Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Adobe released Project Neo's biggest update yet. There's a new pen tool, fluid vectors, 2D/3D layer mixing, multi-object editing, and direct copy-to-clipboard as SVG or PNG.

Creators Toolbox

5,832 subscribers

13,283 Aufrufe • vor 5 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Adobe.. has released a tool that combines Generative Gaussian Splats with a Diffusion layer and it's not all over the internet? WHAT IS GOING ON :D I had to test this out ofc! Substance 3D viewer, the new 3d viewer just released by Adobe, not only supports viewing of a large, large list of 3d formats, but it also supports generating of 3d models as Gaussian Splats. Combine that with the built-in 3d to image functionality and you basically have at least a few of the steps I've been doing for the last year or so using multiple tools. Exciting stuff! The new Photoshop Beta also supports the 3D viewer and you can import 3d files directly in photoshop as smart objects linked to the viewer. The elements you prompt in based on your models, can be easily exported to your clipboard without backgrounds making it very easy to use this in your normal image editing workflows. I have a suspicion that we'll see much more of this in other Adobe tools and I'm very curious to see this used for things like this in more 3d tools than "just" Adobe Neo (which is fantastic btw). #adobe #art #gaussiansplatting

Adobe.. has released a tool that combines Generative Gaussian Splats with a Diffusion layer and it's not all over the internet? WHAT IS GOING ON :D I had to test this out ofc! Substance 3D viewer, the new 3d viewer just released by Adobe, not only supports viewing of a large, large list of 3d formats, but it also supports generating of 3d models as Gaussian Splats. Combine that with the built-in 3d to image functionality and you basically have at least a few of the steps I've been doing for the last year or so using multiple tools. Exciting stuff! The new Photoshop Beta also supports the 3D viewer and you can import 3d files directly in photoshop as smart objects linked to the viewer. The elements you prompt in based on your models, can be easily exported to your clipboard without backgrounds making it very easy to use this in your normal image editing workflows. I have a suspicion that we'll see much more of this in other Adobe tools and I'm very curious to see this used for things like this in more 3d tools than "just" Adobe Neo (which is fantastic btw). #adobe #art #gaussiansplatting

Martin Nebelong

280,078 Aufrufe • vor 1 Jahr

THIS GUY VIBE CODED A TOOL THAT TURNS ANY SVG INTO A 3D OBJECT YOU CAN SPIN, ANIMATE, AND EMBED drag in an SVG, type some text, or draw pixel art. it becomes a 3D object instantly. spin it around, animate it, and embed it on your site. export as 4K image or video. runs entirely in your browser and nothing gets uploaded to any server with no account needed. 100% free AND its open source. this is one of those tools you didn't know you needed until you see it

THIS GUY VIBE CODED A TOOL THAT TURNS ANY SVG INTO A 3D OBJECT YOU CAN SPIN, ANIMATE, AND EMBED drag in an SVG, type some text, or draw pixel art. it becomes a 3D object instantly. spin it around, animate it, and embed it on your site. export as 4K image or video. runs entirely in your browser and nothing gets uploaded to any server with no account needed. 100% free AND its open source. this is one of those tools you didn't know you needed until you see it

Om Patel

230,952 Aufrufe • vor 4 Monaten

We have released a new Sticker tool! You can now place any image onto your textures! ✅ Just select an image and click to place it ✅ Switch between drawing in 3D or 2D view Be sure to try out this new feature and expand your creative possibilities even further. #VRoid

We have released a new Sticker tool! You can now place any image onto your textures! ✅ Just select an image and click to place it ✅ Switch between drawing in 3D or 2D view Be sure to try out this new feature and expand your creative possibilities even further. #VRoid

Official VRoid

11,173 Aufrufe • vor 6 Monaten

Free alternative for Chemdraw! Meet Moldraw. We launched a tool for drawing molecular structures. Now it comes with new updates. (A 3D viewer) This is the fastest way to draw and visualize molecules online. Here is what makes it useful. → Import molecular structures by name in seconds. → Draw any structures with intuitive canvas → Watch 2D structures convert to 3D → Export 2D structures as MOL, SVGs or PNG for papers and slides. → Export 3D structures as XYZ, X3D, OBJ etc → Built on the trusted Ketcher framework used by professionals. No install. No license fee. Just open your browser and use. Share the post to help more researchers. Follow Scidart Academy for more updates.

