体剪裁和内部支撑保持自然廓形。不得出现人体填充物或人体形状。
设计风格： 每次随机设计独特的未来主义高级定制礼服，随机搭配鲜艳高级配色、金属缎面、透明薄纱、立体欧根纱、水晶、珍珠、宝石刺绣、不对称肩部、雕塑感胸衣、立体花朵、层叠裙摆及华丽披肩。
构图： 单件礼服正面完整展示，从领口到裙摆全部入镜，不裁切。服装独立悬浮于明亮简洁的高级摄影棚，画面中没有其他物体。
画质： 顶级奢侈品牌高级定制广告风格，超写实3D产品渲染，精细面料纹理，电影级柔和布光，鲜艳饱满的色彩，华丽、梦幻、优雅、前卫。
以前我一直以为，保持人物脸部一致很简单，给 GPT 一张参考图，就能一直生成同一张脸
直到我用 ComfyUI 重新一点点迭代面部细节，才发现不管是本地模型还是云端模型，都没法 100% 复刻出我设计的那张脸
回头想，以前觉得简单，是因为生成的都是 AI 随机出的脸，没加进我自己的细节。好看是好看，但长得都差不多，所以才觉得一致很容易
真有了自己设计的脸，才知道一致性有多难
Update: My Grok Bot usage is finally back to normal!
I tried a few tasks after it was restored, and the usage isn't shooting up like crazy anymore, at least not like it was yesterday. I'm really happy to see that.
I just hope things can stay this way.
If prices need to go up someday, or usage limits need to be reduced, that's fine. Just give us a heads-up so we can decide what works for us.
I've said this before, and I still mean it: I really love Grok Bot. I've been gradually moving more and more of my work and daily life over to it, and I genuinely want to keep using it for a long time.
That's why I was so upset in the first place.
Anyway, I'm glad things are back to normal, and I hope they stay that way.
This isn’t about us not having enough usage or picking the wrong plan.
I’ve been buying the 12-inch pizza from your place forever, and you guys have always given me a normal 12-inch. Then one day I open the box and it’s a 6-inch. You tell me costs got too high, so from now on the “12-inch” is actually 6 inches, and if I’m still hungry it’s my fault for not choosing the right size.
That’s insane.
If you needed to cut costs, just tell us ahead of time. If your pizza is good and I still want it, I can just order two or three of these fake 12-inch ones. Or if I’m not full, I can go somewhere else. Either way that’s my call, not yours.
But you don’t get to keep selling me a normal 12-inch and then suddenly shrink it to 6 inches with zero notice, not even a heads-up so I can adjust. Don’t turn around and say I picked the wrong subscription. The problem is you unilaterally changed what you were delivering without telling anyone.
@elonmusk @mark_k @BenjaminDEKR @CWLemoine
This isn’t about us not having enough usage or picking the wrong plan.
I’ve been buying the 12-inch pizza from your place forever, and you guys have always given me a normal 12-inch. Then one day I open the box and it’s a 6-inch. You tell me costs got too high, so from now on the “12-inch” is actually 6 inches, and if I’m still hungry it’s my fault for not choosing the right size.
That’s insane.
If you needed to cut costs, just tell us ahead of time. If your pizza is good and I still want it, I can just order two or three of these fake 12-inch ones. Or if I’m not full, I can go somewhere else. Either way that’s my call, not yours.
But you don’t get to keep selling me a normal 12-inch and then suddenly shrink it to 6 inches with zero notice, not even a heads-up so I can adjust. Don’t turn around and say I picked the wrong subscription. The problem is you unilaterally changed what you were delivering without telling anyone.
@elonmusk @mark_k @BenjaminDEKR @CWLemoine
虽然非常讨厌爆论这个词，但不得不说，我也有了自己的猜测
现在还在强调怎么省 Grok Bot token 的人，或者如何获得便宜订阅的人，大概率自己都没在用。
昨天到今天大面积用户额度被莫名吃掉的问题还在持续扩散中
结论先行：bot 点瑞幸可用，但得是固定场景、流程固定才方便，要是还得自己选单就不太方便了
今天照着原作者 @0xmomonifty 的思路试了一下。我给 bot 接了高德地图的 API，它能根据我所在的位置找到离我最近的店，下单是成功的
先按他说的用 bot 发过来的二维码付，真的不方便，聊天里微信没法直接识别，得先存成照片再去微信扫。后来我想，bot 下单成功后本来就会生成二维码，那是不是不用把它复制过来，直接去小程序自己的订单里付就行。为了验证，又给媳妇点了一杯，第二杯就是这么付的，没问题
真正方便的还是你有固定的消费习惯，常喝某一种，直接告诉 bot 去点就行。要是还得挑，饮品店的名字看着有关键词，和想象的完全不一样，还是得回小程序或 app 里选。这和昨天跟原作者聊打滴滴差不多，他写脚本盯订单我觉得挺麻烦，但他提了一个场景，固定的起点终点，一句话就行。
所以用 bot 来点单、订服务，还是得有一个固定可用的场景
从这条帖子学到的第一个是 Dr Eggbot，它的功能是创建 bot。它和主 bot 的区别是，主 bot 是干活的，Eggbot 能更好地界定和设置更符合个人需求的 bot。就像一个公司里，CEO 知道他需要什么样的人，但只有 HR 能找到合适的人，可以这么理解。
第二个是让干活的 bot 自己去总结、创建 skill。我之前每次要省 token 或者建 skill，都是去问主 bot，这次我直接问了子 bot，它给了我差不多它现在做的所有事情的列表，很多都能做成 skill 来省 token，确实比主 bot 细致。
自动化和语音输入这两个功能对我作用不大。自动化我没有使用场景，或者说我所有的使用场景都已经自动化了。
以上就是我结合 Grok 的讲解和在 bot 上的实践，从这条帖子里学到的东西
here’s a short grok bot guide on how i create high quality bots and manage my team. ask @bot to read this post and help you improve your team!
• add dr eggbot to your team! he’s my bot designer that i use to create bots
• you don’t need a lot of bots. a few good bots can be more useful and easier to manage than a large team
• tell your bots to create skills for itself as you give it instructions on how to do tasks. this lets them do them more consistently even over long conversations. you can even ask it to create a private github repo for you to store all your skills if you want them preserved independently
• add connectors, use the vault, and give access to all the tools you use to do your work. you can also ask your bot to setup its own email and it can sign up for its own accounts for better separation
• thinking about all the work you do by hand, or steps in your workflows where you have to copy and paste information back to your bot. ask your bot how it can do that for you instead!
• imagine you hired an intern, how would you onboard them and help them do the work correctly and efficiently? introduce yourself to your bot and describe the work you do, then ask it how it can help you automate it
and my favorite tip: use voice mode or the transcription option! it’s a good way to just brain dump a lot of information. then, at the end, tell your bot to “restate this in your own words” so you can confirm it understood you
x.ai/bot/_jOdbfkB16zxu7MRcmR…
