Sensitive content

This media may contain sensitive content.

Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

🔞Ordinary day in school. Maybe. First big animation Alice model by @ XBJRTMSTUDX (gimme yo fen model bro....) 2 video with and without background music Enjoy yall (if there anyone 3d nsfw animators, how yall adding impact physics) #porno #3d #fpe #animation #video #nsfw #blender

The_Oligard's profile picture

🔞The oligard🔞 (comms open)

1,733 subscribers

35,654 görüntüleme • 1 ay önce •via X (Twitter)

NSFW#porno#3d#fpe#animation#video#nsfw#blender
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

🎥Assembly Video-Loona Rider🛠️ ⚠️Music🎧 This video will help you know how to assemble it without the need for glue, using a little bluetack is enough and if you have to travel you can take it with you! Exclusive model for Foxenprints. 🛠️🖌️Printed and painted in Foxenprints Workshop. 🗿3D sculpt by General Buta🔞 🎨Collaboration based in the amazing art of スイギ 🏪Get yours only here👇🏻
0:57

Sensitive content

🎥Assembly Video-Loona Rider🛠️ ⚠️Music🎧 This video will help you know how to assemble it without the need for glue, using a little bluetack is enough and if you have to travel you can take it with you! Exclusive model for Foxenprints. 🛠️🖌️Printed and painted in Foxenprints Workshop. 🗿3D sculpt by General Buta🔞 🎨Collaboration based in the amazing art of スイギ 🏪Get yours only here👇🏻

FoxenPrints, Furry-Kemono Dreams🦊

18,895 görüntüleme • 11 ay önce

How to Create Unlimited 3D AI Documentary Videos for FREE (Complete Guide) In this video you will learn how to create high quality 3D documentary videos from scratch using free AI tools without spending money on expensive software. You will learn the exact workflow for writing documentary scripts, generating cinematic 3D visuals, turning images into realistic video scenes, adding AI voiceovers, music, sound effects, and editing everything into a professional documentary. This tutorial covers AI documentary creation, 3D image generation, image to video animation, AI voiceovers, video editing, cinematic storytelling, and the complete workflow for creating professional documentary style videos with AI. This information is for both new and experienced creators who want to build faceless YouTube channels, create engaging documentary content, and produce unlimited AI videos using free tools in 2026. Like, Retweet and Bookmark. Follow BIG CHRIS Video Credit: Cash-Coach 🤝 (
31:37

How to Create Unlimited 3D AI Documentary Videos for FREE (Complete Guide) In this video you will learn how to create high quality 3D documentary videos from scratch using free AI tools without spending money on expensive software. You will learn the exact workflow for writing documentary scripts, generating cinematic 3D visuals, turning images into realistic video scenes, adding AI voiceovers, music, sound effects, and editing everything into a professional documentary. This tutorial covers AI documentary creation, 3D image generation, image to video animation, AI voiceovers, video editing, cinematic storytelling, and the complete workflow for creating professional documentary style videos with AI. This information is for both new and experienced creators who want to build faceless YouTube channels, create engaging documentary content, and produce unlimited AI videos using free tools in 2026. Like, Retweet and Bookmark. Follow BIG CHRIS Video Credit: Cash-Coach 🤝 (

BIG CHRIS

15,172 görüntüleme • 2 ay önce

With GPT-6 Astra, my 3D character came to life in Blender and started modeling her own clothes right inside the viewport. The video shows the real process: the character is literally redesigning her wardrobe in real time. Selecting polygons, extruding sleeves, adding modifiers, and tailoring the hoodie pattern to her body. All by herself. From the first vertex to deleting discarded meshes. OpenAI claims GPT-6 Astra can already operate software through the interface: opening apps, clicking buttons, extruding geometry, and making edits like a seasoned 3D artist. In tests with 3D and CAD environments, the new model hit record accuracy across complex workflows, leaving older versions far behind. And through agentic pipelines, it generates production-ready assets, clothing, and full scenes from simple text prompts without manual grind. Would you trust routine 3D modeling to AI or keep moving vertices by hand?
0:46

