Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Neck and back muscles, layer by layer. An exploded view created with SciePro’s 3D anatomy model—where anatomical accuracy drives every detail. License medical illustrations and animations through our library. Link in the first reply. #SciePro #3DAnatomy

SciePro's profile picture

SciePro

27,879 subscribers

14,107 Aufrufe • vor 1 Monat •via X (Twitter)

#SciePro#3DAnatomy
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Blood flow through the right ventricle, visualized with SciePro’s detailed 3D anatomy model. Conceptual visualization: far less blood is shown to keep the internal anatomy visible. Medical visuals and licensing → first reply. #SciePro #HeartAnatomy
0:10

Blood flow through the right ventricle, visualized with SciePro’s detailed 3D anatomy model. Conceptual visualization: far less blood is shown to keep the internal anatomy visible. Medical visuals and licensing → first reply. #SciePro #HeartAnatomy

SciePro

22,767 Aufrufe • vor 28 Tagen

Exploded view of the human brain. Showing how its regions connect and form one coordinated system. Based on SciePro’s 3D anatomy models. Licensing: #brain #neuroscience #neurology
0:12

Exploded view of the human brain. Showing how its regions connect and form one coordinated system. Based on SciePro’s 3D anatomy models. Licensing: #brain #neuroscience #neurology

SciePro

16,235 Aufrufe • vor 11 Monaten

Everything you are lives inside this structure. The brain has the consistency of soft tofu. Without the skull, it would be destroyed by everyday forces. This exploded view shows the multi-layered defense: interlocking bones, impact-distributing sutures, three meningeal layers, and cerebrospinal fluid. Bone, sutures, meninges, CSF. Four layers of protection. #SkullAnatomy All animations created using the SciePro 3D anatomy model.
0:19

Everything you are lives inside this structure. The brain has the consistency of soft tofu. Without the skull, it would be destroyed by everyday forces. This exploded view shows the multi-layered defense: interlocking bones, impact-distributing sutures, three meningeal layers, and cerebrospinal fluid. Bone, sutures, meninges, CSF. Four layers of protection. #SkullAnatomy All animations created using the SciePro 3D anatomy model.

SciePro

26,235 Aufrufe • vor 2 Monaten

The chordae tendineae. The "heartstrings." Thin fibrous cords that prevent your valve leaflets from flipping inside out every time your heart contracts. ~20-30 per valve. Slack during filling, taut during contraction. ~100,000 cycles per day. ~3.5 billion over a lifetime. When one snaps, blood flows backward. #ChordaeTendineae All animations created using the SciePro 3D anatomy model.
0:19

The chordae tendineae. The "heartstrings." Thin fibrous cords that prevent your valve leaflets from flipping inside out every time your heart contracts. ~20-30 per valve. Slack during filling, taut during contraction. ~100,000 cycles per day. ~3.5 billion over a lifetime. When one snaps, blood flows backward. #ChordaeTendineae All animations created using the SciePro 3D anatomy model.

SciePro

36,711 Aufrufe • vor 2 Monaten

Your gut has 200-600 million neurons. More than the spinal cord. It can run digestion entirely on its own, even if the vagus nerve is cut. That is why it's called the "second brain." This visualization shows the nerve plexuses surrounding the small and large intestine. #EntericNervousSystem All animations created using the SciePro 3D anatomy model.
0:10

Your gut has 200-600 million neurons. More than the spinal cord. It can run digestion entirely on its own, even if the vagus nerve is cut. That is why it's called the "second brain." This visualization shows the nerve plexuses surrounding the small and large intestine. #EntericNervousSystem All animations created using the SciePro 3D anatomy model.

