Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

I added a node to my custom node that converts the depth image to a normal map! This is useful for 2D-style images where Normals Estimation doesn't work well.

toyxyz3's profile picture

toyxyz

33,235 subscribers

117,502 Aufrufe • vor 2 Jahren •via X (Twitter)

KunstBildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

The Set Mesh Normal node has just been added to #GeometryNodes. It allows adding and modifying custom normals, opening up many new possibilities. #b3d #devfund
0:18

The Set Mesh Normal node has just been added to #GeometryNodes. It allows adding and modifying custom normals, opening up many new possibilities. #b3d #devfund

Jacques Lucke

142,126 Aufrufe • vor 1 Jahr

Fun & likely unintended use case for #NanoBananaPro: image→3D point cloud Prompt: This is a rendering of a 3D model of a person. Make an accurate image of the corresponding normal map. Then I run Poisson-based normals→3D Pretty amazing for a general-purpose 2D image model 🤩
0:15

Fun & likely unintended use case for #NanoBananaPro: image→3D point cloud Prompt: This is a rendering of a 3D model of a person. Make an accurate image of the corresponding normal map. Then I run Poisson-based normals→3D Pretty amazing for a general-purpose 2D image model 🤩

Keenan Crane

71,816 Aufrufe • vor 11 Monaten

An image + a detailed normal map generated by GeoWizard --> a relightable image. Geowizard is a generative geometry estimation model that could jointly produce high-quality depth and normal with intricate details. Try our huggingface demo here: #huggingface #gradio #geowizard
0:13

An image + a detailed normal map generated by GeoWizard --> a relightable image. Geowizard is a generative geometry estimation model that could jointly produce high-quality depth and normal with intricate details. Try our huggingface demo here: #huggingface #gradio #geowizard

Xiao-Xiao Long

30,338 Aufrufe • vor 2 Jahren

some custom node controls for editing mesh gradients. i wanted to be able to distinguish between grabbing a node and grabbing the effect area. so when you hover over that circle, your cursor disappears and only shows the arc.
0:14

some custom node controls for editing mesh gradients. i wanted to be able to distinguish between grabbing a node and grabbing the effect area. so when you hover over that circle, your cursor disappears and only shows the arc.

Isaiah

34,545 Aufrufe • vor 1 Monat

Tension Map / Dynamic Squish 1. Geo Node to capture the distance between "Edge Vertices" node Position 1 & 2 as `before_edge_dist` 2. Curve modifier 3. Geo Node same again as `after_edge_dist`. `after_edge_dist / before_edge_dist = diff`. 4. Use the diff to mix normal maps
0:10

Tension Map / Dynamic Squish 1. Geo Node to capture the distance between "Edge Vertices" node Position 1 & 2 as `before_edge_dist` 2. Curve modifier 3. Geo Node same again as `after_edge_dist`. `after_edge_dist / before_edge_dist = diff`. 4. Use the diff to mix normal maps

snek3d

192,856 Aufrufe • vor 6 Monaten

Testing angled node connections #b3d #geometrynodes (This is in a custom build)
0:14

Testing angled node connections #b3d #geometrynodes (This is in a custom build)

Cartesian Caramel

39,052 Aufrufe • vor 1 Jahr

Material for my introduction course to volumetric rendering/raymarching using custom HLSL node in UE5.
0:12

Material for my introduction course to volumetric rendering/raymarching using custom HLSL node in UE5.

Gil Damoiseaux

15,841 Aufrufe • vor 1 Jahr

Added mouse drag and zoom support for this node
0:19

Added mouse drag and zoom support for this node

jtydhr88

16,368 Aufrufe • vor 10 Monaten

📢 Impossible Cloud Network's Node Sale is coming in December! 📢 The countdown begins! This is your chance to become a node operator with ICN, helping to build a secure, decentralized cloud infrastructure while earning rewards for your contribution. More info on the Node Sale will be released soon, so stay tuned! 🚀
0:12

📢 Impossible Cloud Network's Node Sale is coming in December! 📢 The countdown begins! This is your chance to become a node operator with ICN, helping to build a secure, decentralized cloud infrastructure while earning rewards for your contribution. More info on the Node Sale will be released soon, so stay tuned! 🚀

Impossible Cloud Network

91,360 Aufrufe • vor 2 Jahren

Introducing Steerable Motion, a ComfyUI custom node for steering videos using batches of images. You provide images & instructions on how you want to travel between them and it creates smooth video to fill in the gaps. See attached + more here:
0:12

Introducing Steerable Motion, a ComfyUI custom node for steering videos using batches of images. You provide images & instructions on how you want to travel between them and it creates smooth video to fill in the gaps. See attached + more here:

POM

68,592 Aufrufe • vor 2 Jahren

A few people have asked me about how I handle the lighting for my renders, so I figured it'd be good to share in case someone wants to replicate the technique! The lighting is completely artificial, handled from within the shader using a normal node for each "light source."
0:18

A few people have asked me about how I handle the lighting for my renders, so I figured it'd be good to share in case someone wants to replicate the technique! The lighting is completely artificial, handled from within the shader using a normal node for each "light source."

