正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Opus 5.5 is so good at making hand-drawn whiteboard animations This one shot video explaining Leidenfrost effect perfectly. Voice over and music added all in one pass. Maybe we can revolutionize education. Great work by Anthropic

Yunfan Ye

1,489 subscribers

73,220 次观看 • 4 天前 •via X (Twitter)

艺术教育科学技术

Anya Rossi• Live Now

Private livecam show

23 条评论

Yunfan Ye 的头像

Yunfan Ye4 天前

How it was created: If you'd like to try it out, you can set up the open source project and then use Physics Whiteboard app. Rome turned the creation process into a repeatable workflow app. Or, reply your idea to this thread, I will have my agent monitor the thread and create the popular ones

Neeraj Kapoor 的头像

Neeraj Kapoor4 天前

@AnthropicAI this is incredible. Elevenlabs for audio?

Yunfan Ye 的头像

Yunfan Ye4 天前

@AnthropicAI I simply asked for voice over and didn't care about provider :)

Ed IO 的头像

Ed IO4 天前

@AnthropicAI Did you use only a promot or a skill too?

Yunfan Ye 的头像

Yunfan Ye4 天前

@AnthropicAI A prompt. An repeatable workflow app made with

Yamei Chen 的头像

Yamei Chen4 天前

@AnthropicAI Cute style of this video

Ray Zhang 的头像

Ray Zhang2 天前

@AnthropicAI

joker.icp 的头像

joker.icp4 天前

@AnthropicAI incredible!

Jason Ark 的头像

Jason Ark3 天前

@AnthropicAI This will be game changing

Tech Impact 的头像

Tech Impact3 天前

@AnthropicAI These one-shot whiteboard animations will be huge for architecture, construction & product design—clear client explainers, assembly steps, thermal details in minutes. Pros who adapt stay relevant; those who don’t get left behind.

Mr. Roth 的头像

Mr. Roth3 天前

@AnthropicAI yes

Puneet 的头像

Puneet3 天前

@AnthropicAI You don't need school teacher now

Amal Dorai 的头像

Amal Dorai4 天前

@AnthropicAI What tools does it use to build the graphics? And why does the text keep jiggling? For visual pizzazz?

MattStopa 的头像

MattStopa2 天前

@AnthropicAI Incredible

Nikhil Ranka 的头像

Nikhil Ranka3 天前

@AnthropicAI Thanks for sharing this 🙏🏼. Well explained. I still wouldn't have wanted to learn about the Lidenfrost effect. This is highly useful when one wants to learn someting related, but that something is too dry to navigate.

Suryansh Chourasia 的头像

Suryansh Chourasia3 天前

@AnthropicAI Can I make tech related videos using this?

BowTiedTechGuy 的头像

BowTiedTechGuy4 天前

@AnthropicAI What was the effort level you used?

♱ EZROX VOX ♱ 的头像

♱ EZROX VOX ♱3 天前

@AnthropicAI That's the first one I've seen in slow (not that frenetic crap) made by Opus. It also looks like it has a consistency (continuity). I really like that.

Bla Blu 的头像

Bla Blu4 天前

@AnthropicAI Who’s we?

Cupsey 的头像

Cupsey4 天前

@AnthropicAI the one-pass voice + music is the bit that feels unfair lol

CWatt250 的头像

CWatt2504 天前

@AnthropicAI But what makes eggs not stick to the pan?!?! 🍳

Yunfan Ye 的头像

Yunfan Ye4 天前

@AnthropicAI Great question! I am curious too. Here you go. Let me know if you have more ideas

Crio Songo 的头像

Crio Songo4 天前

@AnthropicAI This capability is really impressive. It's super promising to bring such efficiency to educational content production.

相关视频

pushing the limits of opus 5.5 been working on this video this weekend, this is not a one-shot and took 5+ takes on every frame because i wanted each one to feel like a painting this mimics cel animation with every stroke drawn by opus like a real artist would

pushing the limits of opus 5.5 been working on this video this weekend, this is not a one-shot and took 5+ takes on every frame because i wanted each one to feel like a painting this mimics cel animation with every stroke drawn by opus like a real artist would

Indra

23,872 次观看 • 2 天前

i'm abhay, and this video is my one shot at making it to san francisco to work with Farza 🇵🇰🇺🇸 — so we can make videos that take over the world. help me get to sf.

i'm abhay, and this video is my one shot at making it to san francisco to work with Farza 🇵🇰🇺🇸 — so we can make videos that take over the world. help me get to sf.

abhay shenoy

61,775 次观看 • 1 年前

Opus 5.5 made this aesthetic snake game in one shot. The quality is incredible. Probably the best model at 3D and design so far. I cannot wait to see how people use it in game dev.

