Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Microsoft released Trellis! Trellis is a new 3D model that generates high-quality 3D assets in formats like Radiance Fields, 3D Gaussians, and meshes.

dreamingtulpa's profile picture

Dreaming Tulpa ๐Ÿฅ“๐Ÿ‘‘

54,890 subscribers

85,115 Aufrufe โ€ข vor 1 Jahr โ€ขvia X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossiโ€ข Live Now

Private livecam show

11 Kommentare

Profilbild von Dreaming Tulpa ๐Ÿฅ“๐Ÿ‘‘
Dreaming Tulpa ๐Ÿฅ“๐Ÿ‘‘vor 1 Jahr

Project Page: Code: Demo:

Profilbild von Neuro
Neurovor 1 Jahr

Ngl that looks solid

Profilbild von Dreaming Tulpa ๐Ÿฅ“๐Ÿ‘‘
Dreaming Tulpa ๐Ÿฅ“๐Ÿ‘‘vor 1 Jahr

yeah, probably the best one yet

Profilbild von David Richeson
David Richesonvor 1 Jahr

- thanks for the info and link!! ๐Ÿ˜€ In 5 minutes I made this neat 3D Mech Crab. Sending it to print now on my Bambu printer, I have 4 3d printers and love it.

Profilbild von Dreaming Tulpa ๐Ÿฅ“๐Ÿ‘‘
Dreaming Tulpa ๐Ÿฅ“๐Ÿ‘‘vor 1 Jahr

The A1 mini looks like a great starter printer

Profilbild von David Sno
David Snovor 1 Jahr

Wow. Itโ€™s soooo close. ๐Ÿคฏ @Slant3D

Profilbild von Dreaming Tulpa ๐Ÿฅ“๐Ÿ‘‘
Dreaming Tulpa ๐Ÿฅ“๐Ÿ‘‘vor 1 Jahr

@Slant3D Not bad!

Profilbild von Justin Means
Justin Meansvor 1 Jahr

MIT licensed SOTA model ๐Ÿ˜ฒ. Crazy this is the only post on X about Trellis!

Profilbild von Dreaming Tulpa ๐Ÿฅ“๐Ÿ‘‘
Dreaming Tulpa ๐Ÿฅ“๐Ÿ‘‘vor 1 Jahr

Just wait, all the "AI educators" will follow ๐Ÿ˜…

Profilbild von Chris Rogers
Chris Rogersvor 1 Jahr

@Scobleizer Seems we are getting close to replicator technology... (in a way). Hook the output of this to an on demand FDM or SLA printer and get parts on demand via a text prompt!

Profilbild von Dreaming Tulpa ๐Ÿฅ“๐Ÿ‘‘
Dreaming Tulpa ๐Ÿฅ“๐Ÿ‘‘vor 1 Jahr

@Scobleizer I need to get my hands on a 3D printer. Any recommendation that won't break the bank?

ร„hnliche Videos

Current 3D generative models are slow and low quality. We present GRM, a large-scale model that reconstructs 3D Gaussians in 0.1s and generates high-quality 3D assets from text or single images in a few seconds. Demo: 1/4
0:37

Current 3D generative models are slow and low quality. We present GRM, a large-scale model that reconstructs 3D Gaussians in 0.1s and generates high-quality 3D assets from text or single images in a few seconds. Demo: 1/4

Gordon Wetzstein

19,189 Aufrufe โ€ข vor 2 Jahren

Another gem-TRELLIS.2: Native 3D generation via structured latents; - full PBR assets up to 1536ยณ; - outperforms TRELLIS & Direct3D-S2.
0:24

Another gem-TRELLIS.2: Native 3D generation via structured latents; - full PBR assets up to 1536ยณ; - outperforms TRELLIS & Direct3D-S2.

