←
BubbleBrain6,156 posts
BubbleBrain avatar

BubbleBrain

@BubbleBrain

AI Enthusiasts | Non-Professional Prompt Engineer|AI Art |Sharing AI news, tools & insights

◷ Joined April 2024▧ 1,465 Photos and videos
BubbleBrain avatar
BubbleBrain@BubbleBrain·Aug 1

Seedance 2.5 vlog case. This is so real. ---prompt--- A realistic handheld travel vlog filmed by a friend following the main character throughout the day. Use the woman from the reference image as the main subject. Maintain her exact facial identity, hairstyle, facial features, and body proportions throughout the entire video. The camera feels like a real personal vlog camera, not a commercial production. Natural handheld movement, casual framing, imperfect human camera motion, authentic everyday atmosphere. No scripted acting. The woman behaves naturally, interacting with the environment like a real travel vlog. 0-5s: Morning departure. The woman leaves a cozy apartment with a small backpack. She checks her phone, smiles at the camera, adjusts her hair, and starts walking outside. The camera follows her from behind, slightly shaky like a friend filming. Morning sunlight, quiet neighborhood streets, people starting their day. 5-12s: Exploring the city. The camera follows her walking through local streets. She visits a small cafe, buys a drink, briefly talks to the camera, laughs naturally. She walks through a street market, looks at small shops, takes casual photos. The camera stays close, capturing spontaneous moments. 12-20s: Arriving at the beach. She takes public transportation or walks toward the coast. The environment gradually changes from city streets to a seaside town. Ocean breeze moves her hair. She looks excited when she sees the ocean. The camera follows her walking along the beach. She picks up a seashell, watches waves, and interacts naturally with people nearby. 20-27s: Summer beach afternoon. She meets friends at the beach. Everyone chats, laughs, plays near the water. The camera moves naturally between people, capturing real candid moments. She looks back at the camera and smiles. 27-30s: Ending moment. Golden hour sunset. She sits near the ocean, holding a drink, watching the sunset. The camera slowly moves backward, revealing the beach, waves, and the peaceful evening. A feeling of a real personal travel memory. Visual style: Authentic travel vlog footage. Realistic smartphone or mirrorless camera look. Natural daylight. Casual handheld movement. Slight camera shake. Real human reactions. Documentary realism. No cinematic commercial look. No dramatic posing. No artificial transitions. No text overlays. No logos. No face changes. No identity changes.

0:30
BubbleBrain avatar
BubbleBrain@BubbleBrain·18h

🚨Another mind blowing creation from Fable 5.2. I asked it to make a macro wildlife documentary of a bee collecting nectar from flowers. About six hours later, it handed me this video. The realism is absolutely insane. and one more thing: it even used Edge TTS to generate the voiceover and narrate the whole thing. So please sound on.

1:15
BubbleBrain avatar
BubbleBrain@BubbleBrain·Nov 17

When I asked Fable 5.2 to capture a macro shot of a bee collecting nectar, this is what it handed me. And once again, everything you see was created entirely with code.

Post attachment
BubbleBrain avatar
BubbleBrain@BubbleBrain·Nov 16

🚨 When Fable 5.2 give this video to me, I was genuinely blown away. Everything you see, and even everything you hear, was created entirely with code. Now, let Fable 5.2 take you on a journey through the world as seen through the eyes of a little cat.

1:50
BubbleBrain avatar
BubbleBrain@BubbleBrain·Nov 16

🚨Explore the wilderness in first person with Fable 5.2. Still built entirely with code. Sound on, there's even narration!

1:35
BubbleBrain avatar
BubbleBrain@BubbleBrain·Nov 15

🚨 Welcome to Fable 5.2's underwater world. It's so real!

1:18
BubbleBrain avatar
BubbleBrain@BubbleBrain·Nov 14

it's been over half a year and not one American video generation model has really impressed anyone. Looks like they are giving up on video generation, which is ironic considering they own YouTube, the largest video platform in the world.

It's been months and not one Chinese model has really impressed anyone. Looks like losing access to distill from Anthropic hurt them way more than they'd admit.

BubbleBrain avatar
BubbleBrain@BubbleBrain·Nov 12

Fable 5.2 made this and even explained that it's a phenomenon called Snell's window.

