正在加载视频...

视频加载失败

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.

270,942 次观看 • 2 年前 •via X (Twitter)

10 条评论

Dreaming Tulpa 🥓👑 的头像
Dreaming Tulpa 🥓👑2 年前

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 2800+ subscribers here:

esflow 的头像
esflow2 年前

Damn what a time to be alive

Mind Wank 的头像
Mind Wank2 年前

🤯

Crystalwizard 的头像
Crystalwizard2 年前

Surprised they have jumped to this before putting generative ai into premier pro

Merzmensch Kosmopol🧑‍🎨🤖 的头像
Merzmensch Kosmopol🧑‍🎨🤖2 年前

Wow, that's big!

inhabitant 的头像
inhabitant2 年前

I hope someone has had the idea of using ai to texture a hand crafted geometry with nice topology, based off reference image. I'm a dummy though, so perhaps whole new problem rather than a subset of this and optimizing/rework a generated mesh is superior anyway. This is so cool

Creative AIgency | Kevin K. Shah 的头像
Creative AIgency | Kevin K. Shah2 年前

👀🔥

Nathania 的头像
Nathania2 年前

🔥

Whisper Gently 的头像
Whisper Gently2 年前

Should be great. Adobe does it right

utkarsh 的头像
utkarsh2 年前

@rahilkoshti

相关视频