SciePro

14,204 Aufrufe • vor 4 Monaten

The thyroid gland regulates your metabolism, heart rate, and body temperature. Learn how this butterfly-shaped gland works in our 3D animation! 🦋 #ThyroidGland #EndocrineSystem
0:18

The thyroid gland regulates your metabolism, heart rate, and body temperature. Learn how this butterfly-shaped gland works in our 3D animation! 🦋 #ThyroidGland #EndocrineSystem

SciePro

12,940 Aufrufe • vor 1 Jahr

Get to the root of lower teeth health with #SciePro's insights into the inferior alveolar nerve, vein, and artery. Perfect for #Dentistry enthusiasts and professionals! Explore the anatomy that sustains your smile. #DentalAnatomy #OralHealth #3dmodel #meded
0:12

Get to the root of lower teeth health with #SciePro's insights into the inferior alveolar nerve, vein, and artery. Perfect for #Dentistry enthusiasts and professionals! Explore the anatomy that sustains your smile. #DentalAnatomy #OralHealth #3dmodel #meded

SciePro

12,706 Aufrufe • vor 2 Jahren

A reference sheet can now become a complete 3D asset and an interactive website. I generated the multi-view temple concept with GPT Image 2.0, then gave it to Codex + GPT-5.6 Ultra through Blender MCP. Blender was controlled entirely from the terminal. The model, materials, cameras, renders and exports were all generated through Python scripts. Codex then created a Three.js viewer where I can rotate the temple, switch between every angle and hide each architectural layer. The result still needs refinement, especially around the roofs and ornaments, but the complete image → Blender → web workflow is working. All from one prompt 👇
0:18

A reference sheet can now become a complete 3D asset and an interactive website. I generated the multi-view temple concept with GPT Image 2.0, then gave it to Codex + GPT-5.6 Ultra through Blender MCP. Blender was controlled entirely from the terminal. The model, materials, cameras, renders and exports were all generated through Python scripts. Codex then created a Three.js viewer where I can rotate the temple, switch between every angle and hide each architectural layer. The result still needs refinement, especially around the roofs and ornaments, but the complete image → Blender → web workflow is working. All from one prompt 👇

Givros

26,024 Aufrufe • vor 3 Monaten

The aortic and mitral valves are essential for regulating blood flow through the heart, ensuring oxygenated blood reaches the body efficiently. #HeartHealth #Cardiology
0:14

The aortic and mitral valves are essential for regulating blood flow through the heart, ensuring oxygenated blood reaches the body efficiently. #HeartHealth #Cardiology

SciePro

20,699 Aufrufe • vor 2 Jahren

The heart and pulmonary blood vessels work together to oxygenate blood and maintain circulation. Discover how this vital process keeps your body running smoothly. #HeartHealth #PulmonaryVessels #SciePro
0:15

The heart and pulmonary blood vessels work together to oxygenate blood and maintain circulation. Discover how this vital process keeps your body running smoothly. #HeartHealth #PulmonaryVessels #SciePro

SciePro

12,223 Aufrufe • vor 2 Jahren

Created this mixed media video using the 'invideo editor', just by chatting with an editing agent. ~ Asked the agent to break up the original video into individual frames (for this one it was 12 fps) ~ Described the mixed media style we wanted in detail to the agent (you could also give the agent reference images and videos that you feel work best for the video you're creating), ~ And then asked it to generate each frame using an image-gen model and line it back up in the right place as a separate layer. Did all this in ~30 minutes.
0:14

Created this mixed media video using the 'invideo editor', just by chatting with an editing agent. ~ Asked the agent to break up the original video into individual frames (for this one it was 12 fps) ~ Described the mixed media style we wanted in detail to the agent (you could also give the agent reference images and videos that you feel work best for the video you're creating), ~ And then asked it to generate each frame using an image-gen model and line it back up in the right place as a separate layer. Did all this in ~30 minutes.

Invideo

219,869 Aufrufe • vor 1 Monat

We are proud to announce our first contribution to open source Computer Vision research! 🚀 Today, we’re publishing on Hugging Face a 1,000 3D Maps Dataset under CC-BY-NC license, designed to accelerate progress in 3D perception and spatial AI. Our way to give back to the global AI community and show how DePIN can make an impact. 🧵 👉
0:10

We are proud to announce our first contribution to open source Computer Vision research! 🚀 Today, we’re publishing on Hugging Face a 1,000 3D Maps Dataset under CC-BY-NC license, designed to accelerate progress in 3D perception and spatial AI. Our way to give back to the global AI community and show how DePIN can make an impact. 🧵 👉

