Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Oh, I love this one! FlipSketch can generate sketch animations from static drawings using text prompts! Links ⬇️

Dreaming Tulpa 🥓👑

54,846 subscribers

33,368 views • 1 year ago •via X (Twitter)

Science & Technology Education Arts

Anya Rossi• Live Now

Private livecam show

10 Comments

Dreaming Tulpa 🥓👑1 year ago

Project Page: Code (coming soon): Get notified on release:

Hmrishav1 year ago

Thank you for covering this! We have released the code :)

Dreaming Tulpa 🥓👑1 year ago

You dropped this 👑

John Schoenith1 year ago

Need this for a project that I’m working on today. Thanks

Dreaming Tulpa 🥓👑1 year ago

Enjoy! Code just got published 🥳

EyeSeeThru 👁️1 year ago

me too!

Bjorn1 year ago

Oh that’s cool!

aymiee1 year ago

Very cool!

Dreaming Tulpa 🥓👑1 year ago

Very cool indeed :)

Vincent Valentine (CEO of UnOpen.ai)1 year ago

@mreflow That sounds like a fascinating tool.

Related Videos

HoloDreamer can generate enclosed 3D scenes from text descriptions! It does so by first creating a high-quality equirectangular panorama and then rapidly reconstructing the 3D scene using 3D Gaussian Splatting. Links ⬇️

HoloDreamer can generate enclosed 3D scenes from text descriptions! It does so by first creating a high-quality equirectangular panorama and then rapidly reconstructing the 3D scene using 3D Gaussian Splatting. Links ⬇️

Dreaming Tulpa 🥓👑

59,377 views • 2 years ago

omg.. I can't believe Gemini 3 can do this it can generate an entire 3D interactive building facility management system(digital twin) using Three.js.. no code, just text prompt it analyse, simulate real time data to identify potential issues tutorial and prompts in comments

omg.. I can't believe Gemini 3 can do this it can generate an entire 3D interactive building facility management system(digital twin) using Three.js.. no code, just text prompt it analyse, simulate real time data to identify potential issues tutorial and prompts in comments

el.cine

681,626 views • 9 months ago

oh my.. AI is coming for motion graphics you can animate text&graphics by prompting using Claude now.. guide&prompts+crazy examples:

oh my.. AI is coming for motion graphics you can animate text&graphics by prompting using Claude now.. guide&prompts+crazy examples:

el.cine

64,883 views • 7 months ago

AI can synthesize dynamic textures on 3D meshes without UV maps! MeshNCA is a model that can generate dynamic textures from images, text prompts, and motion vector fields.

AI can synthesize dynamic textures on 3D meshes without UV maps! MeshNCA is a model that can generate dynamic textures from images, text prompts, and motion vector fields.

Dreaming Tulpa 🥓👑

79,605 views • 2 years ago

100% AI ad using my v3 prompts. this is the recent dramAds you can try. literally can generate whatever you want, and it's crazy to see. here's a random vid i did:

100% AI ad using my v3 prompts. this is the recent dramAds you can try. literally can generate whatever you want, and it's crazy to see. here's a random vid i did:

0x ROAS

12,931 views • 3 months ago

From text to reality: MIT researchers find new ways to use LLMs to help in design & manufacturing. These models can convert text prompts to CAD, generate manufacturing instructions, and search for optimal designs:

From text to reality: MIT researchers find new ways to use LLMs to help in design & manufacturing. These models can convert text prompts to CAD, generate manufacturing instructions, and search for optimal designs:

MIT CSAIL

59,161 views • 3 years ago

Gemini 3.0 Pro is at great 3D design and front-end. It can generate complex 3D scenes and Three.js objects from text prompts. Here's a nice retro-future example from cris.

Gemini 3.0 Pro is at great 3D design and front-end. It can generate complex 3D scenes and Three.js objects from text prompts. Here's a nice retro-future example from cris.

Addy Osmani

90,189 views • 8 months ago

You can now generate smart personal podcasts from any of your PDFs, articles, eBooks, links or text in 32 languages with our ElevenReader iOS app.

You can now generate smart personal podcasts from any of your PDFs, articles, eBooks, links or text in 32 languages with our ElevenReader iOS app.