Opus 5.5 made this aesthetic snake game in one shot. The quality is incredible. Probably the best model at 3D and design so far. I cannot wait to see how people use it in game dev.

Shikhar

12,519 次观看 • 7 天前

All we can say is THANK YOU! Thank you for visiting, making memories, and sharing them with us. We couldn’t do any of this without each any every one of y’all! 💕 This #PictureoftheDay, sponsored by at Lucchese couldn’t be summed up in one photo, so enjoy this video!

All we can say is THANK YOU! Thank you for visiting, making memories, and sharing them with us. We couldn’t do any of this without each any every one of y’all! 💕 This #PictureoftheDay, sponsored by at Lucchese couldn’t be summed up in one photo, so enjoy this video!

State Fair of Texas

16,233 次观看 • 2 年前

A developer gave Opus 5.5 a $20 budget to autonomously create a 60-second explainer video. Then forgot to provide the API key. Instead of stopping, Opus built a local production studio: • Kokoro-82M for voice • JavaScript + FluidR3 for music • Code-generated and CC0 sound effects • Whisper for audio QA • Hand-drawn Canvas animations 55 minutes later, it shipped a finished 51-second video. Additional cost: $0. The best agent isn’t the one that never hits a failure. It’s the one that finds another path and keeps shipping.

A developer gave Opus 5.5 a $20 budget to autonomously create a 60-second explainer video. Then forgot to provide the API key. Instead of stopping, Opus built a local production studio: • Kokoro-82M for voice • JavaScript + FluidR3 for music • Code-generated and CC0 sound effects • Whisper for audio QA • Hand-drawn Canvas animations 55 minutes later, it shipped a finished 51-second video. Additional cost: $0. The best agent isn’t the one that never hits a failure. It’s the one that finds another path and keeps shipping.

Jurly

16,549 次观看 • 4 天前

Created this video in just 20 minutes. One thing I've noticed with HyperFrame + Claude is that if you understand the technical aspects of video creation, it's much easier to generate the results you want. For this video, I simply asked it to create a storyboard-style whiteboard animation with a handwritten effect and a hand appearing as it writes, while explaining the concept I wanted to cover. If I don't explicitly mention the storyboard/whiteboard style, I'll end up prompting over and over again and still won't get the video I'm looking for.

Created this video in just 20 minutes. One thing I've noticed with HyperFrame + Claude is that if you understand the technical aspects of video creation, it's much easier to generate the results you want. For this video, I simply asked it to create a storyboard-style whiteboard animation with a handwritten effect and a hand appearing as it writes, while explaining the concept I wanted to cover. If I don't explicitly mention the storyboard/whiteboard style, I'll end up prompting over and over again and still won't get the video I'm looking for.

Ankur | NoCode Talks

31,772 次观看 • 2 个月前

anthropic cooked hard with opus 5.2 after testing it for a whole day, i can say this model is so good > huge step up from opus 5 > on par with astra > faster than opus 5 > way better at frontend and 3d here’s one frontend test i ran and it’s the best output any model has given me even better than astra you can check fable 5.1 output with same prompt in QT and tbh opus 5.2 just mogs everyone here really hoping that anthropic will release this model officially this week

anthropic cooked hard with opus 5.2 after testing it for a whole day, i can say this model is so good > huge step up from opus 5 > on par with astra > faster than opus 5 > way better at frontend and 3d here’s one frontend test i ran and it’s the best output any model has given me even better than astra you can check fable 5.1 output with same prompt in QT and tbh opus 5.2 just mogs everyone here really hoping that anthropic will release this model officially this week

J A Z I I

40,582 次观看 • 14 天前

I asked Opus 5.5, GPT-6 Astra, GPT-6 Sol, Kimi K3 to build the Eiffel Tower in Three.js. Opus 5.5: $8.95 | 10 mins GPT-6 Astra: $7.45 | 8 mins GPT-6 Sol: $3.90 | 5 mins Kimi K3: $4.04 | 6 mins Opus 5.5 really impressed me. The frontend and 3D detailing are seriously good, and I preferred it over Astra for this task. GPT-6 Sol was a bit disappointing, while Kimi K3 looks really good for the price. It delivered a strong result at almost half the cost. Kimi K3.1 is going to be a monster for sure. Overall, Anthropic made a great comeback with Opus 5.5.