With GPT-6 Astra, my 3D character came to life in Blender and started modeling her own clothes right inside the viewport. The video shows the real process: the character is literally redesigning her wardrobe in real time. Selecting polygons, extruding sleeves, adding modifiers, and tailoring the hoodie pattern to her body. All by herself. From the first vertex to deleting discarded meshes. OpenAI claims GPT-6 Astra can already operate software through the interface: opening apps, clicking buttons, extruding geometry, and making edits like a seasoned 3D artist. In tests with 3D and CAD environments, the new model hit record accuracy across complex workflows, leaving older versions far behind. And through agentic pipelines, it generates production-ready assets, clothing, and full scenes from simple text prompts without manual grind. Would you trust routine 3D modeling to AI or keep moving vertices by hand?

Damir Akaza

167,678 görüntüleme • 11 gün önce

Very excited to share the release of my addon Blender FastHenry! Use Blender's powerful modelling capability combined with geometry nodes to run FastHenry simulations! Blender is becoming a multi-purpose tool not just a tool for 3D graphics and animation, but also for engineering and scientific work too. This video shows how you can calculate the impedance of wire bonds and leads of a Mosfet in a TO-220 package, you can see what effect bending the leads and adding a heatsink have on the impedance! hackaday Dave Jones Sybren A. Stüvel 🔶 🐈‍⬛ (sybren@fosstodon.org) #b3d #blender3d #electronics #geometrynodes #3dart #pcbdesign #transistors #Engineering #science #physics #Technology #kicad #simulation #manufacturing
1:30

Very excited to share the release of my addon Blender FastHenry! Use Blender's powerful modelling capability combined with geometry nodes to run FastHenry simulations! Blender is becoming a multi-purpose tool not just a tool for 3D graphics and animation, but also for engineering and scientific work too. This video shows how you can calculate the impedance of wire bonds and leads of a Mosfet in a TO-220 package, you can see what effect bending the leads and adding a heatsink have on the impedance! hackaday Dave Jones Sybren A. Stüvel 🔶 🐈‍⬛ ([email protected]) #b3d #blender3d #electronics #geometrynodes #3dart #pcbdesign #transistors #Engineering #science #physics #Technology #kicad #simulation #manufacturing

Sam M

45,882 görüntüleme • 1 yıl önce

Want to create an avatar from a single image? FlexAvatar is a transformer model that creates full 360°, high-quality, and expressive 3D head avatar from just a single portrait image in minutes. Real-time Demo: FlexAvatar's lightweight architecture allows both animation and rendering in real-time, enabling interactive user experiences. To create a new 3D head avatar, only one image is required, e.g., from a webcam. The final avatar is ready after 2 minutes. Architecture: Under the hood, FlexAvatar adopts a transformer-based encoder-decoder design. The encoder maps the input image onto a latent avatar space, while the decoder produces 3D Gaussian attribute maps by incorporating the animation signal via cross-attention. The model learns all facial animations directly from the data without relying on pre-built 3D face models. This equips the avatars with realistic facial expressions. The internal avatar latent space can be conveniently used to integrate additional observations of a person via fitting. This enables use-cases where more than one image of a person is available, e.g., from a phone scan of the person. We train jointly on 2D monocular videos and multi-view data. However, in monocular videos, the animation signal leaks the target viewpoint, causing the model to produce incomplete 3D heads. We call this phenomenon entanglement of driving signal and target viewpoint. To prevent entanglement, we introduce bias sinks. These are learnable tokens that indicate whether a training sample stems from a monocular or a multi-view dataset. During training, the model learns to produce incomplete 3D heads only when the monocular token is present. During inference, FlexAvatar then always uses the multi-view token for which the model has learned to produce complete 3D heads. This simple design allows to combine the generalizability from monocular data with the quality of multi-view data. FlexAvatar summary: - Input: Single-image, phone scan, or monocular video - Output: Full 360° head avatar - Expressive animations - Real-time rendering and animation - Generalization to any portrait - Create a new avatar in 2 minutes - Use bias sinks to combine 2D and 3D data 🏠 🌍 🎥 Great work by Tobias Kirschstein and Simon Giebenhain!
0:30

