正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Meet Idol, an open image-to-3D model. A 3D-DiT that generates complete 3D objects from just an image. Pre-trained from scratch, contains only 600M parameters, it runs on consumer GPUs, using less than 7.2 GB of VRAM and can generate 1M splats in 3 seconds. Try it today. Fully open:... show more

Speridlabs

2,250 subscribers

221,584 次观看 • 7 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

37 条评论

Speridlabs 的头像

Speridlabs7 天前

Weights: Code: Try it:

Alex Garabito 的头像

Alex Garabito7 天前

here is my humble contribution

Speridlabs 的头像

Speridlabs7 天前

we pay researchers to do this

Javier Álvarez 的头像

Javier Álvarez7 天前

good job team! this is fine, from every angle 🔥

Guli Moreno 的头像

Guli Moreno7 天前

@martin_casado a nice combo for Radix? Made in 🇪🇸

Joan Rodriguez 的头像

Joan Rodriguez7 天前

This is sick! Congrats @chema_garabito and team

Studio Foxtales 🦊 的头像

Studio Foxtales 🦊7 天前

>3D objects >outputs splats :(

Carlos Bort 的头像

Carlos Bort7 天前

This is absolutely incredible! Congrats team!

Neil 的头像

Neil7 天前

If you'd like more control in your image-to-3D generations check out our work:

guille 的头像

guille7 天前

No recuerdo ya que modelo salió en 2023 imagen a 3d que generé con stable diffusion una imagen de un delorean por delante, se la pasé al modelo y me generó bien los faros de atrás, y eso me voló la cabeza. Desde entonces mi benchmark favorito es usar a tigershark (un Invizimal jajaja) que no debe salir en datos de entrenamiento entonces ocurren bizarradas curiosas. Es una pasada, habéis cocinado algo chulísimo, enhorabuena!

Hao 的头像

Hao7 天前

The backpack example is worth spinning around. The back panel and shoulder straps hold up well. Local GPU note from your README 4090 - 19.1s at 262k Gaussians / 50 steps

Marc 的头像

Marc7 天前

👏👏👏

Gonzalo Duarte 的头像

Gonzalo Duarte7 天前

Guapísimo! Go Team!!

Fernando 的头像

Fernando7 天前

So cool!

Ale Sánchez 的头像

Ale Sánchez7 天前

Equipazo 🤘🏻🤘🏻🤘🏻

txema puch 的头像

txema puch7 天前

Wow crackss!

JoseJavier 的头像

JoseJavier7 天前

Qué barbaridad 😲👏👏

Crio Songo 的头像

Crio Songo7 天前

The speed and parameter size are really impressive. Full openness also makes it easy to test and improve.

Gravity Research 的头像

Gravity Research7 天前

Apache 2.0 and running local on a single consumer card is huge, now the whole game is just how clean those splats convert to usable meshes.

Louan 的头像

Louan7 天前

Enhorabuena equipo! Orgulloso del talento 🇪🇸

Ottis 的头像

Ottis6 天前

pretty wild! 3DGS will be massive in the tech industry in the near future

Yoland Yan 的头像

Yoland Yan7 天前

Woah!

Farfan 的头像

Farfan6 天前

Does it work with a 3070 ti on 8 gb vram ?

Speridlabs 的头像

Speridlabs6 天前

it should!

Javier Gil Avilés 的头像

Javier Gil Avilés7 天前

Idolo 🇪🇸🐐

Alejandro Buján 的头像

Alejandro Buján7 天前

absolute 🐐s

leal 的头像

leal7 天前

vamos vamos vamos!! 🔥🇪🇸

Igna 的头像

Igna7 天前

Hell yeah!

Sabab 的头像

Sabab7 天前

G. O. A. T

alena titova 的头像

alena titova7 天前

wow !!

￦的头像

￦7 天前

wow

Christopher Sims 的头像

Christopher Sims7 天前

you guys cooked, amazing!

FutureMind Ai 的头像

FutureMind Ai7 天前

Impressive results with such low VRAM usage. Open 3D AI tools like Idol are a big win for creators.

lost in latency 的头像

lost in latency7 天前

damn, excited for this!

Carlos Martínez García-Villarrubia 的头像

Carlos Martínez García-Villarrubia7 天前

Muy muy top!