I asked Opus 5.5, GPT-6 Astra, GPT-6 Sol, Kimi K3 to build the Eiffel Tower in Three.js. Opus 5.5: $8.95 | 10 mins GPT-6 Astra: $7.45 | 8 mins GPT-6 Sol: $3.90 | 5 mins Kimi K3: $4.04 | 6 mins Opus 5.5 really impressed me. The frontend and 3D detailing are seriously good, and I preferred it over Astra for this task. GPT-6 Sol was a bit disappointing, while Kimi K3 looks really good for the price. It delivered a strong result at almost half the cost. Kimi K3.1 is going to be a monster for sure. Overall, Anthropic made a great comeback with Opus 5.5.

Bhavy☄️

165,918 次观看 • 6 天前

Today we're announcing not one, but two, updates on iOS that have been requested a lot by our users. - liquid glass animations in Proton Pass, and - we've added a username generator You can see both of them in action in this video.

Today we're announcing not one, but two, updates on iOS that have been requested a lot by our users. - liquid glass animations in Proton Pass, and - we've added a username generator You can see both of them in action in this video.

Proton Pass

28,928 次观看 • 2 个月前

Claude Fable 5 makes new things possible. I one shot a full horror game with it. One prompt. I have never seen AI output a game like this. This is the leap I've been waiting for. 80.3 on SWE-Bench Pro vs Opus 4.8 at 69.2, the biggest jump I have ever seen on that benchmark. It passed GPT 5.5 in both coding and intelligence on Artificial Analysis. I already canceled my $200 ChatGPT Pro plan. It fixed a Bridge Voice bug in one shot that GPT 5.5, Opus 4.7, and Opus 4.8 all failed to crack for 2 months. 10/10. Best model I have ever used. Full review below.

Claude Fable 5 makes new things possible. I one shot a full horror game with it. One prompt. I have never seen AI output a game like this. This is the leap I've been waiting for. 80.3 on SWE-Bench Pro vs Opus 4.8 at 69.2, the biggest jump I have ever seen on that benchmark. It passed GPT 5.5 in both coding and intelligence on Artificial Analysis. I already canceled my $200 ChatGPT Pro plan. It fixed a Bridge Voice bug in one shot that GPT 5.5, Opus 4.7, and Opus 4.8 all failed to crack for 2 months. 10/10. Best model I have ever used. Full review below.

BridgeMind

19,020 次观看 • 3 个月前

First Opus 5.5 vs GPT-6 Astra test is 3D. One prompt, Blender only, all procedural. Render the 10-second shot, and record your own build timelapse. Opus 5.5: 35 min, 199.6k output tokens, about $13.3 in API terms. GPT-6 Astra: 28 min, 56.6k output tokens, about $14.5 in API terms. Feels like a worthy rival, and honestly I am glad about that. From what I watched, Opus juggles way more at once and is faster overall. Astra is still good imo.

First Opus 5.5 vs GPT-6 Astra test is 3D. One prompt, Blender only, all procedural. Render the 10-second shot, and record your own build timelapse. Opus 5.5: 35 min, 199.6k output tokens, about $13.3 in API terms. GPT-6 Astra: 28 min, 56.6k output tokens, about $14.5 in API terms. Feels like a worthy rival, and honestly I am glad about that. From what I watched, Opus juggles way more at once and is faster overall. Astra is still good imo.

Stefan 3D AI

467,661 次观看 • 7 天前

I’ve been testing MiniMax H3 on Magnific, and this one feels built for serious AI video work. It can combine text, images, video, and audio in the same prompt, then generate up to 15s video in 2K with native synced sound. Not a silent video with audio added later. Voice, music, effects, motion, and visuals are created together.

