Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Using Uni-1 by Luma to create consistent and correct PBR/Normal/Displacement map, combining with triplanar/image projections to boost asset creation speed while maintaining quality. Made by: Tony Hou

Luma | Dream Lab

3,462 subscribers

26,356 views • 7 months ago •via X (Twitter)

Arts Science & Technology

Anya Rossi• Live Now

Private livecam show

2 Comments

Stefan_Laub7 months ago

@LumaLabsAI @TonyHouart @mrjonfinger I think the mean the teyture set is made by Ai to be used in the model.

JUST CRE8 Productions | AI Creative Filmmaker7 months ago

@LumaLabsAI @TonyHouart @mrjonfinger Looks awesome

Related Videos

📢 IntrinsiX: High-Quality PBR Generation using Image Priors 📢 From text input, we generate renderable PBR maps! Next to editable image generation, our predictions can be distilled into room-scale scenes using SDS for large-scale PBR texture generation. We first train separate LoRA modules for the intrinsic properties of albedo, rough/metal, normal. Then, we introduce cross-intrinsic attention using a rerendering loss with importance-weighted light sampling to enable coherent PBR generation. Our method outperforms text -> image -> PBR methods both in generalization and quality, since directly generating PBR maps does not suffer from the inherent ambiguity of intrinsic image decomposition. In addition, our design choice facilitates SDS-based PBR texture distillation. 🌍 🎥 Great work by Peter Kocsis, Lukas Höllein

📢 IntrinsiX: High-Quality PBR Generation using Image Priors 📢 From text input, we generate renderable PBR maps! Next to editable image generation, our predictions can be distilled into room-scale scenes using SDS for large-scale PBR texture generation. We first train separate LoRA modules for the intrinsic properties of albedo, rough/metal, normal. Then, we introduce cross-intrinsic attention using a rerendering loss with importance-weighted light sampling to enable coherent PBR generation. Our method outperforms text -> image -> PBR methods both in generalization and quality, since directly generating PBR maps does not suffer from the inherent ambiguity of intrinsic image decomposition. In addition, our design choice facilitates SDS-based PBR texture distillation. 🌍 🎥 Great work by Peter Kocsis, Lukas Höllein

Matthias Niessner

21,957 views • 1 year ago

SHEIN has built 170+ tools to speed up clothing production and ensure consistent quality. Now, innovative tools make it faster and cheaper to create the glam dresses you love, streamlining the process while maintaining style and accessibility.

SHEIN has built 170+ tools to speed up clothing production and ensure consistent quality. Now, innovative tools make it faster and cheaper to create the glam dresses you love, streamlining the process while maintaining style and accessibility.

SHEIN

4,675,972 views • 1 year ago

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 views • 2 years ago

AI image creation just changed. Not better prompts better thinking. Uni-1 doesn’t just generate… it understands, plans, and executes. Sketch → photoreal Idea → cinematic frame Concept → full composition This isn’t text-to-image anymore. It’s reasoning-to-image. #Uni1 #AIArt #Luma

AI image creation just changed. Not better prompts better thinking. Uni-1 doesn’t just generate… it understands, plans, and executes. Sketch → photoreal Idea → cinematic frame Concept → full composition This isn’t text-to-image anymore. It’s reasoning-to-image. #Uni1 #AIArt #Luma

Darshal Jaitwar

69,227 views • 7 months ago

Turn a single image into a 3D world you can explore with Lyra 2.0. By combining video generation with 3D reconstruction, our researchers create environments along a camera path you choose. Lyra draws on earlier views and learns to correct accumulating visual errors, helping the world stay consistent as you explore and return to familiar places. Paper, code, and demos:

Turn a single image into a 3D world you can explore with Lyra 2.0. By combining video generation with 3D reconstruction, our researchers create environments along a camera path you choose. Lyra draws on earlier views and learns to correct accumulating visual errors, helping the world stay consistent as you explore and return to familiar places. Paper, code, and demos:

NVIDIA AI

80,256 views • 4 days ago

Using Modular Assets? You can boost performance by combining meshes with Mesh.CombineMeshes()! 🧱💡🚀 #UnityTips #unity3d

Using Modular Assets? You can boost performance by combining meshes with Mesh.CombineMeshes()! 🧱💡🚀 #UnityTips #unity3d

Sunny Valley Studio

21,258 views • 2 years ago

I asked the Rive agent if it could create something like AE's CC Sphere effect. Close, this lets you map an image by asset name to a sphere.

I asked the Rive agent if it could create something like AE's CC Sphere effect. Close, this lets you map an image by asset name to a sphere.