Gilberto S 的头像

Gilberto S7 天前

🇪🇸🇪🇸🇪🇸

Ivan Fioravanti 的头像

Ivan Fioravanti6 天前

Incredible release!!! Gonna test it with something complex later! Congrats!

相关视频

Meet Iris-3B: a pixel-space T2I model and general vision learner that generates every pixel directly. No VAE. Pre-trained from scratch, 3B, open weights. We also explore its generative prior on detail-critical vision tasks: depth estimation and image restoration. Fully open: weights, code and demo (Apache 2.0)

Meet Iris-3B: a pixel-space T2I model and general vision learner that generates every pixel directly. No VAE. Pre-trained from scratch, 3B, open weights. We also explore its generative prior on detail-critical vision tasks: depth estimation and image restoration. Fully open: weights, code and demo (Apache 2.0)

Speridlabs

109,831 次观看 • 28 天前

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 次观看 • 3 年前

I'm making an open-ended coding game/toy about using code to generate 3D objects. Does this explain it?

I'm making an open-ended coding game/toy about using code to generate 3D objects. Does this explain it?

Walaber

35,635 次观看 • 1 年前

Generate 3D from just one image, on your computer. franzipol has built a gradio web ui for Apple's Sharp, which infers an entire 3D view from just one image. You can run it on any computer with 1-click: Mac, Linux, Windows. Just need 10GB VRAM (16GB memory on Macs).

Generate 3D from just one image, on your computer. franzipol has built a gradio web ui for Apple's Sharp, which infers an entire 3D view from just one image. You can run it on any computer with 1-click: Mac, Linux, Windows. Just need 10GB VRAM (16GB memory on Macs).

cocktail peanut

157,863 次观看 • 10 个月前

Fibo 2.0 is live: the #1 open-weights image editing model on Artificial Analysis. Ahead of 33 closed models from leading labs, and trained only on licensed data. Try it in Bria Create:

Fibo 2.0 is live: the #1 open-weights image editing model on Artificial Analysis. Ahead of 33 closed models from leading labs, and trained only on licensed data. Try it in Bria Create:

BRIA AI

18,899 次观看 • 16 天前

🚨 A single image → a fully editable UE5 world. Introducing Lumera: a turnkey pipeline that reconstructs an engine-native 3D scene directly from ONE image — not just pixels, point clouds, or Gaussians. It gives you: → object-level 3D meshes → editable 3D layouts → engine-native lights → HDR environment lighting → a scene ready for Unreal Engine 5 In other words: Image → 3D world → UE5. We believe the future of image-to-3D is not “generate something that looks 3D.” It is generate the actual world project. 🌐 📄

🚨 A single image → a fully editable UE5 world. Introducing Lumera: a turnkey pipeline that reconstructs an engine-native 3D scene directly from ONE image — not just pixels, point clouds, or Gaussians. It gives you: → object-level 3D meshes → editable 3D layouts → engine-native lights → HDR environment lighting → a scene ready for Unreal Engine 5 In other words: Image → 3D world → UE5. We believe the future of image-to-3D is not “generate something that looks 3D.” It is generate the actual world project. 🌐 📄

Hao Zhao

52,734 次观看 • 2 个月前

🚀 Hunyuan 3D 2.1 is here! The first fully open-source, production-ready PBR 3D generative model! ✅Cinema-grade visuals: PBR material synthesis brings leather, bronze, and more to life with stunning light interactions. ✅ Fully open-source: Model weights, training/inference code, data pipelines, and architecture—yours to fine-tune! ✅ Runs on consumer GPUs, empowering creators, devs, and small teams. Be the first to shape the future of 3D! Download now and build something epic. Model: Demo: Github: Hunyuan 3D Creation Engine: #Hunyuan3D #OpenSource #3DCreation

🚀 Hunyuan 3D 2.1 is here! The first fully open-source, production-ready PBR 3D generative model! ✅Cinema-grade visuals: PBR material synthesis brings leather, bronze, and more to life with stunning light interactions. ✅ Fully open-source: Model weights, training/inference code, data pipelines, and architecture—yours to fine-tune! ✅ Runs on consumer GPUs, empowering creators, devs, and small teams. Be the first to shape the future of 3D! Download now and build something epic. Model: Demo: Github: Hunyuan 3D Creation Engine: #Hunyuan3D #OpenSource #3DCreation

Tencent Hy

236,506 次观看 • 1 年前

3DTopia-XL High-Quality 3D PBR Asset Generation via Primitive Diffusion demo: model: 3DTopia-XL scales high-quality 3D asset generation using Diffusion Transformer (DiT) built upon an expressive and efficient 3D representation, PrimX. The denoising process takes 5 seconds to generate a 3D PBR asset from text/image input which is ready for the graphics pipeline to use.