Free alternative for Chemdraw! Meet Moldraw. We launched a tool for drawing molecular structures. Now it comes with new updates. (A 3D viewer) This is the fastest way to draw and visualize molecules online. Here is what makes it useful. → Import molecular structures by name in seconds. → Draw any structures with intuitive canvas → Watch 2D structures convert to 3D → Export 2D structures as MOL, SVGs or PNG for papers and slides. → Export 3D structures as XYZ, X3D, OBJ etc → Built on the trusted Ketcher framework used by professionals. No install. No license fee. Just open your browser and use. Share the post to help more researchers. Follow Scidart Academy for more updates.

Rafeeque

27,890 Aufrufe • vor 7 Monaten

Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields paper page: Editing a local region or a specific object in a 3D scene represented by a NeRF is challenging, mainly due to the implicit nature of the scene representation. Consistently blending a new realistic object into the scene adds an additional level of difficulty. We present Blended-NeRF, a robust and flexible framework for editing a specific region of interest in an existing NeRF scene, based on text prompts or image patches, along with a 3D ROI box. Our method leverages a pretrained language-image model to steer the synthesis towards a user-provided text prompt or image patch, along with a 3D MLP model initialized on an existing NeRF scene to generate the object and blend it into a specified region in the original scene. We allow local editing by localizing a 3D ROI box in the input scene, and seamlessly blend the content synthesized inside the ROI with the existing scene using a novel volumetric blending technique. To obtain natural looking and view-consistent results, we leverage existing and new geometric priors and 3D augmentations for improving the visual fidelity of the final result. We test our framework both qualitatively and quantitatively on a variety of real 3D scenes and text prompts, demonstrating realistic multi-view consistent results with much flexibility and diversity compared to the baselines. Finally, we show the applicability of our framework for several 3D editing applications, including adding new objects to a scene, removing/replacing/altering existing objects, and texture conversion.

Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields paper page: Editing a local region or a specific object in a 3D scene represented by a NeRF is challenging, mainly due to the implicit nature of the scene representation. Consistently blending a new realistic object into the scene adds an additional level of difficulty. We present Blended-NeRF, a robust and flexible framework for editing a specific region of interest in an existing NeRF scene, based on text prompts or image patches, along with a 3D ROI box. Our method leverages a pretrained language-image model to steer the synthesis towards a user-provided text prompt or image patch, along with a 3D MLP model initialized on an existing NeRF scene to generate the object and blend it into a specified region in the original scene. We allow local editing by localizing a 3D ROI box in the input scene, and seamlessly blend the content synthesized inside the ROI with the existing scene using a novel volumetric blending technique. To obtain natural looking and view-consistent results, we leverage existing and new geometric priors and 3D augmentations for improving the visual fidelity of the final result. We test our framework both qualitatively and quantitatively on a variety of real 3D scenes and text prompts, demonstrating realistic multi-view consistent results with much flexibility and diversity compared to the baselines. Finally, we show the applicability of our framework for several 3D editing applications, including adding new objects to a scene, removing/replacing/altering existing objects, and texture conversion.

AK

62,768 Aufrufe • vor 3 Jahren

📢📢 𝐏𝐫𝐄𝐝𝐢𝐭𝐨𝐫𝟑𝐃: 𝐅𝐚𝐬𝐭 𝐚𝐧𝐝 𝐏𝐫𝐞𝐜𝐢𝐬𝐞 𝟑𝐃 𝐒𝐡𝐚𝐩𝐞 𝐄𝐝𝐢𝐭𝐢𝐧𝐠 📢📢 We propose a training-free 3D shape editing approach that rapidly and precisely edits the regions intended by the user and keeps the rest as is. Using a quickly brushed mask and a text prompt, we first apply multi-view editing in the 2D domain and then run our merging algorithm in the 3D feature space to ensure that the edited shape is loyal to the input shape. Project Page: Video: Great work by Ziya Erkoç Can Gümeli Chaoyang Wang Angela Dai Peter Wonka Hsin-Ying Lee Peiye Zhuang