Drawsgood

11,002 views • 9 months ago

Get spatial and character consistency by combining AI with 3D. Learn to create your avatar and generate quality clips with built-in prompts and tools, in this thread 🧵👇

TechHalla

47,213 views • 1 year ago

Made this video (🎶) with a Midjourney v6 image! Started by upscaling/refining with Magnific.ai, pulled a Marigold Depth Map from that in ComfyUI, then used as a displacement map in Blender where I animated this camera pass with some relighting and narrow depth of field.🧵1/12

Made this video (🎶) with a Midjourney v6 image! Started by upscaling/refining with Magnific.ai, pulled a Marigold Depth Map from that in ComfyUI, then used as a displacement map in Blender where I animated this camera pass with some relighting and narrow depth of field.🧵1/12

CoffeeVectors

135,823 views • 2 years ago

PolyPlanar is a triplanar tool at the shading level. No UV unwrapping of any kind needed. Built-in scatter with displacement support. PBR friendly, smooth blending (no seams to hunt) and after all it is animation ready! #b3d

PolyPlanar is a triplanar tool at the shading level. No UV unwrapping of any kind needed. Built-in scatter with displacement support. PBR friendly, smooth blending (no seams to hunt) and after all it is animation ready! #b3d

Cosmo Mídias 🔶

13,070 views • 3 months ago

You can now generate PBR materials within Omma using the /material command. - Diffuse - Normal - Height (for displacement) - Roughness

You can now generate PBR materials within Omma using the /material command. - Diffuse - Normal - Height (for displacement) - Roughness

Omma AI

35,019 views • 7 months ago

Signed Drum Skin & Sticks Ltd Set Limited to 50 hand made by Oasis drummer Tony McCarroll. Embossed with a high-quality image of my drumkit used during our initial formation and 'Definitely Maybe' years.

Signed Drum Skin & Sticks Ltd Set Limited to 50 hand made by Oasis drummer Tony McCarroll. Embossed with a high-quality image of my drumkit used during our initial formation and 'Definitely Maybe' years.

Tony McCarroll

52,957 views • 1 year ago

Made with Depth Scanner by @ActionMovieKid Get Depth Scanner #aescripts #aftereffects #depthscanner Used Depth Scanner to create a displacement map - the latest update has the best temporal coherence they’ve had so far with this plug-in

Made with Depth Scanner by @ActionMovieKid Get Depth Scanner #aescripts #aftereffects #depthscanner Used Depth Scanner to create a displacement map - the latest update has the best temporal coherence they’ve had so far with this plug-in

aescripts+aeplugins

66,885 views • 3 years ago

Layers is now live in Luma Agents. Ask the agent to extract layers from any image - generated in Luma or uploaded. Then keep chatting: swap the product, restyle the background, rewrite the headline. Change one element. Preserve everything else. Powered by Uni-1.

Layers is now live in Luma Agents. Ask the agent to extract layers from any image - generated in Luma or uploaded. Then keep chatting: swap the product, restyle the background, rewrite the headline. Change one element. Preserve everything else. Powered by Uni-1.

Luma

24,901 views • 3 months ago

I'm thrilled to officially annouce🤩 📢 Automatic PBR : Image-to-material (I2M) 👉Textured Mesh in > Full PBR Mesh out Our latest foundation model for enriching existing 3D assets with the full array of PBR materials, whilst maintaining the same mesh geometry and UV unwrap. 🧵A thread : 1 of 7 👇 #I2M #PBR #CV #Marso #texturing #gamedev #computervision M-XR

I'm thrilled to officially annouce🤩 📢 Automatic PBR : Image-to-material (I2M) 👉Textured Mesh in > Full PBR Mesh out Our latest foundation model for enriching existing 3D assets with the full array of PBR materials, whilst maintaining the same mesh geometry and UV unwrap. 🧵A thread : 1 of 7 👇 #I2M #PBR #CV #Marso #texturing #gamedev #computervision M-XR

Elliott Round

36,845 views • 6 months ago

AI video creation just changed forever. One image, one prompt, and you're directing a full cinematic sequence. I used 2 tools to create this short film with consistent characters, style, and emotion. Here’s exactly how I did it, step by step Bookmarked this for later 🔖

AI video creation just changed forever. One image, one prompt, and you're directing a full cinematic sequence. I used 2 tools to create this short film with consistent characters, style, and emotion. Here’s exactly how I did it, step by step Bookmarked this for later 🔖

Amira Zairi

1,585,572 views • 1 year ago

Seedance 2.5 has landed on Luma. 🚀 Create up to 30 seconds of multi-shot video, high-definition in a single generation using up to 50 references (text, image, video, and audio). With Luma Agents, you can control scenes, camera angles, and pacing to produce your next masterpiece.

Seedance 2.5 has landed on Luma. 🚀 Create up to 30 seconds of multi-shot video, high-definition in a single generation using up to 50 references (text, image, video, and audio). With Luma Agents, you can control scenes, camera angles, and pacing to produce your next masterpiece.

Luma

26,457 views • 3 months ago

Another episode of the Godot PBR Mastery Series is out! Learn how to optimize 5 textures down to just 2, using Channel Packing! You can easily optimize textures by combining them using channel packing, reducing GPU and storage overhead. Full video in comments!

Another episode of the Godot PBR Mastery Series is out! Learn how to optimize 5 textures down to just 2, using Channel Packing! You can easily optimize textures by combining them using channel packing, reducing GPU and storage overhead. Full video in comments!

Foyezes

11,931 views • 7 months ago