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.

adobe just released a method that can generate transparent videos from text and images 👀

Dreaming Tulpa 🥓👑

55,233 subscribers

77,051 views • 1 year ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

12 Comments

Dreaming Tulpa 🥓👑1 year ago

the method is called TransPixar and makes it possible to create transparent elements like smoke and reflections that blend seamlessly into scenes project page: code: demo:

Freepik1 year ago

🚀 Introducing Freepik AI video generator. Everything you need to create high-quality, physically accurate videos in one place. 🤩

metaᑐᑌᑎᑕ.tez1 year ago

Nope, not falling for it! I’ve downloaded enough ‘transparent’ pngs off Google to know that checkerboard background will be embedded 🙃😂

Dreaming Tulpa 🥓👑1 year ago

lmao

The Artist1 year ago

Wow this is gonna change the after affects game!!!

Dreaming Tulpa 🥓👑1 year ago

yes, lots of potential

Markus Malmros1 year ago

Wait a minute, Adobe and released code. That's not every day, but I wholeheartedly support it!

alex1 year ago

There are a lot of potential gif and video meme applications with this new tech. The future is here.

Dreaming Tulpa 🥓👑1 year ago

yeeeep

ǝɥǝ⅄1 year ago

just add alpha channel.

Heather Cooper1 year ago

Oh wow! Nice!

Dreaming Tulpa 🥓👑1 year ago

totally heather

Related Videos

Nvidia released Describe Anything! a new method that can generate detailed descriptions for specific areas in images and videos using points, boxes, scribbles, or masks

Nvidia released Describe Anything! a new method that can generate detailed descriptions for specific areas in images and videos using points, boxes, scribbles, or masks

Dreaming Tulpa 🥓👑

52,217 views • 1 year ago

adobe is cooking a new method to generate sound from vocal imitations 👀

adobe is cooking a new method to generate sound from vocal imitations 👀

Dreaming Tulpa 🥓👑

154,020 views • 1 year ago

Adobe presents SynCHMR! A method that can reconstruct camera trajectory, human motion, and scene in one global coordinate from videos 🔥

Adobe presents SynCHMR! A method that can reconstruct camera trajectory, human motion, and scene in one global coordinate from videos 🔥

Dreaming Tulpa 🥓👑

108,620 views • 2 years ago

Adobe is entering the image-to-3D game! Their new method, LRM, can create high-fidelity 3D meshes from a single image in just 5 seconds 🔥 It's trained on 1 million objects and is able to generate objects from real-world images and generative AI models.

Adobe is entering the image-to-3D game! Their new method, LRM, can create high-fidelity 3D meshes from a single image in just 5 seconds 🔥 It's trained on 1 million objects and is able to generate objects from real-world images and generative AI models.

Dreaming Tulpa 🥓👑

270,942 views • 2 years 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 🥓👑

79,593 views • 2 years ago

Meet Gemini Omni, our new model that can create anything from any input, starting with video. With Gemini Omni, you can combine images, videos and text as inputs and generate high-quality videos grounded in Gemini's real-world knowledge. #GoogleIO

Meet Gemini Omni, our new model that can create anything from any input, starting with video. With Gemini Omni, you can combine images, videos and text as inputs and generate high-quality videos grounded in Gemini's real-world knowledge. #GoogleIO

Google Gemini

88,240 views • 29 days ago

Meet Gemini Omni, our new model that can create anything from any input, starting with video. With Gemini Omni, you can combine images, videos and text as inputs and generate high-quality videos grounded in Gemini's real-world knowledge.

Meet Gemini Omni, our new model that can create anything from any input, starting with video. With Gemini Omni, you can combine images, videos and text as inputs and generate high-quality videos grounded in Gemini's real-world knowledge.