Want to create an avatar from a single image? FlexAvatar is a transformer model that creates full 360°, high-quality, and expressive 3D head avatar from just a single portrait image in minutes. Real-time Demo: FlexAvatar's lightweight architecture allows both animation and rendering in real-time, enabling interactive user experiences. To create a new 3D head avatar, only one image is required, e.g., from a webcam. The final avatar is ready after 2 minutes. Architecture: Under the hood, FlexAvatar adopts a transformer-based encoder-decoder design. The encoder maps the input image onto a latent avatar space, while the decoder produces 3D Gaussian attribute maps by incorporating the animation signal via cross-attention. The model learns all facial animations directly from the data without relying on pre-built 3D face models. This equips the avatars with realistic facial expressions. The internal avatar latent space can be conveniently used to integrate additional observations of a person via fitting. This enables use-cases where more than one image of a person is available, e.g., from a phone scan of the person. We train jointly on 2D monocular videos and multi-view data. However, in monocular videos, the animation signal leaks the target viewpoint, causing the model to produce incomplete 3D heads. We call this phenomenon entanglement of driving signal and target viewpoint. To prevent entanglement, we introduce bias sinks. These are learnable tokens that indicate whether a training sample stems from a monocular or a multi-view dataset. During training, the model learns to produce incomplete 3D heads only when the monocular token is present. During inference, FlexAvatar then always uses the multi-view token for which the model has learned to produce complete 3D heads. This simple design allows to combine the generalizability from monocular data with the quality of multi-view data. FlexAvatar summary: - Input: Single-image, phone scan, or monocular video - Output: Full 360° head avatar - Expressive animations - Real-time rendering and animation - Generalization to any portrait - Create a new avatar in 2 minutes - Use bias sinks to combine 2D and 3D data 🏠 🌍 🎥 Great work by Tobias Kirschstein and Simon Giebenhain!

Matthias Niessner

96,371 görüntüleme • 9 ay önce

New clean 3D AI workflow Control Rig physics in UEFN! Been exploring some more hybrid AI workflows lately, and for 3D assets splitting the model into parts is kinda essential. This video shows my first test using AssetHub, one of the cleanest ways i've used to keep the whole generation process organized. It auto-detected the pose in my main image and broke it down into parts, then generated images for each. From there I can just iterate on each piece separately and generate the 3D models in one workflow. AssetHub is still in closed beta atm, so let me know if you want to try it out. Main reference image came from Grok Imagine. All the part images and high poly meshes were done in AssetHub, selected Tripo 3.1 as the main model. After that I ran it through Hunyuan 3D for retopo + unwrap. Final assembly in Blender. Baked normals from high to low poly. End result: under 60K tris, 3 materials, 2K textures. Also Control Rig physics in Unreal Engine are insane. It finally validates in UEFN too, so of course I had to test it out.
1:17

New clean 3D AI workflow Control Rig physics in UEFN! Been exploring some more hybrid AI workflows lately, and for 3D assets splitting the model into parts is kinda essential. This video shows my first test using AssetHub, one of the cleanest ways i've used to keep the whole generation process organized. It auto-detected the pose in my main image and broke it down into parts, then generated images for each. From there I can just iterate on each piece separately and generate the 3D models in one workflow. AssetHub is still in closed beta atm, so let me know if you want to try it out. Main reference image came from Grok Imagine. All the part images and high poly meshes were done in AssetHub, selected Tripo 3.1 as the main model. After that I ran it through Hunyuan 3D for retopo + unwrap. Final assembly in Blender. Baked normals from high to low poly. End result: under 60K tris, 3 materials, 2K textures. Also Control Rig physics in Unreal Engine are insane. It finally validates in UEFN too, so of course I had to test it out.