Wildminder

56,275 Aufrufe โ€ข vor 6 Monaten

I 3D printed this viral Trellis Storage System
0:53

I 3D printed this viral Trellis Storage System

CodeMiko

17,189 Aufrufe โ€ข vor 6 Monaten

Microsoft just released TRELLIS 2
0:59

Microsoft just released TRELLIS 2

AK

294,115 Aufrufe โ€ข vor 6 Monaten

Oh wow! TRELLIS 2 just dropped and it's a huge leap for image โ†’ 3D mesh generation. ๐Ÿ“ฆ Compact structured latents = editable, efficient meshes ๐Ÿ” Sharper topology + better materials ๐Ÿ’จ Faster inference with higher quality Links ๐Ÿ‘‡
0:37

Oh wow! TRELLIS 2 just dropped and it's a huge leap for image โ†’ 3D mesh generation. ๐Ÿ“ฆ Compact structured latents = editable, efficient meshes ๐Ÿ” Sharper topology + better materials ๐Ÿ’จ Faster inference with higher quality Links ๐Ÿ‘‡

Will Eastcott

21,235 Aufrufe โ€ข vor 6 Monaten

Itโ€™s really cool to see โ€œlegacyโ€ players in geospatial like ESRI adopt 3D gaussian splatting in ArcGIS. Radiance fields are v. complementary to point clouds and textured 3D meshes โ€” exceedingly human readable and much closer to reality than anything else.
0:37

Itโ€™s really cool to see โ€œlegacyโ€ players in geospatial like ESRI adopt 3D gaussian splatting in ArcGIS. Radiance fields are v. complementary to point clouds and textured 3D meshes โ€” exceedingly human readable and much closer to reality than anything else.

Bilawal Sidhu

26,954 Aufrufe โ€ข vor 4 Monaten

Alibaba released LHM! a new model that can generate high-quality, animatable 3D human avatars from a single image in just a few seconds
0:55

Alibaba released LHM! a new model that can generate high-quality, animatable 3D human avatars from a single image in just a few seconds

Dreaming Tulpa ๐Ÿฅ“๐Ÿ‘‘

21,853 Aufrufe โ€ข vor 1 Jahr

๐Ÿ”ฅText-to-3D Foundation Model๐Ÿ”ฅ We are excited to announce #3DTopia, a generalist ๐ŸงŠtext-to-3D๐ŸงŠ foundation model, which produces ** high-quality 3D assets within 5 minutes ** - Code: - Video:
0:58

๐Ÿ”ฅText-to-3D Foundation Model๐Ÿ”ฅ We are excited to announce #3DTopia, a generalist ๐ŸงŠtext-to-3D๐ŸงŠ foundation model, which produces ** high-quality 3D assets within 5 minutes ** - Code: - Video:

Ziwei Liu

62,424 Aufrufe โ€ข vor 2 Jahren

Microsoft lanzรณ TRELLIS 2 Herramienta gratuita y open source que convierte cualquier imagen en un modelo 3D de alta calidad en segundos.
0:59

Microsoft lanzรณ TRELLIS 2 Herramienta gratuita y open source que convierte cualquier imagen en un modelo 3D de alta calidad en segundos.

Miguel รngel | GptZone

33,194 Aufrufe โ€ข vor 2 Monaten

Gaussian Shell Maps are a new neural scene representation that connects fields and 3D Gaussians. This representation unlocks the full potential of 3D Gaussian splatting for generative AI applications, such as 3D avatar generation. 1/2
0:22

Gaussian Shell Maps are a new neural scene representation that connects fields and 3D Gaussians. This representation unlocks the full potential of 3D Gaussian splatting for generative AI applications, such as 3D avatar generation. 1/2

Gordon Wetzstein

52,449 Aufrufe โ€ข vor 2 Jahren

Nvidia presents Edify 3D! The method can generate high-quality 3D assets from text descriptions. It uses a diffusion model to create detailed quad-mesh topologies and high-resolution textures in under 2 minutes.
0:43

Nvidia presents Edify 3D! The method can generate high-quality 3D assets from text descriptions. It uses a diffusion model to create detailed quad-mesh topologies and high-resolution textures in under 2 minutes.