ElevenLabs

232,798 views • 1 year ago

AI image creation just changed. Not better prompts better thinking. Uni-1 doesn’t just generate… it understands, plans, and executes. Sketch → photoreal Idea → cinematic frame Concept → full composition This isn’t text-to-image anymore. It’s reasoning-to-image. #Uni1 #AIArt #Luma

AI image creation just changed. Not better prompts better thinking. Uni-1 doesn’t just generate… it understands, plans, and executes. Sketch → photoreal Idea → cinematic frame Concept → full composition This isn’t text-to-image anymore. It’s reasoning-to-image. #Uni1 #AIArt #Luma

Darshal Jaitwar

69,209 views • 5 months ago

Built a webpage using Grok 4 Heavy to generate Grok Imagine prompts, based on Grok prompting tips from the web. Funny side note: I have scheduled tasks sent to my inbox from Grok4. One arrived while recording this video. Doomers are citing ethics about memes. 😂

Built a webpage using Grok 4 Heavy to generate Grok Imagine prompts, based on Grok prompting tips from the web. Funny side note: I have scheduled tasks sent to my inbox from Grok4. One arrived while recording this video. Doomers are citing ethics about memes. 😂

tetsuo

922,282 views • 1 year ago

🚨 THIS WAS CREATED ENTIRELY WITH AI USING ONLY A FEW PROMPTS Now anyone can create incredible, production-grade animations. The world is changing, fast.

🚨 THIS WAS CREATED ENTIRELY WITH AI USING ONLY A FEW PROMPTS Now anyone can create incredible, production-grade animations. The world is changing, fast.

Coin Bureau

62,305 views • 4 months ago

Google announces MusicLM: a model to generate music from text. Here are some crazy things it can do: 1. Given audio of a melody, it can generate new music inspired by that melody customized by prompts! Here's someone humming bella ciao turned into a cappella chorus, EDM, etc.

Google announces MusicLM: a model to generate music from text. Here are some crazy things it can do: 1. Given audio of a melody, it can generate new music inspired by that melody customized by prompts! Here's someone humming bella ciao turned into a cappella chorus, EDM, etc.

bleedingedge.ai

379,939 views • 3 years ago

This Hungarian animated short from 1980 called "The Fly" was made using 4,000 crayon drawings. This is the soul Al can never replace.

This Hungarian animated short from 1980 called "The Fly" was made using 4,000 crayon drawings. This is the soul Al can never replace.

Time Capsule Tales

337,927 views • 5 months ago

ByteDance announced SeedEdit! A new image model that can edit images with text prompts. It allows for high-resolution editing and supports various changes like local replacements, geometric transformations, and style adjustments. Links ⬇️

ByteDance announced SeedEdit! A new image model that can edit images with text prompts. It allows for high-resolution editing and supports various changes like local replacements, geometric transformations, and style adjustments. Links ⬇️

Dreaming Tulpa 🥓👑

46,557 views • 1 year ago

oh i LOVE this one

oh i LOVE this one

lara

88,657 views • 6 months ago

I generated this 3D enviroment using a single image using "Marble" from World Labs. The new version can generate a mesh from the splat and is directly usable in Unreal Engine 5.7.

I generated this 3D enviroment using a single image using "Marble" from World Labs. The new version can generate a mesh from the splat and is directly usable in Unreal Engine 5.7.

Matt Workman

42,460 views • 9 months ago

i created this Vietnam War documentary in a few minutes just using the 2 preset prompts from this article this is how: 1- copy-pasted both image & video prompts 2- sent them to Claude 3- used the Calliope MCP connector to create a template in 16:9 4- generated ideas + a 1 min script for this example (you can generate up to 60 mins 💀) 5- created the video using the Extra High models which is now 50% cheaper than yesterday! (this is permanent) minimax h3 (calliope’s Ex.H model) cooked these amazing motion graphic animations ⬇️ this was one-shot, and has obvious quirks, like putting red strings all over the place. It'd just be a matter of correcting that… “NO red strings” in the Video Style (one sentence), and iterating :)

i created this Vietnam War documentary in a few minutes just using the 2 preset prompts from this article this is how: 1- copy-pasted both image & video prompts 2- sent them to Claude 3- used the Calliope MCP connector to create a template in 16:9 4- generated ideas + a 1 min script for this example (you can generate up to 60 mins 💀) 5- created the video using the Extra High models which is now 50% cheaper than yesterday! (this is permanent) minimax h3 (calliope’s Ex.H model) cooked these amazing motion graphic animations ⬇️ this was one-shot, and has obvious quirks, like putting red strings all over the place. It'd just be a matter of correcting that… “NO red strings” in the Video Style (one sentence), and iterating :)

Sergio Gil

50,795 views • 7 days ago

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.

AK

126,612 views • 2 years ago