Over the Reality 🌐

88,633 Aufrufe • vor 11 Monaten

Made with Skywork Prompt: A massive hyper-realistic black war horse stands in a desolate wasteland under a moonless sky, full-body cinematic wide shot. The cracked ground is littered with scorched bones, shattered armor, rusted weapons, and drifting ash, while distant ruined towers and collapsed cathedrals silhouette against storm-heavy clouds. Cold wind drives thick dust storms across the terrain, with embers floating through the air and faint lightning illuminating the horizon. Violent supernatural flames erupt from the horse’s hooves, igniting the dry earth and crawling upward in slow motion, burning through the skin layer by layer as glowing bone structure becomes visible beneath — ghost-rider-style transformation. The skull emerges first with blazing white-hot eyes, ribs glowing through fire, mane and tail transforming into roaring infernos. Explosive sparks scatter across the wasteland, shockwave embers ripple through the air, heat distortion warps the environment, volumetric smoke rolls low across the ground, physically accurate fire simulation, ultra-realistic global illumination, IMAX cinematic framing, slow dramatic metamorphosis, 8K hyper-detail, dark fantasy apocalypse atmosphere.
0:10

Made with Skywork Prompt: A massive hyper-realistic black war horse stands in a desolate wasteland under a moonless sky, full-body cinematic wide shot. The cracked ground is littered with scorched bones, shattered armor, rusted weapons, and drifting ash, while distant ruined towers and collapsed cathedrals silhouette against storm-heavy clouds. Cold wind drives thick dust storms across the terrain, with embers floating through the air and faint lightning illuminating the horizon. Violent supernatural flames erupt from the horse’s hooves, igniting the dry earth and crawling upward in slow motion, burning through the skin layer by layer as glowing bone structure becomes visible beneath — ghost-rider-style transformation. The skull emerges first with blazing white-hot eyes, ribs glowing through fire, mane and tail transforming into roaring infernos. Explosive sparks scatter across the wasteland, shockwave embers ripple through the air, heat distortion warps the environment, volumetric smoke rolls low across the ground, physically accurate fire simulation, ultra-realistic global illumination, IMAX cinematic framing, slow dramatic metamorphosis, 8K hyper-detail, dark fantasy apocalypse atmosphere.

Iris

38,393 Aufrufe • vor 8 Monaten

[Backpropagation] by Hand✍️ [1] Forward Pass ↳ Given a multi layer perceptron (3 levels), an input vector X, predictions Y^{Pred} = [0.5, 0.5, 0], and ground truth label Y^{Target} = [0, 1, 0]. [2] Backpropagation ↳ Insert cells to hold our calculations. [3] Layer 3 - Softmax (blue) ↳ Calculate ∂L / ∂z3 directly using the simple equation: Y^{Pred} - Y^{Target} = [0.5, -0.5, 0]. ↳ This simple equation is the benefit of using Softmax and Cross Entropy Loss together. [4] Layer 3 - Weights (orange) & Biases (black) ↳ Calculate ∂L / ∂W3 and ∂L / ∂b3 by multiplying ∂L / ∂z3 and [ a2 | 1 ]. [5] Layer 2 - Activations (green) ↳ Calculate ∂L / ∂a2 by multiplying ∂L / ∂z3 and W3. [6] Layer 2 - ReLU (blue) ↳ Calculate ∂L / ∂z2 by multiplying ∂L / ∂a2 with 1 for positive values and 0 otherwise. [7] Layer 2 - Weights (orange) & Biases (black) ↳ Calculate ∂L / ∂W2 and ∂L / ∂b2 by multiplying ∂L / ∂z2 and [ a1 | 1 ]. [8] Layer 1 - Activations (green) ↳ Calculate ∂L / ∂a1 by multiplying ∂L / ∂z2 and W2. [9] Layer 1 - ReLU (blue) ↳ Calculate ∂L / ∂z1 by multiplying ∂L / ∂a1 with 1 for positive values and 0 otherwise. [10] Layer 1 - Weights (orange) & Biases (black) ↳ Calculate ∂L / ∂W1 and ∂L / ∂b1 by multiplying ∂L / ∂z1 and [ x | 1 ]. [11] Gradient Descent ↳ Update weights and biases (typically a learning rate is applied here). 💡 Matrix Multiplication is All You Need: Just like in the forward pass, backpropagation is all about matrix multiplications. You can definitely do everything by hand as I demonstrated in this exercise, albeit slow and imperfect. This is why GPU's ability to multiply matrices efficiently plays such an important role in the deep learning evolution. This is why NVIDIA is now close to $1 trillion in valuation. 💡Exploding Gradients: We can already see the gradients are getting larger as we back-propagate up, even in this simple 3-layer network. This motivates using methods like skip connections to handle exploding (or diminishing) gradients as in the ResNet. I did the calculations entirely by hand. Please let me know if you spot any error or have any questions!
0:11