Dreaming Tulpa ๐Ÿฅ“๐Ÿ‘‘

39,338 Aufrufe โ€ข vor 1 Jahr

๐Ÿ“ฃ New research from GenAI at Meta, introducing Meta 3D Gen: A new system for end-to-end generation of 3D assets from text in <1min. Meta 3D Gen is a new combined AI system that can generate high-quality 3D assets, with both high-resolution textures and material maps end-to-end, producing results that are superior to existing solutions โ€” at 3-10x the speed of existing work in this space. Details in the technical report โžก๏ธ
2:44

๐Ÿ“ฃ New research from GenAI at Meta, introducing Meta 3D Gen: A new system for end-to-end generation of 3D assets from text in <1min. Meta 3D Gen is a new combined AI system that can generate high-quality 3D assets, with both high-resolution textures and material maps end-to-end, producing results that are superior to existing solutions โ€” at 3-10x the speed of existing work in this space. Details in the technical report โžก๏ธ

AI at Meta

408,708 Aufrufe โ€ข vor 1 Jahr

Microsoft just dropped TRELLIS.2 This AI turns image into photoreal-ish 3D with full PBR Now with higher definition and hyper realism Code + live demo below ๐Ÿ‘‡
0:52

Microsoft just dropped TRELLIS.2 This AI turns image into photoreal-ish 3D with full PBR Now with higher definition and hyper realism Code + live demo below ๐Ÿ‘‡

Min Choi

103,328 Aufrufe โ€ข vor 6 Monaten

2/ 3D world-building with NVIDIA NVIDIA used Edify AI to create a detailed 3D desert in minutes during a live demo Edify 3D generates editable 3D meshes from text or image prompts
0:52

2/ 3D world-building with NVIDIA NVIDIA used Edify AI to create a detailed 3D desert in minutes during a live demo Edify 3D generates editable 3D meshes from text or image prompts

Poonam Soni

107,014 Aufrufe โ€ข vor 1 Jahr

Breaking news ๐Ÿšจ: A Brand New AI Service on OctaSpace ( yes another one โ˜๏ธ ) Hunyuan3D 2.0 Advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets using AI. Generate high quality 3D assets with textures which you can then import into 3D tools.
0:44

Breaking news ๐Ÿšจ: A Brand New AI Service on OctaSpace ( yes another one โ˜๏ธ ) Hunyuan3D 2.0 Advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets using AI. Generate high quality 3D assets with textures which you can then import into 3D tools.

OctaSpace

15,495 Aufrufe โ€ข vor 1 Jahr

โšก๏ธ Introducing Bolt3D โšก๏ธ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that *directly* generates 3D Gaussians of seen and unseen regions, without any test time optimization. ๐Ÿงต๐Ÿ‘‡ (1/9)
0:20

โšก๏ธ Introducing Bolt3D โšก๏ธ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that *directly* generates 3D Gaussians of seen and unseen regions, without any test time optimization. ๐Ÿงต๐Ÿ‘‡ (1/9)

Stan Szymanowicz

125,828 Aufrufe โ€ข vor 1 Jahr

An AVATAR program developed with UE5 that supports connecting to AI motion capture for real-time, high-quality UE animation output. It features a highly flexible character customization system and rich clothing and accessory assets. You can upload images to generate 3D models and quickly obtain high-quality 3D model assets.
1:52

An AVATAR program developed with UE5 that supports connecting to AI motion capture for real-time, high-quality UE animation output. It features a highly flexible character customization system and rich clothing and accessory assets. You can upload images to generate 3D models and quickly obtain high-quality 3D model assets.

CYANPUPPETS

11,542 Aufrufe โ€ข vor 4 Monaten

Introducing the Mint 3D asset pack generator. Generate 20 high quality 3D assets from one prompt!
0:56

Introducing the Mint 3D asset pack generator. Generate 20 high quality 3D assets from one prompt!

tamrat

369,508 Aufrufe โ€ข vor 5 Tagen

#SIGGRAPH2024 ๐Ÿ†Best Paper Honorable Mentioned Introducing the magic behind #Rodin ( CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets (1/n) CLAY is 3D #stablediffusion + #ControlNet + #LoRA.
4:18

#SIGGRAPH2024 ๐Ÿ†Best Paper Honorable Mentioned Introducing the magic behind #Rodin ( CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets (1/n) CLAY is 3D #stablediffusion + #ControlNet + #LoRA.

Deemos

30,855 Aufrufe โ€ข vor 2 Jahren

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.
1:19

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 ๐Ÿฅ“๐Ÿ‘‘

79,593 Aufrufe โ€ข vor 2 Jahren