Google Gemini

32,779,480 views • 20 days ago

adobe is cooking a new method that can automatically rig 3D assets by generating joints, skeletons, and skinning weights 👀

adobe is cooking a new method that can automatically rig 3D assets by generating joints, skeletons, and skinning weights 👀

Dreaming Tulpa 🥓👑

99,404 views • 1 year ago

Introducing Text-to-Video on ChatGPT 🤯 I built a plugin that allows you to generate videos from just text! Built on Replit ⠕ and powered by Replicate 🔥

Introducing Text-to-Video on ChatGPT 🤯 I built a plugin that allows you to generate videos from just text! Built on Replit ⠕ and powered by Replicate 🔥

Zahid Khawaja

228,012 views • 3 years ago

Adobe just released its first “commercially safe” Adobe Firefly Video in public beta. You can access it in Adobe Premiere & a new Firefly mobile app. Scene to Image & Text to Image are interesting for 3D artists, as you have a lot of control over your images. What do you think?

Adobe just released its first “commercially safe” Adobe Firefly Video in public beta. You can access it in Adobe Premiere & a new Firefly mobile app. Scene to Image & Text to Image are interesting for 3D artists, as you have a lot of control over your images. What do you think?

E.J. Hassenfratz

22,858 views • 1 year ago

Adobe just released design AI Assistant in Adobe Express 🎉 I designed video game assets and a thumbnail for my new retro video game. You can design templates and edit images with it just with a prompt. Isn’t it cool? 🥹 🐢

Adobe just released design AI Assistant in Adobe Express 🎉 I designed video game assets and a thumbnail for my new retro video game. You can design templates and edit images with it just with a prompt. Isn’t it cool? 🥹 🐢

Kris Kashtanova

22,256 views • 7 months ago

Stanford and NVIDIA released a TTT-MLP Al that can generate a 1 minute animated from a text prompt. Not perfect, but incredibly interesting. Tom & Jerry but 100% Al.

Stanford and NVIDIA released a TTT-MLP Al that can generate a 1 minute animated from a text prompt. Not perfect, but incredibly interesting. Tom & Jerry but 100% Al.

Brian Roemmele

79,607 views • 1 year ago

Nvidia presents EdgeRunner! The method can generate high-quality 3D meshes with up to 4,000 faces at a spatial resolution of 512 from images and point-clouds.

Nvidia presents EdgeRunner! The method can generate high-quality 3D meshes with up to 4,000 faces at a spatial resolution of 512 from images and point-clouds.

Dreaming Tulpa 🥓👑

173,103 views • 1 year ago

Now you can generate entirely new videos from text, bring images to life, or extend, remix, or blend videos you already have. We’ve developed new interfaces to allow easier prompting, creative controls, and community sharing:

Now you can generate entirely new videos from text, bring images to life, or extend, remix, or blend videos you already have. We’ve developed new interfaces to allow easier prompting, creative controls, and community sharing:

OpenAI

108,312 views • 1 year ago

BREAKING: a new Chinese model is out. And no. This is NOT DeepSeek. Meet Qwen-2.5, from the giant Alibaba: 1. It can code, write text, search the web. 2. It can generate images, like Dall-E. 3. It can even generate videos. Here's everything you need to know:

BREAKING: a new Chinese model is out. And no. This is NOT DeepSeek. Meet Qwen-2.5, from the giant Alibaba: 1. It can code, write text, search the web. 2. It can generate images, like Dall-E. 3. It can even generate videos. Here's everything you need to know:

Ruben Hassid

363,453 views • 1 year ago

This week, grounding DINO 1.5 was released It is a new model that uses text prompts to detect objects from videos and images in real-time Examples & demo to try below:

This week, grounding DINO 1.5 was released It is a new model that uses text prompts to detect objects from videos and images in real-time Examples & demo to try below:

Allen T.

56,013 views • 2 years ago

Bye bye expensive mocap equipment 👋 AiOS is yet another method that can reconstruct human from videos and images! This one also supports hands and facial expressions.

Bye bye expensive mocap equipment 👋 AiOS is yet another method that can reconstruct human from videos and images! This one also supports hands and facial expressions.

Dreaming Tulpa 🥓👑

59,479 views • 2 years ago

Use Chat Mode to generate anything. From ideation to iteration, you can now generate both images and videos within a single conversational interface. Learn how in today's Runway Academy.

Use Chat Mode to generate anything. From ideation to iteration, you can now generate both images and videos within a single conversational interface. Learn how in today's Runway Academy.

Runway

17,508 views • 1 year ago