Jerome | InsaneUnreal

83,297 görüntüleme • 5 ay önce

World Model is trending— let's revisit our HunyuanWorld journey. We’ve been pioneering open-source 3D world generation in the past two months, and this ride’s only getting started. 🌍 📅 July: HunyuanWorld 1.0 📌 First open-source 3D world model compatible with CG pipelines (Unity/Unreal/Blender) 📌 Hit 2K+ GitHub stars in just two months ⭐—thank you for the love! 📅 August: 1.0-Lite 📌Same top-tier quality, running on consumer GPUs! 📅 September: 1.0-Voyager 📌 Direct 3D output + world memory—taking exploration further! Seamlessly integrated into CG pipelines with layered 3D modeling (assets, terrain, skybox) and fully open-sourced.. we’re fully committed to building open-source spatial intelligence for all! 🚀 💡 Why it matters? ✅ Seamless CG Pipeline Integration: Export generated 3D scenes as standard mesh formats, effortlessly integrating into industry-standard tools like Blender, Unity, and Unreal Engine for direct editing, animation, and physical simulation. ✅ Hierarchical Scene Editing: Deconstruct scenes into semantic layers (sky, background, foreground objects) via instance recognition and layer decomposition, allowing for atomic-level control—independently modify, relocate, or replace objects without rebuilding the entire world. Project page: Github: Amazing creations by Stijn Spanhove camenduru GENEL | AIを用いた動画制作 apolinario 🌐 とりにく Directive Creator 🪥 👇 #AI #3DGeneration #OpenSource #WorldModels #Hunyuan3D #HunyuanWorld
0:28

World Model is trending— let's revisit our HunyuanWorld journey. We’ve been pioneering open-source 3D world generation in the past two months, and this ride’s only getting started. 🌍 📅 July: HunyuanWorld 1.0 📌 First open-source 3D world model compatible with CG pipelines (Unity/Unreal/Blender) 📌 Hit 2K+ GitHub stars in just two months ⭐—thank you for the love! 📅 August: 1.0-Lite 📌Same top-tier quality, running on consumer GPUs! 📅 September: 1.0-Voyager 📌 Direct 3D output + world memory—taking exploration further! Seamlessly integrated into CG pipelines with layered 3D modeling (assets, terrain, skybox) and fully open-sourced.. we’re fully committed to building open-source spatial intelligence for all! 🚀 💡 Why it matters? ✅ Seamless CG Pipeline Integration: Export generated 3D scenes as standard mesh formats, effortlessly integrating into industry-standard tools like Blender, Unity, and Unreal Engine for direct editing, animation, and physical simulation. ✅ Hierarchical Scene Editing: Deconstruct scenes into semantic layers (sky, background, foreground objects) via instance recognition and layer decomposition, allowing for atomic-level control—independently modify, relocate, or replace objects without rebuilding the entire world. Project page: Github: Amazing creations by Stijn Spanhove camenduru GENEL | AIを用いた動画制作 apolinario 🌐 とりにく Directive Creator 🪥 👇 #AI #3DGeneration #OpenSource #WorldModels #Hunyuan3D #HunyuanWorld

Tencent HY

20,178 görüntüleme • 1 yıl önce

I've been a proponent of the idea of combining 3d and generative ai for a long time - as a way to get the best of both worlds: The precision and control of 3d - the detail, realism, lighting and speed of generative models. Here's another example of that idea, realized through a procedural system - entirely vibe-coded with Fable. Inspired by a photograph I took of an old tower in a town in southern France. In the first part of the video I'm using Krea AI's realtime model - later examples show how Nano Banana 2 can be used to take 3d stills and transform them to pretty much anything. What do you think of workflows like this compared to purely generating video or images from text, image or video input?
0:34

I've been a proponent of the idea of combining 3d and generative ai for a long time - as a way to get the best of both worlds: The precision and control of 3d - the detail, realism, lighting and speed of generative models. Here's another example of that idea, realized through a procedural system - entirely vibe-coded with Fable. Inspired by a photograph I took of an old tower in a town in southern France. In the first part of the video I'm using Krea AI's realtime model - later examples show how Nano Banana 2 can be used to take 3d stills and transform them to pretty much anything. What do you think of workflows like this compared to purely generating video or images from text, image or video input?