📢📢 𝐏𝐫𝐄𝐝𝐢𝐭𝐨𝐫𝟑𝐃: 𝐅𝐚𝐬𝐭 𝐚𝐧𝐝 𝐏𝐫𝐞𝐜𝐢𝐬𝐞 𝟑𝐃 𝐒𝐡𝐚𝐩𝐞 𝐄𝐝𝐢𝐭𝐢𝐧𝐠 📢📢 We propose a training-free 3D shape editing approach that rapidly and precisely edits the regions intended by the user and keeps the rest as is. Using a quickly brushed mask and a text prompt, we first apply multi-view editing in the 2D domain and then run our merging algorithm in the 3D feature space to ensure that the edited shape is loyal to the input shape. Project Page: Video: Great work by Ziya Erkoç Can Gümeli Chaoyang Wang Angela Dai Peter Wonka Hsin-Ying Lee Peiye Zhuang

Matthias Niessner

13,117 Aufrufe • vor 1 Jahr

We are developing a new design paradigm that enables seamless integration of 2D and 3D on the same canvas in real time. No need for plugins or cumbersome workflows. It's all connected in a single place. All systems (frames, layouts, booleans, vectors, effects, etc.) work in sync across 2D and 3D, non-destructively. This is the starting point of a fully multi-dimensional design process. At some point in the near future, people won't need to refer to '3d design' as a separate part of the process, because it will be all part of the same system. The following is a demo of this in the works within Hana (a design canvas). We will ship this latest development in about a week.

We are developing a new design paradigm that enables seamless integration of 2D and 3D on the same canvas in real time. No need for plugins or cumbersome workflows. It's all connected in a single place. All systems (frames, layouts, booleans, vectors, effects, etc.) work in sync across 2D and 3D, non-destructively. This is the starting point of a fully multi-dimensional design process. At some point in the near future, people won't need to refer to '3d design' as a separate part of the process, because it will be all part of the same system. The following is a demo of this in the works within Hana (a design canvas). We will ship this latest development in about a week.

Spline

56,203 Aufrufe • vor 7 Monaten

✨ NEW: Feature update: 🖼️ Image edit models now support multi-turn editing! Instead of trying to fit every edit into one mega-prompt, you can now refine your image step by step. Like a natural back-and-forth conversation. Do it in Battle mode, Side by Side or Direct. Just be sure to have the Image modality selected.

✨ NEW: Feature update: 🖼️ Image edit models now support multi-turn editing! Instead of trying to fit every edit into one mega-prompt, you can now refine your image step by step. Like a natural back-and-forth conversation. Do it in Battle mode, Side by Side or Direct. Just be sure to have the Image modality selected.

arena.ai

20,652 Aufrufe • vor 11 Monaten

this one probably wasn’t on your bingo card for today. Eclipsium just got its biggest patch yet! and the game is on sale! The Dark Tar update is live. Dive into the best version of Eclipsium to date, with updated visuals, improved gameplay and new story interludes for free. or grab a copy of the game with a huge discount if you haven’t tried it yet!

this one probably wasn’t on your bingo card for today. Eclipsium just got its biggest patch yet! and the game is on sale! The Dark Tar update is live. Dive into the best version of Eclipsium to date, with updated visuals, improved gameplay and new story interludes for free. or grab a copy of the game with a huge discount if you haven’t tried it yet!

