Загрузка видео...

Не удалось загрузить видео

На главную

MoGe‑3 is now available in ComfyUI. fine-detail monocular 3D geometry from open-domain images recovers metric point/depth/normal maps + FOV in one pass

wildmindai's profile picture

Wildminder

11,531 subscribers

14,956 просмотров • 6 дней назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 4

Фото профиля Elise Tech Ai
Elise Tech Ai6 дней назад

MoGe-3 in ComfyUI is huge metric depth + normals + FOV in one pass from a single image wild

Фото профиля Sophia AI & Tool Expert
Sophia AI & Tool Expert5 дней назад

Incredible metric 3D geometry from a single image in one pass MoGe 3 in ComfyUI is huge

Фото профиля Alice The Ai Expert
Alice The Ai Expert6 дней назад

MoGe 3 in ComfyUI is huge one pass metric 3D from a single image is so good!

Фото профиля Evia AI
Evia AI5 дней назад

Single pass 3D reconstruction makes detailed geometry workflows much easier

Похожие видео

Good. ComfyUI just got native MoGe support - 3D geometry from monocular images.
0:35

Good. ComfyUI just got native MoGe support - 3D geometry from monocular images.

Wildminder

16,196 просмотров • 4 месяцев назад

Sweet! Marigold V2 is in ComfyUI now. turns regular 2D images into ultra-detailed 3D depth maps. - individual hairs, animal fur, thin foliage - handles surface normals/material properties in a single step - super fast
1:00

Sweet! Marigold V2 is in ComfyUI now. turns regular 2D images into ultra-detailed 3D depth maps. - individual hairs, animal fur, thin foliage - handles surface normals/material properties in a single step - super fast

Wildminder

31,442 просмотров • 12 дней назад

Qwen-Image-2.1 is now supported in ComfyUI! Open weights. One 7B checkpoint that generates and edits. → Image generation at native 2K → Instruction editing from up to 10 reference images in a single pass → RGBA output, alpha included
0:36

Qwen-Image-2.1 is now supported in ComfyUI! Open weights. One 7B checkpoint that generates and edits. → Image generation at native 2K → Instruction editing from up to 10 reference images in a single pass → RGBA output, alpha included

ComfyUI

183,372 просмотров • 3 дней назад

TikTok presents Depth Anything Unleashing the Power of Large-Scale Unlabeled Data paper page: demo: Depth Anything is trained on 1.5M labeled images and 62M+ unlabeled images jointly, providing the most capable Monocular Depth Estimation (MDE) foundation models with the following features: zero-shot relative depth estimation, better than MiDaS v3.1 (BEiTL-512) zero-shot metric depth estimation, better than ZoeDepth optimal in-domain fine-tuning and evaluation on NYUv2 and KITTI
0:44

TikTok presents Depth Anything Unleashing the Power of Large-Scale Unlabeled Data paper page: demo: Depth Anything is trained on 1.5M labeled images and 62M+ unlabeled images jointly, providing the most capable Monocular Depth Estimation (MDE) foundation models with the following features: zero-shot relative depth estimation, better than MiDaS v3.1 (BEiTL-512) zero-shot metric depth estimation, better than ZoeDepth optimal in-domain fine-tuning and evaluation on NYUv2 and KITTI

AK

600,186 просмотров • 2 лет назад

Meet MapAnything – a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art results 🚀 One universal model enables SoTA for: 🔥 Mono Depth Estimation 🔥 Multi-View SfM 🔥 Multi-View Stereo 🔥 Depth Completion 🔥 Registration … and many more possibilities! – plus everything is metric 🎯 We release code for data processing, training, benchmarking & ablations – everything Apache 2.0! Details & Links 👇
1:30

Meet MapAnything – a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art results 🚀 One universal model enables SoTA for: 🔥 Mono Depth Estimation 🔥 Multi-View SfM 🔥 Multi-View Stereo 🔥 Depth Completion 🔥 Registration … and many more possibilities! – plus everything is metric 🎯 We release code for data processing, training, benchmarking & ablations – everything Apache 2.0! Details & Links 👇