Martin Nebelong

20,265 görüntüleme • 1 ay önce

Tripo raised ~3B yuan (Series B + B+, led by MPCi) and dropped the preview of P2.0 at #Gamescom2026. The headline feature is native quad topology in seconds, which is a first for any 3D foundation model. If you've ever had to manually retopo a generated mesh before it was riggable, you know why that matters. Also pushing up to 50K triangles / 25K quads with cleaner edge flow, so output is actually usable for rigging/animation, not just a pretty render. You can try it yourself - 2 free gens in Tripo Studio:
0:24

Tripo raised ~3B yuan (Series B + B+, led by MPCi) and dropped the preview of P2.0 at #Gamescom2026. The headline feature is native quad topology in seconds, which is a first for any 3D foundation model. If you've ever had to manually retopo a generated mesh before it was riggable, you know why that matters. Also pushing up to 50K triangles / 25K quads with cleaner edge flow, so output is actually usable for rigging/animation, not just a pretty render. You can try it yourself - 2 free gens in Tripo Studio:

Tyler Wayne

80,879 görüntüleme • 13 gün önce

I still can't believe it. I have the pleasure to announce that I created the intro for Penny Parker's latest REAL TIME FANDUB: KINGDOM HEARTS - DO NO HARM. Being able to work closely with Penny on a fandub was a dream come true. Credits: Music by: Penny Parker | ❤️ jamie p! 💚 | Marcy Nabors Intro/3D Animation/Motion Graphics by: ๖̶̶̶ζ͜͡𝑵𝑨𝑻𝑬𝑿𝑰𝑰☆ Sora, Kairi, Riku, Donald, and Goofy art by: ||Ani☀️|| CLERITH NATION 3D Models/Rigs by: @caehum | KylieStylishWorkshop Everyone involved in this video is immensely talented. From ||Ani☀️|| CLERITH NATION's gorgeous custom art of the Destiny Trio as well as Donald and Goofy, to the lovely music created by Penny Parker, ❤️ jamie p! 💚, and Marcy Nabors (I LOVE BIRDBRAIN, SO WORKING WITH YOUR MUSIC IN AN OFFICIAL CAPACITY WAS AN ABSOLUTE TREAT), to @caehum & KylieStylish's gorgeous and models/rigs. This wouldn't be possible without all of them! PLEASE ENJOY LONG AWAITED RELEASE OF DO NO HARM: A KINGDOM HEARTS REAL TIME FANDUB.
1:23

I still can't believe it. I have the pleasure to announce that I created the intro for Penny Parker's latest REAL TIME FANDUB: KINGDOM HEARTS - DO NO HARM. Being able to work closely with Penny on a fandub was a dream come true. Credits: Music by: Penny Parker | ❤️ jamie p! 💚 | Marcy Nabors Intro/3D Animation/Motion Graphics by: ๖̶̶̶ζ͜͡𝑵𝑨𝑻𝑬𝑿𝑰𝑰☆ Sora, Kairi, Riku, Donald, and Goofy art by: ||Ani☀️|| CLERITH NATION 3D Models/Rigs by: @caehum | KylieStylishWorkshop Everyone involved in this video is immensely talented. From ||Ani☀️|| CLERITH NATION's gorgeous custom art of the Destiny Trio as well as Donald and Goofy, to the lovely music created by Penny Parker, ❤️ jamie p! 💚, and Marcy Nabors (I LOVE BIRDBRAIN, SO WORKING WITH YOUR MUSIC IN AN OFFICIAL CAPACITY WAS AN ABSOLUTE TREAT), to @caehum & KylieStylish's gorgeous and models/rigs. This wouldn't be possible without all of them! PLEASE ENJOY LONG AWAITED RELEASE OF DO NO HARM: A KINGDOM HEARTS REAL TIME FANDUB.