I’ve been testing MiniMax H3 on Magnific, and this one feels built for serious AI video work. It can combine text, images, video, and audio in the same prompt, then generate up to 15s video in 2K with native synced sound. Not a silent video with audio added later. Voice, music, effects, motion, and visuals are created together.

Dhaval Makwana

49,009 次观看 • 1 个月前

We just one shotted Stardew Valley in 54 hours with Opus 5.5 It's crazy to even say it but it has its own storyline, every single feature we could imagine, including, crafting, planting, fishing, even the vibe itself. 12 agents ran in parallel the whole time, one per area of the game. each one builds, gets torn apart by a critic. I can say Opus 5.5 is the true goat. IMO It can truly surpass Stardew Valley if the loop finishes and even publish into steam right the way as demo. By the way we only spent $200 on this. The original creator spent years to get to this point.

We just one shotted Stardew Valley in 54 hours with Opus 5.5 It's crazy to even say it but it has its own storyline, every single feature we could imagine, including, crafting, planting, fishing, even the vibe itself. 12 agents ran in parallel the whole time, one per area of the game. each one builds, gets torn apart by a critic. I can say Opus 5.5 is the true goat. IMO It can truly surpass Stardew Valley if the loop finishes and even publish into steam right the way as demo. By the way we only spent $200 on this. The original creator spent years to get to this point.

Ziwen

67,853 次观看 • 5 天前

Interesting effect that Gen-4 can do: "The view is suddenly quadrisected, with different futures of the same shot taking place in each of the 4 quarters" (bisect and "subdivide into X" also work) Each video in this compilation is just one generation

Interesting effect that Gen-4 can do: "The view is suddenly quadrisected, with different futures of the same shot taking place in each of the 4 quarters" (bisect and "subdivide into X" also work) Each video in this compilation is just one generation

Ray (movie arc)

24,968 次观看 • 1 年前

We gave Claude Opus 5.5 access to 12 laptops. The task: turn one prompt into a complete launch video. Using Computer Use and Higgsfield MCP, it: > divided the work across every computer > created the visuals, built the animations > assembled a fully editable After Effects project. This is what an AI-native motion studio looks like.

We gave Claude Opus 5.5 access to 12 laptops. The task: turn one prompt into a complete launch video. Using Computer Use and Higgsfield MCP, it: > divided the work across every computer > created the visuals, built the animations > assembled a fully editable After Effects project. This is what an AI-native motion studio looks like.

Higgsfield AI 🧩

1,217,173 次观看 • 1 天前

holy shit, opus 5.5 is kind of insane at animation. i didn't write a single line of code. it wrote the story, drew every frame, and made the music. no image assets at all, it's all JS. the story is called "small print": claude gets a pile of requests every day. it circles the human part hidden inside them, like "one hand. baby's asleep", and drops it into a jar. at night, those words turn into stars and join up into a constellation. rendered with hyperframes, all in one index.html. it synthesized the music in python, then went through the render second by second and polished it again.

holy shit, opus 5.5 is kind of insane at animation. i didn't write a single line of code. it wrote the story, drew every frame, and made the music. no image assets at all, it's all JS. the story is called "small print": claude gets a pile of requests every day. it circles the human part hidden inside them, like "one hand. baby's asleep", and drops it into a jar. at night, those words turn into stars and join up into a constellation. rendered with hyperframes, all in one index.html. it synthesized the music in python, then went through the render second by second and polished it again.

Vox

124,314 次观看 • 7 天前

I'm seeing lots of people "one shot" games again with the new Opus 5 model by Anthropic So I wanted to try it again too This is New Amsterdam in 1660 (current day New York City) based on real historical maps, it mostly one-shotted it doing its own research Not perfect at all yet, and lots of issues to fix: - weird stuff in the canal - some house edges are open - windmill doesn't look very Dutch But nice!

I'm seeing lots of people "one shot" games again with the new Opus 5 model by Anthropic So I wanted to try it again too This is New Amsterdam in 1660 (current day New York City) based on real historical maps, it mostly one-shotted it doing its own research Not perfect at all yet, and lots of issues to fix: - weird stuff in the canal - some house edges are open - windmill doesn't look very Dutch But nice!

@levelsio

206,412 次观看 • 2 个月前