3DTopia-XL High-Quality 3D PBR Asset Generation via Primitive Diffusion demo: model: 3DTopia-XL scales high-quality 3D asset generation using Diffusion Transformer (DiT) built upon an expressive and efficient 3D representation, PrimX. The denoising process takes 5 seconds to generate a 3D PBR asset from text/image input which is ready for the graphics pipeline to use.

AK

87,282 次观看 • 2 年前

Claude Fable 5 built a 3D product website with Claude Code Generate an image of a product with the Magnific MCP, and convert it into a 3D model. Download that model and give it to Fable 5 to develop an interactive page with. Here's the final result + prompts:

Claude Fable 5 built a 3D product website with Claude Code Generate an image of a product with the Magnific MCP, and convert it into a 3D model. Download that model and give it to Fable 5 to develop an interactive page with. Here's the final result + prompts:

Jerrod Lew

33,687 次观看 • 4 个月前

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

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 🥓👑

21,853 次观看 • 1 年前

RIP to everyone who spent years learning 3D in Blender 💀 Hi3D just released an open-source model that turns any object from a photo into a full 3D model. It's trained on 2 million 3D assets, and in their technical report 90% of its models pass 3D-print slicing. Just generate the base from a photo, refine the details with Opus 5.5 and you're done. The barrier to 3D just disappeared, you can find more details in the article below:

RIP to everyone who spent years learning 3D in Blender 💀 Hi3D just released an open-source model that turns any object from a photo into a full 3D model. It's trained on 2 million 3D assets, and in their technical report 90% of its models pass 3D-print slicing. Just generate the base from a photo, refine the details with Opus 5.5 and you're done. The barrier to 3D just disappeared, you can find more details in the article below:

Anatoli Kopadze

225,941 次观看 • 9 天前

Genie3 generates videos. We generate 𝟯𝗗 𝘄𝗼𝗿𝗹𝗱𝘀 you can actually use. Launching tomorrow — Tencent #HYWorld 2.0, an engine-ready World Model🚀 This isn't a video. It's a real 3D scene, all generated & editable. One image in. A whole 3D world out. 🔥Open-source tomorrow

Genie3 generates videos. We generate 𝟯𝗗 𝘄𝗼𝗿𝗹𝗱𝘀 you can actually use. Launching tomorrow — Tencent #HYWorld 2.0, an engine-ready World Model🚀 This isn't a video. It's a real 3D scene, all generated & editable. One image in. A whole 3D world out. 🔥Open-source tomorrow

Tengfei Wang

553,274 次观看 • 6 个月前

What if we can simulate an *interactive 3D world*, from a single image, in the wild, in real time? Introducing PointWorld-1B: a large pre-trained 3D world model that predicts env dynamics given RGB-D capture and robot actions. 🌐 from Stanford University NVIDIA

What if we can simulate an interactive 3D world, from a single image, in the wild, in real time? Introducing PointWorld-1B: a large pre-trained 3D world model that predicts env dynamics given RGB-D capture and robot actions. 🌐 from Stanford University NVIDIA

Wenlong Huang

280,325 次观看 • 10 个月前

Stable Diffusion generates beautiful images, but can it be used for open-world recognition? Try Demo! Our #CVPR2023 paper shows that the pre-trained diffusion model indeed is a good image parser, allows for open-vocabulary segmentation and detection.

Stable Diffusion generates beautiful images, but can it be used for open-world recognition? Try Demo! Our #CVPR2023 paper shows that the pre-trained diffusion model indeed is a good image parser, allows for open-vocabulary segmentation and detection.