๖̶̶̶ζ͜͡𝑵𝑨𝑻𝑬𝑿𝑰𝑰☆

113,975 görüntüleme • 11 ay önce

Here are 10 AI video editor GitHub repos worth bookmarking: 1. Shotcut Most actively maintained open source video editor in 2026. 14K stars. Cross-platform with AI-assisted features. Just shipped a new release April 30, 2026. 2. Kdenlive The closest open source alternative to Adobe Premiere Pro. Multi-track editing, proxy editing, VST audio, and customizable workspace. Best for professional workflows. 3. OpenShot The easiest entry point for beginners. Drag and drop, 400+ transitions, 3D titles, and AI-assisted trimming. 5,700 stars. 4. Blender Not just 3D. Blender's video sequence editor and compositing pipeline is used in professional film production. 18,300 stars. Unmatched for VFX. 5. Recordly Screen recorder with auto-zoom, cursor polish, webcam overlays, and styled frames built in. Built for demo videos and walkthroughs. 6. Wan2.1 Alibaba's open source text-to-video model. Cinema-grade 1080p generation. Apache 2.0. The gold standard for open source video generation in 2026. 7. HunyuanVideo Tencent's 13B parameter open source video model. 11.9K stars. Handles 720p and 1080p with high temporal coherence. 8. CogVideoX Apache 2.0 licensed. Loads natively via Hugging Face Diffusers. Strong prompt following and smooth frame transitions. Needs 16GB VRAM minimum. 12.5K stars. 9. Open-Sora Most starred open source video generation project at 24K stars. Full training pipeline for $200K. Production-level output quality. 10. Mochi 1 Focused entirely on motion quality. The most natural-looking physics of any open source video model. Water, fabric, and human gestures without AI jitter. Apache 2.0.
1:18

Here are 10 AI video editor GitHub repos worth bookmarking: 1. Shotcut Most actively maintained open source video editor in 2026. 14K stars. Cross-platform with AI-assisted features. Just shipped a new release April 30, 2026. 2. Kdenlive The closest open source alternative to Adobe Premiere Pro. Multi-track editing, proxy editing, VST audio, and customizable workspace. Best for professional workflows. 3. OpenShot The easiest entry point for beginners. Drag and drop, 400+ transitions, 3D titles, and AI-assisted trimming. 5,700 stars. 4. Blender Not just 3D. Blender's video sequence editor and compositing pipeline is used in professional film production. 18,300 stars. Unmatched for VFX. 5. Recordly Screen recorder with auto-zoom, cursor polish, webcam overlays, and styled frames built in. Built for demo videos and walkthroughs. 6. Wan2.1 Alibaba's open source text-to-video model. Cinema-grade 1080p generation. Apache 2.0. The gold standard for open source video generation in 2026. 7. HunyuanVideo Tencent's 13B parameter open source video model. 11.9K stars. Handles 720p and 1080p with high temporal coherence. 8. CogVideoX Apache 2.0 licensed. Loads natively via Hugging Face Diffusers. Strong prompt following and smooth frame transitions. Needs 16GB VRAM minimum. 12.5K stars. 9. Open-Sora Most starred open source video generation project at 24K stars. Full training pipeline for $200K. Production-level output quality. 10. Mochi 1 Focused entirely on motion quality. The most natural-looking physics of any open source video model. Water, fabric, and human gestures without AI jitter. Apache 2.0.

Kanika

17,726 görüntüleme • 3 ay önce

I got this custom scorpion rigged, animated and running in my game in one full day with AI. GPT-6 built the entire rig. My part was preparing the model and motion references, then giving feedback. After trying a few approaches, I found a workflow that worked: 1. Give it a model that makes sense. I generated the model with Tripo P2.0, then cleaned it up myself. Low-poly, optimized, split into logical parts. I think that preparation mattered a lot. GPT-6 works on the mesh through code. A manageable vertex count and sensible parts give it a clearer starting point for bone placement and skinning. 2. Show it the movement you want. I took a reference image of the character and used Seedance to generate side-view animation videos. I decided which animations the game needed and selected the takes with the movements I liked. Then I gave GPT-6 the model, the videos and that animation list. There was no existing rig to start from. 3. Compare the animation frame by frame. This was the idea I wanted to test: ask GPT-6 to compare its Blender animation against the reference video frame by frame, from the same view. That gave it concrete poses and timing to work toward. I could point to where the feet should be planted or when the tail should strike. 4. Expect to give feedback. A generated run can look like hopping. An attack can start with a jump you never wanted. Choosing the references matters, and a side view still leaves depth and hidden legs to figure out. It took several iterations. I explained what looked wrong and how I wanted it to move, and GPT-6 kept refining the animation. Once the walk worked, I also had it create left and right strafe animations procedurally from that walk. Those didn't need their own reference videos. By the end of the day, the creature was in Unity. I've recorded the full workflow, including the Blender setup and feedback process:
0:59