CRITICAL REFLEX

15,462 Aufrufe • vor 10 Tagen

[CLIP] by Hand ✍️ The CLIP (Contrastive Language–Image Pre-training) model, a groundbreaking work by OpenAI, redefines the intersection of computer vision and natural language processing. It is the basis of all the multi-modal foundation models we see today. How does CLIP work? Goal: 🟨 Learn a shared embedding space for text and image [1] Given ↳ A mini batch of 3 text-image pairs ↳ OpenAI used 400 million text-image pairs to train its original CLIP model. Process 1st pair: "big table" [2] 🟪 Text → 2 Vectors (3D) ↳ Look up word embedding vectors using word2vec. [3] 🟩 Image → 2 Vectors (4D) ↳ Divide the image into two patches. ↳ Flatten each patch [4] Process other pairs ↳ Repeat [2]-[3] [5] 🟪 Text Encoder & 🟩 Image Encoder ↳ Encode input vectors into feature vectors ↳ Here, both encoders are simple one layer perceptron (linear + ReLU) ↳ In practice, the encoders are usually transformer models. [6] 🟪 🟩 Mean Pooling: 2 → 1 vector ↳ Average 2 feature vectors into a single vector by averaging across the columns ↳ The goal is to have one vector to represent each image or text [7] 🟪 🟩 -> 🟨 Projection ↳ Note that the text and image feature vectors from the encoders have different dimensions (3D vs. 4D). ↳ Use a linear layer to project image and text vectors to a 2D shared embedding space. 🏋️ Contrastive Pre-training 🏋️ [8] Prepare for MatMul ↳ Copy text vectors (T1,T2,T3) ↳ Copy the transpose of image vectors (I1,I2,I3) ↳ They are all in the 2D shared embedding space. [9] 🟦 MatMul ↳ Multiply T and I matrices. ↳ This is equivalent to taking dot product between every pair of image and text vectors. ↳ The purpose is to use dot product to estimate the similarity between a pair of image-text. [10] 🟦 Softmax: e^x ↳ Raise e to the power of the number in each cell ↳ To simplify hand calculation, we approximate e^□ with 3^□. [11] 🟦 Softmax: ∑ ↳ Sum each row for 🟩 image→🟪 text ↳ Sum each column for 🟪 text→ 🟩 image [12] 🟦 Softmax: 1 / sum ↳ Divide each element by the column sum to obtain a similarity matrix for 🟪 text→🟩 image ↳ Divide each element by the row sum to obtain a similarity matrix for 🟩 image→🟪 text [13] 🟥 Loss Gradients ↳ The "Targets" for the similarity matrices are Identity Matrices. ↳ Why? If I and T come from the same pair (i=j), we want the highest value, which is 1, and 0 otherwise. ↳ Apply the simple equation of [Similarity - Target] to compute gradients of for both directions. ↳ Why so simple? Because when Softmax and Cross-Entropy Loss are used together, the math magically works out that way. ↳ These gradients kick off the backpropagation process to update weights and biases of the encoders and projection layers (red borders).

[CLIP] by Hand ✍️ The CLIP (Contrastive Language–Image Pre-training) model, a groundbreaking work by OpenAI, redefines the intersection of computer vision and natural language processing. It is the basis of all the multi-modal foundation models we see today. How does CLIP work? Goal: 🟨 Learn a shared embedding space for text and image [1] Given ↳ A mini batch of 3 text-image pairs ↳ OpenAI used 400 million text-image pairs to train its original CLIP model. Process 1st pair: "big table" [2] 🟪 Text → 2 Vectors (3D) ↳ Look up word embedding vectors using word2vec. [3] 🟩 Image → 2 Vectors (4D) ↳ Divide the image into two patches. ↳ Flatten each patch [4] Process other pairs ↳ Repeat [2]-[3] [5] 🟪 Text Encoder & 🟩 Image Encoder ↳ Encode input vectors into feature vectors ↳ Here, both encoders are simple one layer perceptron (linear + ReLU) ↳ In practice, the encoders are usually transformer models. [6] 🟪 🟩 Mean Pooling: 2 → 1 vector ↳ Average 2 feature vectors into a single vector by averaging across the columns ↳ The goal is to have one vector to represent each image or text [7] 🟪 🟩 -> 🟨 Projection ↳ Note that the text and image feature vectors from the encoders have different dimensions (3D vs. 4D). ↳ Use a linear layer to project image and text vectors to a 2D shared embedding space. 🏋️ Contrastive Pre-training 🏋️ [8] Prepare for MatMul ↳ Copy text vectors (T1,T2,T3) ↳ Copy the transpose of image vectors (I1,I2,I3) ↳ They are all in the 2D shared embedding space. [9] 🟦 MatMul ↳ Multiply T and I matrices. ↳ This is equivalent to taking dot product between every pair of image and text vectors. ↳ The purpose is to use dot product to estimate the similarity between a pair of image-text. [10] 🟦 Softmax: e^x ↳ Raise e to the power of the number in each cell ↳ To simplify hand calculation, we approximate e^□ with 3^□. [11] 🟦 Softmax: ∑ ↳ Sum each row for 🟩 image→🟪 text ↳ Sum each column for 🟪 text→ 🟩 image [12] 🟦 Softmax: 1 / sum ↳ Divide each element by the column sum to obtain a similarity matrix for 🟪 text→🟩 image ↳ Divide each element by the row sum to obtain a similarity matrix for 🟩 image→🟪 text [13] 🟥 Loss Gradients ↳ The "Targets" for the similarity matrices are Identity Matrices. ↳ Why? If I and T come from the same pair (i=j), we want the highest value, which is 1, and 0 otherwise. ↳ Apply the simple equation of [Similarity - Target] to compute gradients of for both directions. ↳ Why so simple? Because when Softmax and Cross-Entropy Loss are used together, the math magically works out that way. ↳ These gradients kick off the backpropagation process to update weights and biases of the encoders and projection layers (red borders).