[Backpropagation] by Hand✍️ [1] Forward Pass ↳ Given a multi layer perceptron (3 levels), an input vector X, predictions Y^{Pred} = [0.5, 0.5, 0], and ground truth label Y^{Target} = [0, 1, 0]. [2] Backpropagation ↳ Insert cells to hold our calculations. [3] Layer 3 - Softmax (blue) ↳ Calculate ∂L / ∂z3 directly using the simple equation: Y^{Pred} - Y^{Target} = [0.5, -0.5, 0]. ↳ This simple equation is the benefit of using Softmax and Cross Entropy Loss together. [4] Layer 3 - Weights (orange) & Biases (black) ↳ Calculate ∂L / ∂W3 and ∂L / ∂b3 by multiplying ∂L / ∂z3 and [ a2 | 1 ]. [5] Layer 2 - Activations (green) ↳ Calculate ∂L / ∂a2 by multiplying ∂L / ∂z3 and W3. [6] Layer 2 - ReLU (blue) ↳ Calculate ∂L / ∂z2 by multiplying ∂L / ∂a2 with 1 for positive values and 0 otherwise. [7] Layer 2 - Weights (orange) & Biases (black) ↳ Calculate ∂L / ∂W2 and ∂L / ∂b2 by multiplying ∂L / ∂z2 and [ a1 | 1 ]. [8] Layer 1 - Activations (green) ↳ Calculate ∂L / ∂a1 by multiplying ∂L / ∂z2 and W2. [9] Layer 1 - ReLU (blue) ↳ Calculate ∂L / ∂z1 by multiplying ∂L / ∂a1 with 1 for positive values and 0 otherwise. [10] Layer 1 - Weights (orange) & Biases (black) ↳ Calculate ∂L / ∂W1 and ∂L / ∂b1 by multiplying ∂L / ∂z1 and [ x | 1 ]. [11] Gradient Descent ↳ Update weights and biases (typically a learning rate is applied here). 💡 Matrix Multiplication is All You Need: Just like in the forward pass, backpropagation is all about matrix multiplications. You can definitely do everything by hand as I demonstrated in this exercise, albeit slow and imperfect. This is why GPU's ability to multiply matrices efficiently plays such an important role in the deep learning evolution. This is why NVIDIA is now close to $1 trillion in valuation. 💡Exploding Gradients: We can already see the gradients are getting larger as we back-propagate up, even in this simple 3-layer network. This motivates using methods like skip connections to handle exploding (or diminishing) gradients as in the ResNet. I did the calculations entirely by hand. Please let me know if you spot any error or have any questions!

Tom Yeh

64,783 Aufrufe • vor 2 Jahren

One thing that still feels unsolved in AI video is spatial control. A model can generate a beautiful frame, but once the camera starts moving through a more complicated scene, you need to know where the camera is and where everything else is supposed to be. That’s why GPT-6 Astra’s 3D scene and spatial mapping approach is interesting. Camera and character paths can be planned within the Viewport before the scene is rendered. From there, I manually bring it into CapCut PC and use Seedance 2.5 for the video generation. 3D might be becoming an important pre-production layer for AI filmmaking..
0:15

One thing that still feels unsolved in AI video is spatial control. A model can generate a beautiful frame, but once the camera starts moving through a more complicated scene, you need to know where the camera is and where everything else is supposed to be. That’s why GPT-6 Astra’s 3D scene and spatial mapping approach is interesting. Camera and character paths can be planned within the Viewport before the scene is rendered. From there, I manually bring it into CapCut PC and use Seedance 2.5 for the video generation. 3D might be becoming an important pre-production layer for AI filmmaking..

Rshhad

27,958 Aufrufe • vor 1 Monat

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.
0:16

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

elvis

11,303 Aufrufe • vor 2 Monaten