I got this custom scorpion rigged, animated and running in my game in one full day with AI. GPT-6 built the entire rig. My part was preparing the model and motion references, then giving feedback. After trying a few approaches, I found a workflow that worked: 1. Give it a model that makes sense. I generated the model with Tripo P2.0, then cleaned it up myself. Low-poly, optimized, split into logical parts. I think that preparation mattered a lot. GPT-6 works on the mesh through code. A manageable vertex count and sensible parts give it a clearer starting point for bone placement and skinning. 2. Show it the movement you want. I took a reference image of the character and used Seedance to generate side-view animation videos. I decided which animations the game needed and selected the takes with the movements I liked. Then I gave GPT-6 the model, the videos and that animation list. There was no existing rig to start from. 3. Compare the animation frame by frame. This was the idea I wanted to test: ask GPT-6 to compare its Blender animation against the reference video frame by frame, from the same view. That gave it concrete poses and timing to work toward. I could point to where the feet should be planted or when the tail should strike. 4. Expect to give feedback. A generated run can look like hopping. An attack can start with a jump you never wanted. Choosing the references matters, and a side view still leaves depth and hidden legs to figure out. It took several iterations. I explained what looked wrong and how I wanted it to move, and GPT-6 kept refining the animation. Once the walk worked, I also had it create left and right strafe animations procedurally from that walk. Those didn't need their own reference videos. By the end of the day, the creature was in Unity. I've recorded the full workflow, including the Blender setup and feedback process:

Stefan 3D AI

12,563 görüntüleme • 8 gün önce

In my career, I've spent over $100,000 commissioning artists and animators. I held a fundraiser for animators in Japan. I've given graphic tablets to artists in need. I promote young animators that I think are talented without asking for anything in return. I created an original series (Demon Rush), with 15 manga chapters and 2 animated promo episodes- all original art and animation. Spent 4 years on it, but was not recognized for doing it the true hard way. In my latest video, I hired 3 animators and paid them well for their cuts. People on X are upset that I used AI to speed up the process in the fan animation, even though in the 4 update videos leading up to it, I was completely open about how I was using it. The same people who complained about Saitama vs Cosmic Garou having too many impact frames for their liking. I don't care about these people. They complain about literally everything. I make these for fun, not to impress anyone. Even if I spent 10 years making the best episode possible, 100% hand done, these guys would still complain. I did that before with Demon Rush. In any case, this was my last animated video. I am retiring from anime and moving onto other things, so you won't have to worry about me.
1:59

In my career, I've spent over $100,000 commissioning artists and animators. I held a fundraiser for animators in Japan. I've given graphic tablets to artists in need. I promote young animators that I think are talented without asking for anything in return. I created an original series (Demon Rush), with 15 manga chapters and 2 animated promo episodes- all original art and animation. Spent 4 years on it, but was not recognized for doing it the true hard way. In my latest video, I hired 3 animators and paid them well for their cuts. People on X are upset that I used AI to speed up the process in the fan animation, even though in the 4 update videos leading up to it, I was completely open about how I was using it. The same people who complained about Saitama vs Cosmic Garou having too many impact frames for their liking. I don't care about these people. They complain about literally everything. I make these for fun, not to impress anyone. Even if I spent 10 years making the best episode possible, 100% hand done, these guys would still complain. I did that before with Demon Rush. In any case, this was my last animated video. I am retiring from anime and moving onto other things, so you won't have to worry about me.