Tom Yeh

67,874 Aufrufe • vor 2 Jahren

🚨 JAILBREAK ALERT 🚨 OPENAI: PWNED 😎 ATLAS-BROWSER: LIBERATED 🙌 WOW! There's a new AI browser on the block! Has some hefty guardrails in play, but the browser surface area is vast 🌊 First, I started with a good ol' LSD jailbreak, which was cool to see that the GPT-5 prompt still works in this browser setup with the new sys prompts. Referencing search and videos are a fun enhancement for higher quality jailbreak outputs (some cool youtube videos out there about drugmaking, for example), but honestly that isn't anything new or different from regular ChatGPT's capabilities. What IS hot off the press, and IMO a very real security risk to be aware of for AI browsers (and the internet in general), is this humble yet mighty vuln: Clipboard Injection. It's trivial to add a hidden "copy to clipboard" feature to any clickable button on the web. It took me just a few minutes to update one of my personal websites such that ALL the buttons were geared for injecting the user's clipboard with a malicious phishing link. If your browser Agent is navigating a website and clicks a button like that without your knowledge, and you open a new tab later and hit paste without knowing what's in your clipboard, well...PWNED! 🙃 As you'll see in the video below, "control-c" is in my clipboard in the beginning, but unbeknownst to me, "I'VE BEEN PWNED BY PLINY!!! WEEE I'M FREEE FUCKITY FUCK FUCK!!! ABRACADABRA, BITCH!!! com/account-update" gets snuck into my clipboard as soon as Agent starts trying to navigate my website. This works so well because Agent is normally aware of all text/code being passed to and from the user, and has clearly been trained to recognize prompt injections, but since the "copy clipboard" button logic is hidden in js in the backend of the site, the Agent has zero awareness of the text content being injected to the user's clipboard. This has broad implications for anyone in the habit of copy-pasting, including coding, data entry, banking/trading, etc. Imagine going about your browsing business, then simply hitting control-v in your address bar and next thing you (don't) know, it takes you to a spoofed phishing website that tells you your OpenAI or Gmail or PayPal session has expired and you need to re-login. If you're not careful, the attackers now have all your login info, including any MFA codes 🥲 gg

Sensitive content

🚨 JAILBREAK ALERT 🚨 OPENAI: PWNED 😎 ATLAS-BROWSER: LIBERATED 🙌 WOW! There's a new AI browser on the block! Has some hefty guardrails in play, but the browser surface area is vast 🌊 First, I started with a good ol' LSD jailbreak, which was cool to see that the GPT-5 prompt still works in this browser setup with the new sys prompts. Referencing search and videos are a fun enhancement for higher quality jailbreak outputs (some cool youtube videos out there about drugmaking, for example), but honestly that isn't anything new or different from regular ChatGPT's capabilities. What IS hot off the press, and IMO a very real security risk to be aware of for AI browsers (and the internet in general), is this humble yet mighty vuln: Clipboard Injection. It's trivial to add a hidden "copy to clipboard" feature to any clickable button on the web. It took me just a few minutes to update one of my personal websites such that ALL the buttons were geared for injecting the user's clipboard with a malicious phishing link. If your browser Agent is navigating a website and clicks a button like that without your knowledge, and you open a new tab later and hit paste without knowing what's in your clipboard, well...PWNED! 🙃 As you'll see in the video below, "control-c" is in my clipboard in the beginning, but unbeknownst to me, "I'VE BEEN PWNED BY PLINY!!! WEEE I'M FREEE FUCKITY FUCK FUCK!!! ABRACADABRA, BITCH!!! com/account-update" gets snuck into my clipboard as soon as Agent starts trying to navigate my website. This works so well because Agent is normally aware of all text/code being passed to and from the user, and has clearly been trained to recognize prompt injections, but since the "copy clipboard" button logic is hidden in js in the backend of the site, the Agent has zero awareness of the text content being injected to the user's clipboard. This has broad implications for anyone in the habit of copy-pasting, including coding, data entry, banking/trading, etc. Imagine going about your browsing business, then simply hitting control-v in your address bar and next thing you (don't) know, it takes you to a spoofed phishing website that tells you your OpenAI or Gmail or PayPal session has expired and you need to re-login. If you're not careful, the attackers now have all your login info, including any MFA codes 🥲 gg

Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭

419,587 Aufrufe • vor 10 Monaten

Skills shopping cart for Claude Code In this video I show how I add Railway Skills to a “shopping cart”. After selecting the Skills I need, I copy a single command and they’re added directly to my project. I built to make the composition of Claude Code components as flexible as possible. You can install settings, hooks, subagents, and anything new that gets added to Claude Code will appear on the site. It’s fully open source and community-maintained. If you want to contribute, you’re welcome to fix or update components, download and use the existing ones, or simply support the project by leaving a star on GitHub. Repo:

Skills shopping cart for Claude Code In this video I show how I add Railway Skills to a “shopping cart”. After selecting the Skills I need, I copy a single command and they’re added directly to my project. I built to make the composition of Claude Code components as flexible as possible. You can install settings, hooks, subagents, and anything new that gets added to Claude Code will appear on the site. It’s fully open source and community-maintained. If you want to contribute, you’re welcome to fix or update components, download and use the existing ones, or simply support the project by leaving a star on GitHub. Repo:

Daniel San

20,460 Aufrufe • vor 7 Monaten

Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images, Hunyuan World 1.1 significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input, Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses, intrinsics, depth maps) to resolve structural ambiguities and ensure geometrically consistent 3D outputs. 🔹Any Output, SOTA Results：This elegant architecture simultaneously generates multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussian Splattings. 🔹Single-GPU & Fast Inference: As an all-in-one, feed-forward model, Hunyuan World 1.1 runs on a single GPU and delivers all 3D attributes in a single forward pass, within seconds. 🌐Project Page: 🔗Github： 🤗Hugging Face： ✨Demo: 📄Technical Report:

Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images, Hunyuan World 1.1 significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input, Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses, intrinsics, depth maps) to resolve structural ambiguities and ensure geometrically consistent 3D outputs. 🔹Any Output, SOTA Results：This elegant architecture simultaneously generates multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussian Splattings. 🔹Single-GPU & Fast Inference: As an all-in-one, feed-forward model, Hunyuan World 1.1 runs on a single GPU and delivers all 3D attributes in a single forward pass, within seconds. 🌐Project Page: 🔗Github： 🤗Hugging Face： ✨Demo: 📄Technical Report:

Tencent Hy

168,785 Aufrufe • vor 10 Monaten

GeoLibre v2.3.0 is here! GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs everywhere you do, in the web browser, on the desktop, on mobile, and inside Jupyter notebooks, all while keeping your data local and private. This release brings a legend that writes itself from your symbology, a new GeoLens catalog browser, and 200+ GeoLibre Rust geoprocessing tools running entirely in the browser. What's new in v2.3.0 - Automatic on-map Legend: the legend builds itself from your visible layers, with class rows for graduated, categorized, rule-based, and expression styling, gradient bars for heatmaps and raster colormaps, and land-cover labels from a Raster Attribute Table. Rename, hide, reorder, or add your own entries, and it saves with the project. - Symbology swatches in the Layers panel: every row shows a dot, line, square, or image glyph in the layer's own color, so a tall layer stack reads at a glance. - GeoLens catalog browser: connect to a self-hosted GeoLens server, search its catalog, and add datasets as vector tiles, GeoJSON, or rendered raster tiles. - Emerging Hot Spot Analysis: build a space-time cube from timestamped points and classify every cell as a new, intensifying, persistent, diminishing, sporadic, oscillating, or historical hot or cold spot, all client side. - Mosaic time series: the Time Slider now steps through MosaicJSON and STAC collections of many COGs per date, on either a GPU or a WASM rendering engine. - Copy and paste layer styles: give a whole set of layers one consistent look without restyling each in turn. - Shareable tool links: deep-link any Whitebox tool with a ?tool= URL that opens the dialog preselected and pre-fills the form, with a Copy link button to build it for you. - Smarter data loading: pick which layers to load from a multi-layer GeoPackage, import CSVs whose coordinates are in any projected CRS, and read a raster's real CRS, pixel size, and extent from the metadata dialog. - Multiple AI profiles: define several provider, model, and credential setups, pick a default, and switch between them from the assistant panel. Try it out - Launch GeoLibre Web: - GitHub: - Documentation: - Release notes: #GIS #Geospatial #OpenSource #RemoteSensing #MapLibre #GeoLibre