AreCreeps

43,180 Aufrufe • vor 8 Monaten

I created a simple GUI to use Depth to Normal without ComfyUI! Once you input an image, it will be exported as a .glTF with a normal map. Import it directly into your favorite tool like Blender or CSP. #AI :
0:11

I created a simple GUI to use Depth to Normal without ComfyUI! Once you input an image, it will be exported as a .glTF with a normal map. Import it directly into your favorite tool like Blender or CSP. #AI :

toyxyz

29,716 Aufrufe • vor 2 Jahren

Turns out the full node can travel light: same full verification and 97% less storage. We previously said substantially lower storage would require a separate light node with different security assumptions. Well, we got one thing wrong. Our upcoming upgrade delivers that reduction to the full nodes, with full transaction verification stays intact. Igra node storage: 1TB -> 30GB. Storage growth: 150GB -> 4GB per month at current activity. Running a node and verifying Igra yourself is now practical for far more people. Node operators and attesters: details and documentation coming shortly. Decentralize the world!
0:15

Turns out the full node can travel light: same full verification and 97% less storage. We previously said substantially lower storage would require a separate light node with different security assumptions. Well, we got one thing wrong. Our upcoming upgrade delivers that reduction to the full nodes, with full transaction verification stays intact. Igra node storage: 1TB -> 30GB. Storage growth: 150GB -> 4GB per month at current activity. Running a node and verifying Igra yourself is now practical for far more people. Node operators and attesters: details and documentation coming shortly. Decentralize the world!

Igra Labs

12,813 Aufrufe • vor 1 Monat

🚨 Last week, we announced the massive Checker Node Buyback Program, a chance for node holders to sell their licenses back to Aethir and unlock some exciting benefits. ⏳ The Checker Node Buyback Program goes live on May 27th on this link: Key info 🧵👇
0:12

🚨 Last week, we announced the massive Checker Node Buyback Program, a chance for node holders to sell their licenses back to Aethir and unlock some exciting benefits. ⏳ The Checker Node Buyback Program goes live on May 27th on this link: Key info 🧵👇

Aethir

22,221 Aufrufe • vor 1 Jahr

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”
0:18

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Bilawal Sidhu

92,927 Aufrufe • vor 2 Jahren

just connect the storyboard image to seedance 2 node it analyses the frames and generate a polished scene all by itself
0:19

just connect the storyboard image to seedance 2 node it analyses the frames and generate a polished scene all by itself

el.cine

30,505 Aufrufe • vor 6 Monaten

🤔Applying Depth Estimation models directly to videos can result in inconsistency between frames. 💪Well, not anymore. 🔥ChronoDepth is a new approach to video depth estimation that focuses on achieving both accuracy within each frame and consistency across frames. 📜More👇
0:15

🤔Applying Depth Estimation models directly to videos can result in inconsistency between frames. 💪Well, not anymore. 🔥ChronoDepth is a new approach to video depth estimation that focuses on achieving both accuracy within each frame and consistency across frames. 📜More👇

Gradio

19,994 Aufrufe • vor 2 Jahren

Adding an Ease Functions node to my free node group pack: #b3d #geometrynodes
0:14

Adding an Ease Functions node to my free node group pack: #b3d #geometrynodes

Cartesian Caramel

18,849 Aufrufe • vor 1 Jahr

Some updates on the multiview vistadream pipeline with Rerun! Rerun came in extremely useful here, as being able to visualize depths at each stage of the pipeline allowed me to debug some nasty bugs. Since the last time, I was only working with a single image input. I've added in VGGT as my multiview pose + depth estimator. It works REALLY well for getting camera poses, but the depths are not that great. To try and fix that, I estimated depth maps from MoGeV2 for each of the views, and scale+shift aligned them so that they would match up to the confident sections of VGGT's depth predictions. You can see in the video just how much sharper the visualized 2d depth maps are! The biggest issue continues to be the multiview consistency 🫠 That's up next, along with actually training the Gaussian splat. Lots of work went into actually understanding inputs+outputs for VGGT. I had some funky bugs where the confidence values would all collapse to true I'm also really excited for this pipeline to use Difix3D+ Nvidia instead of Flux Inpainting, it seems like a better suited for a multiview pipeline.
0:14

Some updates on the multiview vistadream pipeline with Rerun! Rerun came in extremely useful here, as being able to visualize depths at each stage of the pipeline allowed me to debug some nasty bugs. Since the last time, I was only working with a single image input. I've added in VGGT as my multiview pose + depth estimator. It works REALLY well for getting camera poses, but the depths are not that great. To try and fix that, I estimated depth maps from MoGeV2 for each of the views, and scale+shift aligned them so that they would match up to the confident sections of VGGT's depth predictions. You can see in the video just how much sharper the visualized 2d depth maps are! The biggest issue continues to be the multiview consistency 🫠 That's up next, along with actually training the Gaussian splat. Lots of work went into actually understanding inputs+outputs for VGGT. I had some funky bugs where the confidence values would all collapse to true I'm also really excited for this pipeline to use Difix3D+ Nvidia instead of Flux Inpainting, it seems like a better suited for a multiview pipeline.

Pablo Vela

29,904 Aufrufe • vor 1 Jahr

Writing my own automated lip sync solution. Think I have it where I like it now and I’ll port it into Comfy. This is my first time making a custom node pack so… will be a fun learning experience. I’ll release it once it’s done
0:02

Writing my own automated lip sync solution. Think I have it where I like it now and I’ll port it into Comfy. This is my first time making a custom node pack so… will be a fun learning experience. I’ll release it once it’s done

A.I.Warper

11,127 Aufrufe • vor 2 Jahren