Загрузка видео...

Не удалось загрузить видео

На главную

Early test run with freshly added depth estimation — Mixed Reality + Diffusion prototype to explore concepts, styles, and moods. #MixedReality #MR #AI #StableDiffusion #Quest3

13,054 просмотров • 1 год назад •via X (Twitter)

Комментарии: 11

Фото профиля Johannes Tscharn
Johannes Tscharn1 год назад

How are you actually computing the depth? I tried MiDaS running locally via Sentis but it’s slow and inaccurate… DepthAPI? Awesome stuff in any case 👍

Фото профиля Hugues Bruyère
Hugues Bruyère1 год назад

Here the depth estimation is done at the same time as the diffusion and therefore on a remote computer (my desktop next to me).

Фото профиля JMIR Publications
JMIR Publications2 лет назад

#CallForPapers 📣 📝 JMIR Rehabilitation and Assistive Technologies invites submissions for our #themeissue, "Incorporating Participatory Methods in Developing, Implementing, and Evaluating #Rehab Interventions and #AssistiveTechnologies" ℹ️ @drsarahmunce

Фото профиля Derek
Derek1 год назад

super impressive! 3D adds so much

Фото профиля Egon
Egon1 год назад

Impressive!

Фото профиля richardanaya2_2048b.Q6_K.gguf 🇺🇸🤖
richardanaya2_2048b.Q6_K.gguf 🇺🇸🤖1 год назад

Eerie

Фото профиля NoobGeek
NoobGeek1 год назад

It's so cool!Does it run locally?

Фото профиля Hugues Bruyère
Hugues Bruyère1 год назад

Diffusion and depth estimation are done on remote machine.

Фото профиля Saucy shuriken
Saucy shuriken1 год назад

I love this! Anyway how I can use it as well ?

Фото профиля AI will fuck your mum
AI will fuck your mum1 год назад

this looks awesome

Фото профиля Daniel Trujillo
Daniel Trujillo1 год назад

I need this in my life.

Похожие видео

In collaboration with Intel, our Depth Fusion showcases the power of our LDM3D diffusion model in generating 360° views from text prompts provided by the user. The LDM3D diffusion model generates a 2D RGB image and its corresponding relative depth map providing a complete RGBD representation corresponding to the text prompt. The LDM 3D model is a specialized version of the stable diffusion V 1.4 model that has been modified to fit both image and depth map data.The model was then fine tuned on a subset of the Laion400M data set - large scale image caption data set. The depth maps used to fine tune our model were generated by the DPTBeiT large 512 depth estimation model that provides highly accurate relative depth estimates for each pixel. We take the generated 2D RGB image and depth map and use them to compute a 360° projection using touchdesigner. Touchdesigner is a versatile platform that allows for the creation of immersive and interactive multimedia experiences. Our application harnesses the power of touchdesigner to bring the generated 360° views to life, providing users with a unique and engaging way to experience their text prompts, whether it’s a description of a tranquil forest, a noisy cityscape or a futuristic sci fi world. Our depth fusion can bring these concepts to life in a vivid and immersive detail. - Scottie Fox, VP Engineering Blockade Labs ScottieFox #AI #VR #3D #gamedev #stablediffusion

Blockade Labs

11,439 просмотров • 3 лет назад