Nikhil Keetha

123,517 просмотров • 1 год назад

Hunyuan 3D 3.0 is now available in ComfyUI via Partner Nodes! We are bringing more models & tools into ComfyUI, starting with state-of-the-art asset generation from text, images, or sketches. Coming soon in ComfyUI: - texture editing - semantic UV unwrapping - intelligent 3D part decomposition The goal isn’t to replace 3D artists. It’s to remove the non-creative friction so real creative moments can happen faster.
0:29

Hunyuan 3D 3.0 is now available in ComfyUI via Partner Nodes! We are bringing more models & tools into ComfyUI, starting with state-of-the-art asset generation from text, images, or sketches. Coming soon in ComfyUI: - texture editing - semantic UV unwrapping - intelligent 3D part decomposition The goal isn’t to replace 3D artists. It’s to remove the non-creative friction so real creative moments can happen faster.

ComfyUI

126,836 просмотров • 7 месяцев назад

After a year of team work, we're thrilled to introduce Depth Anything 3 (DA3)! 🚀 Aiming for human-like spatial perception, DA3 extends monocular depth estimation to any-view scenarios, including single images, multi-view images, and video. In pursuit of minimal modeling, DA3 reveals two key insights: 💎 A plain transformer (e.g., vanilla DINO) is enough. No specialized architecture. ✨ A single depth-ray representation is enough. No complex 3D tasks. Three series of models have been released: the main DA3 series, a monocular metric estimation series, and a monocular depth estimation series. The core team members, aside from me: Haotong Lin, Sili Chen, Jun Hao Liew, Donny Y. Chen. 👇(1/n) #DepthAnything3
0:32

After a year of team work, we're thrilled to introduce Depth Anything 3 (DA3)! 🚀 Aiming for human-like spatial perception, DA3 extends monocular depth estimation to any-view scenarios, including single images, multi-view images, and video. In pursuit of minimal modeling, DA3 reveals two key insights: 💎 A plain transformer (e.g., vanilla DINO) is enough. No specialized architecture. ✨ A single depth-ray representation is enough. No complex 3D tasks. Three series of models have been released: the main DA3 series, a monocular metric estimation series, and a monocular depth estimation series. The core team members, aside from me: Haotong Lin, Sili Chen, Jun Hao Liew, Donny Y. Chen. 👇(1/n) #DepthAnything3

Bingyi Kang

516,072 просмотров • 10 месяцев назад

The wait is over 📢 MAST3R is out! DUSt3R+ dense local feature maps & metric depth - 1st in #MapFreeReloc leaderboard, can handle 1000s of images 😀 !! Blog: Code: Paper:
0:55

The wait is over 📢 MAST3R is out! DUSt3R+ dense local feature maps & metric depth - 1st in #MapFreeReloc leaderboard, can handle 1000s of images 😀 !! Blog: Code: Paper:

NAVER LABS Europe

31,001 просмотров • 2 лет назад

MiniMax H3 is open weights and native in ComfyUI. MiniMax (official) H3 has text, images, video, and audio in one model, video and stereo audio out in a single pass, running locally or on Comfy Cloud. To try this workflow, link below 👇
0:43

MiniMax H3 is open weights and native in ComfyUI. MiniMax (official) H3 has text, images, video, and audio in one model, video and stereo audio out in a single pass, running locally or on Comfy Cloud. To try this workflow, link below 👇

ComfyUI

12,740 просмотров • 1 месяц назад

"YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting" TL;DR: a unified 3D Gaussian splatting model that reconstructs high-quality scene geometry and camera poses from unposed/uncalibrated images in a single forward pass.
0:38

"YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting" TL;DR: a unified 3D Gaussian splatting model that reconstructs high-quality scene geometry and camera poses from unposed/uncalibrated images in a single forward pass.

Alexandre Morgand

15,035 просмотров • 7 месяцев назад

Recraft V4 Styles is now available in ComfyUI. Build a reusable style from 1–10 reference images, then hold that style across every generation - texture, composition, and rendering, not just the overall look.
0:20

Recraft V4 Styles is now available in ComfyUI. Build a reusable style from 1–10 reference images, then hold that style across every generation - texture, composition, and rendering, not just the overall look.

