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.

Microsoft published an image-to-GIF model called Pix2Gif! They claim that the model is better at understand motion, while we’re not talking Sora levels here, it’s certainly a step up compared to the slow-motion outputs we’re currently used to.

Dreaming Tulpa 🥓👑

55,175 subscribers

14,090 views • 2 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

1 Comments

Dreaming Tulpa 🥓👑2 years ago

If you like Tweets like this, you might enjoy my weekly newsletter, #aiartweekly. A free, once–weekly e-mail round-up of the latest AI art news, interviews with artists and useful tools & resources. Join 3500+ subscribers here:

Related Videos

🎉 After six incredible years at Framer, it’s time for my next step. Today, we’re spinning Framer Motion out into its own independent open-source project, to better serve the whole community. Introducing Motion. For React, and now, for everyone.

🎉 After six incredible years at Framer, it’s time for my next step. Today, we’re spinning Framer Motion out into its own independent open-source project, to better serve the whole community. Introducing Motion. For React, and now, for everyone.

Matt Perry

397,457 views • 1 year ago

i used AI to make an ad for an AI tool one product image. one prompt. it generated a cinematic cookie breaking apart in slow motion. no studio. no photographer. no edit. The tool is called eComrads it’s not even launched yet and it just marketed itself?

i used AI to make an ad for an AI tool one product image. one prompt. it generated a cinematic cookie breaking apart in slow motion. no studio. no photographer. no edit. The tool is called eComrads it’s not even launched yet and it just marketed itself?

K

17,387 views • 5 months ago

At we’re building a foundational protein machine learning model that aims to understand everything about macromolecules. We can successfully create a zinc binding site without ever specifying the positions or geometries to the model.

At we’re building a foundational protein machine learning model that aims to understand everything about macromolecules. We can successfully create a zinc binding site without ever specifying the positions or geometries to the model.

Kathy Y. Wei, Ph.D.

32,257 views • 3 years ago

We’re excited to share our latest work published today in Nature Biotechnology: Protein2PAM, an AI model that enables the rapid design of CRISPR editors with new PAM recognition And we’re making the model freely available for research and commercial use:

We’re excited to share our latest work published today in Nature Biotechnology: Protein2PAM, an AI model that enables the rapid design of CRISPR editors with new PAM recognition And we’re making the model freely available for research and commercial use:

Profluent

16,511 views • 6 months ago

Did you know you can create captivating motion sync videos on Yapper Follow the steps below and push your creativity boundaries Step 1: Go to on your browser step 2: Click on videos and select Motion Sync Step 3: Select Base Video The video's movement will be used to animate the reference image. Step 4: Add Reference Image Upload an image of a character to be animated by the base video. Step 5: Describe Your Vision Write a prompt that guides the background of the output video. Step 6: Generate Select your model and the output video will be generated in real-time

Did you know you can create captivating motion sync videos on Yapper Follow the steps below and push your creativity boundaries Step 1: Go to on your browser step 2: Click on videos and select Motion Sync Step 3: Select Base Video The video's movement will be used to animate the reference image. Step 4: Add Reference Image Upload an image of a character to be animated by the base video. Step 5: Describe Your Vision Write a prompt that guides the background of the output video. Step 6: Generate Select your model and the output video will be generated in real-time

Kuria | AI

46,344 views • 3 months ago

Google presents Still-Moving Customized Video Generation without Customized Video Data Customizing text-to-image (T2I) models has seen tremendous progress recently, particularly in areas such as personalization, stylization, and conditional generation. However, expanding this progress to video generation is still in its infancy, primarily due to the lack of customized video data. In this work, we introduce Still-Moving, a novel generic framework for customizing a text-to-video (T2V) model, without requiring any customized video data. The framework applies to the prominent T2V design where the video model is built over a text-to-image (T2I) model (e.g., via inflation). We assume access to a customized version of the T2I model, trained only on still image data (e.g., using DreamBooth or StyleDrop). Naively plugging in the weights of the customized T2I model into the T2V model often leads to significant artifacts or insufficient adherence to the customization data. To overcome this issue, we train lightweight Spatial Adapters that adjust the features produced by the injected T2I layers. Importantly, our adapters are trained on "frozen videos" (i.e., repeated images), constructed from image samples generated by the customized T2I model. This training is facilitated by a novel Motion Adapter module, which allows us to train on such static videos while preserving the motion prior of the video model. At test time, we remove the Motion Adapter modules and leave in only the trained Spatial Adapters. This restores the motion prior of the T2V model while adhering to the spatial prior of the customized T2I model. We demonstrate the effectiveness of our approach on diverse tasks including personalized, stylized, and conditional generation. In all evaluated scenarios, our method seamlessly integrates the spatial prior of the customized T2I model with a motion prior supplied by the T2V model.

Google presents Still-Moving Customized Video Generation without Customized Video Data Customizing text-to-image (T2I) models has seen tremendous progress recently, particularly in areas such as personalization, stylization, and conditional generation. However, expanding this progress to video generation is still in its infancy, primarily due to the lack of customized video data. In this work, we introduce Still-Moving, a novel generic framework for customizing a text-to-video (T2V) model, without requiring any customized video data. The framework applies to the prominent T2V design where the video model is built over a text-to-image (T2I) model (e.g., via inflation). We assume access to a customized version of the T2I model, trained only on still image data (e.g., using DreamBooth or StyleDrop). Naively plugging in the weights of the customized T2I model into the T2V model often leads to significant artifacts or insufficient adherence to the customization data. To overcome this issue, we train lightweight Spatial Adapters that adjust the features produced by the injected T2I layers. Importantly, our adapters are trained on "frozen videos" (i.e., repeated images), constructed from image samples generated by the customized T2I model. This training is facilitated by a novel Motion Adapter module, which allows us to train on such static videos while preserving the motion prior of the video model. At test time, we remove the Motion Adapter modules and leave in only the trained Spatial Adapters. This restores the motion prior of the T2V model while adhering to the spatial prior of the customized T2I model. We demonstrate the effectiveness of our approach on diverse tasks including personalized, stylized, and conditional generation. In all evaluated scenarios, our method seamlessly integrates the spatial prior of the customized T2I model with a motion prior supplied by the T2V model.