Xiaolong Wang

241,277 次观看 • 3 年前

This AI just turned a flat image into a fully interactive 3D world 👀 Hyper3D WorldGen converts a single image into multiple independent, physics-ready 3D assets while preserving their spatial relationships. It doesn’t just generate a 3D scene it actually understands and structures the objects inside it. Watch the breakdown:

This AI just turned a flat image into a fully interactive 3D world 👀 Hyper3D WorldGen converts a single image into multiple independent, physics-ready 3D assets while preserving their spatial relationships. It doesn’t just generate a 3D scene it actually understands and structures the objects inside it. Watch the breakdown:

Markandey Sharma

31,374 次观看 • 1 个月前

Microsoft open-sourced a 4B model that turns any image into a production-ready 3D asset in 3 seconds. It’s called TRELLIS.2, a fully textured, physically accurate 3D models with PBR textures out of the box. → Full PBR (base color, roughness, metallic, opacity) → Handles hair, cloth, glass, non-manifold geometry → Exports .glb ready for Unity/Unreal/Blender → Runs locally, ships in 3 seconds It's not a demo or a research preview. The full training codebase is public. You can fine-tune it on your own asset library and get a model that generates in your studio's exact style. 100% Open Source

Microsoft open-sourced a 4B model that turns any image into a production-ready 3D asset in 3 seconds. It’s called TRELLIS.2, a fully textured, physically accurate 3D models with PBR textures out of the box. → Full PBR (base color, roughness, metallic, opacity) → Handles hair, cloth, glass, non-manifold geometry → Exports .glb ready for Unity/Unreal/Blender → Runs locally, ships in 3 seconds It's not a demo or a research preview. The full training codebase is public. You can fine-tune it on your own asset library and get a model that generates in your studio's exact style. 100% Open Source

Superman

285,908 次观看 • 3 个月前

We're thrilled to release & open-source Hunyuan3D World Model 1.0! This model enables you to generate immersive, explorable, and interactive 3D worlds from just a sentence or an image. It's the industry's first open-source 3D world generation model, compatible with CG pipelines for full editability & simulation. Set to transform game development, VR, digital content creation and so on. Get started now👇🏻 Project Page： Try it now： Github： Hugging Face：

We're thrilled to release & open-source Hunyuan3D World Model 1.0! This model enables you to generate immersive, explorable, and interactive 3D worlds from just a sentence or an image. It's the industry's first open-source 3D world generation model, compatible with CG pipelines for full editability & simulation. Set to transform game development, VR, digital content creation and so on. Get started now👇🏻 Project Page： Try it now： Github： Hugging Face：

Tencent Hy

1,231,203 次观看 • 1 年前

2D is what the camera sees.👀 3D is what the world is. 🌍 Today, we’re proudly open-sourcing QuerySplat — an open-source feed-forward 3D model that turns a few unposed images into a navigable 3D scene in seconds (run on 4090🪶). Your input: a few unposed images Our output: a sharp, navigable 3D scene — generated in seconds! 🚀 🧠 organize scenes with 3D queries, not pixel-bound Gaussians 📷 no camera poses or manual calibration required ⚡ reconstruct new scenes in a single forward pass ✨ preserve sharp geometry and high-frequency appearance 🏆 achieve state-of-the-art results on DL3DV-Evaluation 🔓 code and model weights are now open-source From pixels to scenes, we are making 3D generation scalable. Try our free iOS app — it’s a lot of fun! 😆 🔗 Try it on the Web: 🔗 Paper: 🔗 Code & weights: 🔗 Project page: 🔗 #AIGC #3DGS #AI #Computervision #3D #artist #3dartist #3d

2D is what the camera sees.👀 3D is what the world is. 🌍 Today, we’re proudly open-sourcing QuerySplat — an open-source feed-forward 3D model that turns a few unposed images into a navigable 3D scene in seconds (run on 4090🪶). Your input: a few unposed images Our output: a sharp, navigable 3D scene — generated in seconds! 🚀 🧠 organize scenes with 3D queries, not pixel-bound Gaussians 📷 no camera poses or manual calibration required ⚡ reconstruct new scenes in a single forward pass ✨ preserve sharp geometry and high-frequency appearance 🏆 achieve state-of-the-art results on DL3DV-Evaluation 🔓 code and model weights are now open-source From pixels to scenes, we are making 3D generation scalable. Try our free iOS app — it’s a lot of fun! 😆 🔗 Try it on the Web: 🔗 Paper: 🔗 Code & weights: 🔗 Project page: 🔗 #AIGC #3DGS #AI #Computervision #3D #artist #3dartist #3d

InSpatio｜影溯

30,407 次观看 • 3 个月前