Post attachment
BubbleBrain avatar
BubbleBrain@BubbleBrain·Nov 12

The last Moonshot drama at least came with screenshots and chat records. Now apparently you can just pull an entire story out of thin air, back it up with absolutely nothing, and call it news. And we're talking about regulating AI? Maybe we should start with this shit.

BubbleBrain avatar
BubbleBrain@BubbleBrain·Nov 12

Welcome to an era where people can make baseless claims without any accountability.

I didn't plan to say more about this. But my posts on this got more than 2000 replies and hundreds of DMs, and I can't answer each one. So I'll answer everything once here and then I'm closing this topic for good. Please don't raise it with me after today. Thank you to everyone who thanked me, appreciated the honesty, or disagreed with respect. That's how the AI space should be. Some replies got personal and some were racist. I'm letting that go. I'm writing this out of respect for the many Chinese friends who follow me here. If anything I wrote read as disrespect toward Chinese people or the researchers in these labs, that was never what I meant. I didn't mean to hurt anyone. Now the clarifications. This wasn't about Fable 5.2. It was about an older release. The most common question: how could you face legal trouble if you never signed an agreement? Here's how it works. Labs in this space usually reach out through an intermediary. Someone contacts you, says they represent a lab and proposes a collaboration. That's normal and real work gets done that way. But it means I have nothing official from the lab itself. If I named anyone, they could deny any connection to the intermediary and I'd be the one exposed. So I haven't named the lab and I won't. I'd ask people to stop pushing me to. I also never said a lab emailed me from an official address asking for help with distillation. It came through an intermediary, like most of these conversations do. Why me? I do deep technical comparisons here on the strengths and weaknesses of each model. They wanted me to analyze their model and help in different ways. When distillation came up I said no. Some people mixed up distillation and training. Distillation is training a model on another model's outputs. What I offered in a separate conversation was different: clean data, books with no copyright, and help evaluating the model in areas like design and language. They weren't interested. If you only know me from these posts, I've worked in this field for a long time and I have something to offer. All I ask is that you respond to the arguments. I spoke for the sake of transparency, and because I want to see Chinese labs lead with original work. In my opinion the recent slowdown is tied to distillation getting cut off. That's my opinion and you're free to disagree. We all want strong open models we can rely on. I started here five months ago and nearly everything I've posted is support for open models. Sharing something I saw myself doesn't make me against them. I treat everyone the same way. I talk about OpenAI and Anthropic, whose products I use, with the good and the bad together. On views: I make content, of course I want views. But praising everyone is the easier way to get them and keep everyone happy. I know this upset some of you, maybe because you love these labs or feel you belong with them. I understand and I respect that. What I shared is my own experience and my own opinion. I'm not presenting it as proof against anyone. Take it, look into it yourself and form your own view. That's everything I can say. I'm closing this here. Thank you.

BubbleBrain avatar
BubbleBrain@BubbleBrain·Nov 11

we call this 吹尼玛呢 in Chinese.

A big Chinese lab reached out to me asking for help distilling Fable into their model. I said no. I told them to use the millions of books that have no copyright instead. Offered to help pick them and to help train the model a different way. They only wanted distillation, which tells you a lot about the mindset there. I've worked deep in this field and distillation is real. I wasn't convinced at one point. What I saw changed my mind completely. I'm the biggest supporter of open source. I'm for releasing weights and for the freedom to research and build, because humanity only grows when knowledge gets shared. But let's be logical. Nobody will convince me that labs shipping a model every month or less, each one a big leap, now can't ship a better one after three months. Kimi K3.1 Pro isn't a big leap over Kimi K3 and it's been about 100 days. DeepSeek still can't put out a respectable Pro model. Zai used to release their strongest model in under two months. It's been three with nothing. All I hear about Qwen 4 Max is that it's a letdown. Kimi K3.1 Pro and DeepSeek Flash both show traces of Astra distillation. The leak showed Moonshot used it, and so did DeepSeek. If this isn't the effect of Anthropic blocking distillation then what is it? Chinese labs need to get serious about using the talented researchers they have and give their models an identity. Right now their models at their best are a cheaper alternative. I want them out of that box. I want to see what makes them different. Anthropic has crossed lines too, no argument there. They destroyed millions of books, human knowledge that was in people's hands, and kept it for themselves. I'll never forgive them for that. But Chinese labs rely on distillation more than they rely on better data. I didn't work with them. Transparency and honesty matter to me, like you've known since I started here.