AK

40,485 views • 2 years ago

A slow motion look at an industrial sewing machine is probably the best way to understand how this kind of machines works [animation: [source, Ben Geisler:

A slow motion look at an industrial sewing machine is probably the best way to understand how this kind of machines works [animation: [source, Ben Geisler:

Massimo

229,306 views • 3 years ago

we’re launching Motion, the frontier agent for tasteful motion design. this launch video is made entirely with Motion. 👇🏽 QT + comment "MOTION" to get 1,000 free credits. tag Motion in any X post for a surprise. now generally available at motion [dot] so.

we’re launching Motion, the frontier agent for tasteful motion design. this launch video is made entirely with Motion. 👇🏽 QT + comment "MOTION" to get 1,000 free credits. tag Motion in any X post for a surprise. now generally available at motion [dot] so.

Motion

17,763 views • 2 months ago

we’re launching Motion, the frontier agent for tasteful motion design. this launch video is made entirely with Motion. 👇🏽 QT + comment "MOTION" to get 1,000 free credits. tag Motion in any X post for a surprise. now generally available at motion [dot] so.

we’re launching Motion, the frontier agent for tasteful motion design. this launch video is made entirely with Motion. 👇🏽 QT + comment "MOTION" to get 1,000 free credits. tag Motion in any X post for a surprise. now generally available at motion [dot] so.

Adish Jain ☕️

933,796 views • 2 months ago

everything is better in slow motion 😌 (the choking, the squishing, THE SMILE?!??) is this the video they wanted to do for a long time? #WilliamEst

everything is better in slow motion 😌 (the choking, the squishing, THE SMILE?!??) is this the video they wanted to do for a long time? #WilliamEst

Val♡

59,996 views • 9 months ago

Say goodbye to green screens! DiffusionMat is an AI framework that uses a diffusion model to create refined alpha mattes by correcting the output at every denoising step to look more like the original input image.

Say goodbye to green screens! DiffusionMat is an AI framework that uses a diffusion model to create refined alpha mattes by correcting the output at every denoising step to look more like the original input image.

Dreaming Tulpa 🥓👑

146,582 views • 2 years ago

Claude Fable 5 must be insane. I just used Sonnet 4.5 to build Riley in 10 days. From the initial idea → app design → code → App Store panic. We’re entering an era where waiting for a better model is becoming the new procrastination. You don’t need a better model. You just need to start.

Claude Fable 5 must be insane. I just used Sonnet 4.5 to build Riley in 10 days. From the initial idea → app design → code → App Store panic. We’re entering an era where waiting for a better model is becoming the new procrastination. You don’t need a better model. You just need to start.

Nusret Uzman

11,004 views • 1 month ago

It’s frustrating to see the CE remake default to the Infinite needler when even Infinite MP has a better model (Type-33) they could’ve used. Perhaps it will be the model they go with. Even then, I still think the ammo counter is very redundant and an eyesore.

It’s frustrating to see the CE remake default to the Infinite needler when even Infinite MP has a better model (Type-33) they could’ve used. Perhaps it will be the model they go with. Even then, I still think the ammo counter is very redundant and an eyesore.

ringoid

146,887 views • 10 months ago

Cool new model release: PaintsUndo, which takes an image and outputs step-by-step frames of how to draw it. It starts with a sketch and then fills in the colors, shading, and lighting.

Cool new model release: PaintsUndo, which takes an image and outputs step-by-step frames of how to draw it. It starts with a sketch and then fills in the colors, shading, and lighting.

Justine Moore

146,126 views • 2 years ago

ELON: I’M TRYING TO SET THINGS IN MOTION TO BETTER UNDERSTAND THE UNIVERSE “My motivation, if I've got a religion of any kind, is a religion of curiosity, of trying to understand the universe. It's really the mission of Grok. I'm trying to understand the universe or at least set things in motion such that at some point, civilization understands the universe far better than we do today.” Source: Lex Fridman

ELON: I’M TRYING TO SET THINGS IN MOTION TO BETTER UNDERSTAND THE UNIVERSE “My motivation, if I've got a religion of any kind, is a religion of curiosity, of trying to understand the universe. It's really the mission of Grok. I'm trying to understand the universe or at least set things in motion such that at some point, civilization understands the universe far better than we do today.” Source: Lex Fridman

Mario Nawfal

366,566 views • 2 years ago

Liberal Leader Mark Carney, this weekend, joked about the Canadian response to tariffs. “We’re fighting them on Fox News, which is what they understand. We’re sending Doug Ford on Fox News to show them we’re not messing around up here.” #ONpoli

Liberal Leader Mark Carney, this weekend, joked about the Canadian response to tariffs. “We’re fighting them on Fox News, which is what they understand. We’re sending Doug Ford on Fox News to show them we’re not messing around up here.” #ONpoli

Colin D'Mello | Global News

289,858 views • 1 year ago

Today, we’re launching Reve 2.0, the best 4K image model in the world. We invented a new way to generate and edit any image using precise layouts. For the first time, it’s possible to create images you can touch.

Today, we’re launching Reve 2.0, the best 4K image model in the world. We invented a new way to generate and edit any image using precise layouts. For the first time, it’s possible to create images you can touch.

Reve

11,943,962 views • 2 months ago