正在加载视频...

视频加载失败

i didn't use a single environmental reference for the video input ran leafs pictures through claude for my prompt template, and it named almost all of the IRL geographic locations with a physical description of each 😶

15,916 次观看 • 25 天前 •via X (Twitter)

27 条评论

Leaflit 🍃 Angel's Sword 的头像
Leaflit 🍃 Angel's Sword25 天前

OMG

Kyoryu Diabolos 的头像
Kyoryu Diabolos25 天前

@Leaflit Hafuma! You son of a bitch. I knew someone was bound to do this. Great job!

Mark Dress 的头像
Mark Dress25 天前

@Leaflit Wait so what kind of AI did you use the create this specifically?

🤍Hafuma🩵 的头像
🤍Hafuma🩵25 天前

@Leaflit Seedance 2.5 and opus 5.5 /w my custom seedance skill

Mark Dress 的头像
Mark Dress25 天前

@Leaflit Sorry, I haven't looked into video generation AI for a while but is Seedance 2.5 running locally?

🤍Hafuma🩵 的头像
🤍Hafuma🩵25 天前

@Leaflit Nope its a chinese 200+ billion param model and its owned by the tiktok people so its closed source

Matthew Ball MD ✡️ 的头像
Matthew Ball MD ✡️25 天前

@Leaflit Damn If I was Leaflit - I'd hug you

トラッカーちゃん 的头像
トラッカーちゃん24 天前

@Leaflit Holy crap what. That's friggen incredible.

Itazura Chan 的头像
Itazura Chan25 天前

@Leaflit 😭 Its a true AI gemmie!

Aiden Guo 的头像
Aiden Guo24 天前

@Leaflit damn she went to space too🫣

MidnightInu (Crusade arc: inevitable) 的头像
MidnightInu (Crusade arc: inevitable)24 天前

@Leaflit Once again ai proves the worst it has been is the worst it will ever be The transitions like it’s warping through her adventure is insane

Cybernaut 的头像
Cybernaut25 天前

@Leaflit Wow. Well done Hafuma.

RochefortTen 的头像
RochefortTen25 天前

@Leaflit The animation and transitions in this one are both really smooth. Love it.

WhiteCoffee 的头像
WhiteCoffee25 天前

@Leaflit This is so crazy.

Ðetective Ŵagmi 🔎 的头像
Ðetective Ŵagmi 🔎24 天前

@Leaflit Woooow! Sooo good! I love it! Love to see more ☺️

RoachKnight 的头像
RoachKnight25 天前

@Leaflit Claud is nuts. i just got it the other day

No one special 的头像
No one special24 天前

@Leaflit Leaflit in... SPACE!

Axel Wilbert 的头像
Axel Wilbert25 天前

@Leaflit Was this made With A.I.?

PersonalPurchase 的头像
PersonalPurchase24 天前

@Leaflit I for one would love an anime based of Leaf's traveling adventures

Shawn Wolfe 的头像
Shawn Wolfe24 天前

@Leaflit This is spectacular, it's soooo well done!!! Bravo, and kudos!!!

Sakura Circuit 的头像
Sakura Circuit23 天前

@Leaflit Incredible 🥳

Das Tree 的头像
Das Tree24 天前

@Leaflit Looks really good.

Megacreonte 的头像
Megacreonte25 天前

@Leaflit Looks like a montage from the ending of the last episode of this season

Maineiac 🤪 的头像
Maineiac 🤪25 天前

@Leaflit Damn bud, this is really good. You may need to change that name in your bio

SQA 的头像
SQA25 天前

@Leaflit Opus to Seedance via Higgsfield? Full pipeline or interactions at points?

YohiraKun 的头像
YohiraKun25 天前

@Leaflit Looks cool, but most of us power users know, if you use just text only, it will generate amazing real anime look, with boiling line, but you need consistency, you need characters, environments, and once you introduce that it creates that AI look

salad_ninja 的头像
salad_ninja24 天前

@Leaflit so....12 episodes? 🤣

相关视频

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 次观看 • 8 个月前