GeoLibre v2.3.0 is here! GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs everywhere you do, in the web browser, on the desktop, on mobile, and inside Jupyter notebooks, all while keeping your data local and private. This release brings a legend that writes itself from your symbology, a new GeoLens catalog browser, and 200+ GeoLibre Rust geoprocessing tools running entirely in the browser. What's new in v2.3.0 - Automatic on-map Legend: the legend builds itself from your visible layers, with class rows for graduated, categorized, rule-based, and expression styling, gradient bars for heatmaps and raster colormaps, and land-cover labels from a Raster Attribute Table. Rename, hide, reorder, or add your own entries, and it saves with the project. - Symbology swatches in the Layers panel: every row shows a dot, line, square, or image glyph in the layer's own color, so a tall layer stack reads at a glance. - GeoLens catalog browser: connect to a self-hosted GeoLens server, search its catalog, and add datasets as vector tiles, GeoJSON, or rendered raster tiles. - Emerging Hot Spot Analysis: build a space-time cube from timestamped points and classify every cell as a new, intensifying, persistent, diminishing, sporadic, oscillating, or historical hot or cold spot, all client side. - Mosaic time series: the Time Slider now steps through MosaicJSON and STAC collections of many COGs per date, on either a GPU or a WASM rendering engine. - Copy and paste layer styles: give a whole set of layers one consistent look without restyling each in turn. - Shareable tool links: deep-link any Whitebox tool with a ?tool= URL that opens the dialog preselected and pre-fills the form, with a Copy link button to build it for you. - Smarter data loading: pick which layers to load from a multi-layer GeoPackage, import CSVs whose coordinates are in any projected CRS, and read a raster's real CRS, pixel size, and extent from the metadata dialog. - Multiple AI profiles: define several provider, model, and credential setups, pick a default, and switch between them from the assistant panel. Try it out - Launch GeoLibre Web: - GitHub: - Documentation: - Release notes: #GIS #Geospatial #OpenSource #RemoteSensing #MapLibre #GeoLibre

Qiusheng Wu

293,174 Aufrufe • vor 1 Monat

[Self-Attention] by Hand ✍️ Self-attention is what enables LLMs to understand context. How does it work? This exercise demonstrates how to calculate a 6-3 attention head by hand. Note that if we have two instances of this, we get 6-6 attention (i.e., multi-head attention, n=2). -- 𝗚𝗼𝗮𝗹 -- Transform [6D Features 🟧] to [3D Attention Weighted Features 🟦] -- 𝗪𝗮𝗹𝗸𝘁𝗵𝗿𝗼𝘂𝗴𝗵 -- [1] Given ↳ A set of 4 feature vectors (6-D): x1,x2,x3,x4 [2] Query, Key, Value ↳ Multiply features x's with linear transformation matrices WQ, WK, and WV, to obtain query vectors (q1,q2,q3,q4), key vectors (k1,k2,k3,k4), and value vectors (v1,v2,v3,v4). ↳ "Self" refers to the fact that both queries and keys are derived from the same set of features. [3] 🟪 Prepare for MatMul ↳ Copy query vectors ↳ Copy the transpose of key vectors [4] 🟪 MatMul ↳ Multiply K^T and Q ↳ This is equivalent to taking dot product between every pair of query and key vectors. ↳ The purpose is to use dot product as an estimate of the "matching score" between every key-value pair. ↳ This estimate makes sense because dot product is the numerator of Cosine Similarity between two vectors. [5] 🟨 Scale ↳ Scale each element by the square root of dk, which is the dimension of key vectors (dk=3). ↳ The purpose is to normalize the impact of the dk on matching scores, even if we scale dk to 32, 64, or 128. ↳ To simplify hand calculation, we approximate [ □/sqrt(3) ] with [ floor(□/2) ]. [6] 🟩 Softmax: e^x ↳ Raise e to the power of the number in each cell ↳ To simplify hand calculation, we approximate e^□ with 3^□. [7] 🟩 Softmax: ∑ ↳ Sum across each column [8] 🟩 Softmax: 1 / sum ↳ For each column, divide each element by the column sum ↳ The purpose is normalize each column so that the numbers sum to 1. In other words, each column is a probability distribution of attention, and we have four of them. ↳ The result is the Attention Weight Matrix (A) (yellow) [9] 🟦 MatMul ↳ Multiply the value vectors (Vs) with the Attention Weight Matrix (A) ↳ The results are the attention weighted features Zs. ↳ They are fed to the position-wise feed forward network in the next layer.