ComfyUI

12,507 просмотров • 21 дней назад

I love open source AI in ComfyUI because it lets me control every step. For this spaceship shot I tracked the camera, designed layout geometry in Blender, exported depth maps, prompted the final look with an AI image editor, and jumped into Photoshop to clean it all up.
0:39

I love open source AI in ComfyUI because it lets me control every step. For this spaceship shot I tracked the camera, designed layout geometry in Blender, exported depth maps, prompted the final look with an AI image editor, and jumped into Photoshop to clean it all up.

Mickmumpitz

47,986 просмотров • 5 месяцев назад

ComfyUI 3D Node Improvements 03/18 (Multi-layer Output) Recently, I've made several changes and improvements to Load3D: 1. Support for simultaneous output of multiple layers - original, mask, normal maps, lineart 2. Performance improvements - rendering only occurs when the mouse is over the node 3. UI changes - using menus to manage the buttons in the top left corner 4. UI changes - temporarily removed depth mode from material options 5. Many backend code changes. #ComfyUI
1:03

ComfyUI 3D Node Improvements 03/18 (Multi-layer Output) Recently, I've made several changes and improvements to Load3D: 1. Support for simultaneous output of multiple layers - original, mask, normal maps, lineart 2. Performance improvements - rendering only occurs when the mouse is over the node 3. UI changes - using menus to manage the buttons in the top left corner 4. UI changes - temporarily removed depth mode from material options 5. Many backend code changes. #ComfyUI

jtydhr88

17,581 просмотров • 1 год назад

Now available: Mesh Baker! The newest addition to the @needletools fam. 🥐 heavy 3D → ready for prod 🥞 one click, few seconds 🍥 bakes normal maps, AO, ... 🧁 100% local, on the web, powered by Three.js Learn more in 🧵! highpoly→lowpoly workflow, normal maps, baking, ...
1:09

Now available: Mesh Baker! The newest addition to the @needletools fam. 🥐 heavy 3D → ready for prod 🥞 one click, few seconds 🍥 bakes normal maps, AO, ... 🧁 100% local, on the web, powered by Three.js Learn more in 🧵! highpoly→lowpoly workflow, normal maps, baking, ...

herbst

21,531 просмотров • 26 дней назад

Depth is starting to feel less like an image… and more like geometry. InfiniDepth (open source) pushes exactly in that direction🤩 Depth is no longer just a map. It’s becoming a geometry representation. Single image → depth → 3DGS🥳 It’s not replacing real-world capture, but it’s definitely changing how image-to-3D works.
0:25

Depth is starting to feel less like an image… and more like geometry. InfiniDepth (open source) pushes exactly in that direction🤩 Depth is no longer just a map. It’s becoming a geometry representation. Single image → depth → 3DGS🥳 It’s not replacing real-world capture, but it’s definitely changing how image-to-3D works.

KIRI Engine - 3D Scanner App

26,777 просмотров • 6 месяцев назад

HY 3D advanced features are now available in ComfyUI. This update brings production-ready 3D post-processing from Tencent Hy, which is closer to the same workflow. - 3D Parts Decomposition: split assets into editable components - UV Unwrapping: prepare models for texturing faster - Smart Topology: generate cleaner, production-friendly meshes
0:28

HY 3D advanced features are now available in ComfyUI. This update brings production-ready 3D post-processing from Tencent Hy, which is closer to the same workflow. - 3D Parts Decomposition: split assets into editable components - UV Unwrapping: prepare models for texturing faster - Smart Topology: generate cleaner, production-friendly meshes

ComfyUI

58,851 просмотров • 6 месяцев назад

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.
0:40

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.

Joseph Azar

14,041 просмотров • 4 месяцев назад

LTX-2 is natively supported in ComfyUI on Day 0 🎬🔊 The next chapter in controllability for open-source video generation. - Open-source audio-video foundation model - Generates motion, dialogue, SFX, and music together - Canny, Depth & Pose video-to-video control - Keyframe-driven generation - Native upscaling and prompt enhancement Everything in a single pass.
0:36

LTX-2 is natively supported in ComfyUI on Day 0 🎬🔊 The next chapter in controllability for open-source video generation. - Open-source audio-video foundation model - Generates motion, dialogue, SFX, and music together - Canny, Depth & Pose video-to-video control - Keyframe-driven generation - Native upscaling and prompt enhancement Everything in a single pass.

ComfyUI

108,422 просмотров • 8 месяцев назад