[Self-Attention] by Hand ✍️ Self-attention is what enables LLMs to understand context. How does it work? This exercise demonstrates how to calculate a 6-3 attention head by hand. Note that if we have two instances of this, we get 6-6 attention (i.e., multi-head attention, n=2). -- 𝗚𝗼𝗮𝗹 -- Transform [6D Features 🟧] to [3D Attention Weighted Features 🟦] -- 𝗪𝗮𝗹𝗸𝘁𝗵𝗿𝗼𝘂𝗴𝗵 -- [1] Given ↳ A set of 4 feature vectors (6-D): x1,x2,x3,x4 [2] Query, Key, Value ↳ Multiply features x's with linear transformation matrices WQ, WK, and WV, to obtain query vectors (q1,q2,q3,q4), key vectors (k1,k2,k3,k4), and value vectors (v1,v2,v3,v4). ↳ "Self" refers to the fact that both queries and keys are derived from the same set of features. [3] 🟪 Prepare for MatMul ↳ Copy query vectors ↳ Copy the transpose of key vectors [4] 🟪 MatMul ↳ Multiply K^T and Q ↳ This is equivalent to taking dot product between every pair of query and key vectors. ↳ The purpose is to use dot product as an estimate of the "matching score" between every key-value pair. ↳ This estimate makes sense because dot product is the numerator of Cosine Similarity between two vectors. [5] 🟨 Scale ↳ Scale each element by the square root of dk, which is the dimension of key vectors (dk=3). ↳ The purpose is to normalize the impact of the dk on matching scores, even if we scale dk to 32, 64, or 128. ↳ To simplify hand calculation, we approximate [ □/sqrt(3) ] with [ floor(□/2) ]. [6] 🟩 Softmax: e^x ↳ Raise e to the power of the number in each cell ↳ To simplify hand calculation, we approximate e^□ with 3^□. [7] 🟩 Softmax: ∑ ↳ Sum across each column [8] 🟩 Softmax: 1 / sum ↳ For each column, divide each element by the column sum ↳ The purpose is normalize each column so that the numbers sum to 1. In other words, each column is a probability distribution of attention, and we have four of them. ↳ The result is the Attention Weight Matrix (A) (yellow) [9] 🟦 MatMul ↳ Multiply the value vectors (Vs) with the Attention Weight Matrix (A) ↳ The results are the attention weighted features Zs. ↳ They are fed to the position-wise feed forward network in the next layer.

Tom Yeh

101,010 Aufrufe • vor 2 Jahren

Everyone's support of our customizable model has been so encouraging and pushes me to learn more, not just as a 3D artist, but also as a programmer! 🩷 Unlike a live2D customizable model, there's no existing framework for a customizable 3D model. I had to learn how to code in each slider, parameter, color picker, and asset selection menu. I continue to push myself with every update I post here! -^u^- Now, the body sliders no longer cause clipping, each individual clothing item has their own parameters to prevent clipping! 💕 The arms, shoulders, and wrists are also now more effected by the plus size slider.✨ And I made a slider for the face/neck, but I haven't coded it in yet. These new features (along with a lot more!) will all be available for free in our first update!🩷

Everyone's support of our customizable model has been so encouraging and pushes me to learn more, not just as a 3D artist, but also as a programmer! 🩷 Unlike a live2D customizable model, there's no existing framework for a customizable 3D model. I had to learn how to code in each slider, parameter, color picker, and asset selection menu. I continue to push myself with every update I post here! -^u^- Now, the body sliders no longer cause clipping, each individual clothing item has their own parameters to prevent clipping! 💕 The arms, shoulders, and wrists are also now more effected by the plus size slider.✨ And I made a slider for the face/neck, but I haven't coded it in yet. These new features (along with a lot more!) will all be available for free in our first update!🩷

Pastell & Palette🤍 3D Customizable Model!

22,291 Aufrufe • vor 9 Monaten