Mastar

75,395 görüntüleme • 4 ay önce

A 20 YEAR OLD IS MAKING $20,000 A MONTH WITH THE LAZIEST BUSINESS MODEL ON THE INTERNET. SHE WORKS TWENTY MINUTES A DAY FROM HER CAR. SHE HAS NEVER PRODUCED AN ORIGINAL IDEA. Children's YouTube is a goldmine. Channels with simple songs and bright colors pull hundreds of millions of views. Traditional studios spend a fortune to animate them. She spends zero dollars and does it from the driver's seat. She opens YouTube on her phone. She finds a viral baby video with millions of views. She copies the link. She uses a free tool to rip the entire transcript of the video. She takes that transcript and pastes it into an AI platform called Swagga. She types one sentence: "Make me a prompt for a similar video using this as inspiration." The AI acts as her creative director. It analyzes the viral song and spits out a highly detailed master prompt for a new, original 3D animation. She copies the prompt. She switches to the video generator tab. She selects Sora 2 and hits generate. Three minutes later, the AI outputs a fully rendered, broadcast-ready 3D animation. A brightly colored, musical video designed specifically to capture the attention of a toddler. She downloads it. She posts it. She puts her car in drive. The entire process takes twenty minutes. Her channel pulls in thousands of dollars a week in AdSense. She is running a complete children's television network without an office, without animators, and without original ideas. The traditional creator economy is obsessed with authenticity and hard work. The ghost economy is obsessed with leverage. Most people will watch her video and call it lazy. A few will open a new tab.
0:56

A 20 YEAR OLD IS MAKING $20,000 A MONTH WITH THE LAZIEST BUSINESS MODEL ON THE INTERNET. SHE WORKS TWENTY MINUTES A DAY FROM HER CAR. SHE HAS NEVER PRODUCED AN ORIGINAL IDEA. Children's YouTube is a goldmine. Channels with simple songs and bright colors pull hundreds of millions of views. Traditional studios spend a fortune to animate them. She spends zero dollars and does it from the driver's seat. She opens YouTube on her phone. She finds a viral baby video with millions of views. She copies the link. She uses a free tool to rip the entire transcript of the video. She takes that transcript and pastes it into an AI platform called Swagga. She types one sentence: "Make me a prompt for a similar video using this as inspiration." The AI acts as her creative director. It analyzes the viral song and spits out a highly detailed master prompt for a new, original 3D animation. She copies the prompt. She switches to the video generator tab. She selects Sora 2 and hits generate. Three minutes later, the AI outputs a fully rendered, broadcast-ready 3D animation. A brightly colored, musical video designed specifically to capture the attention of a toddler. She downloads it. She posts it. She puts her car in drive. The entire process takes twenty minutes. Her channel pulls in thousands of dollars a week in AdSense. She is running a complete children's television network without an office, without animators, and without original ideas. The traditional creator economy is obsessed with authenticity and hard work. The ghost economy is obsessed with leverage. Most people will watch her video and call it lazy. A few will open a new tab.

ZER

126,725 görüntüleme • 2 ay önce

What would a World Model look like if we start from a real embodied agent acting in the real world? It has to have: 1) A real, physically grounded and complex action space—not just abstract control signals. 2) Diverse, real-life scenarios and activities. Or in short: It has to be annoyingly complex—in both the action and vision space—to even get close to real life. We did an initial attempt: Whole-Body Conditioned Egocentric Video Prediction. In collaboration with @dans_t123 , Amir Bar, Yann LeCun , trevordarrell and Jitendra MALIK. (For more details, check: What we did is very simple: Predict Egocentric Video from human Actions (PEVA) - Given the past video and a future action represented by relative 3D body pose, PEVA predicts how the world looks next—from the first-person view. By conditioning on kinematic pose trajectories, structured by the joint hierarchy of the body, it learns how physical actions shape perception.
3:12

What would a World Model look like if we start from a real embodied agent acting in the real world? It has to have: 1) A real, physically grounded and complex action space—not just abstract control signals. 2) Diverse, real-life scenarios and activities. Or in short: It has to be annoyingly complex—in both the action and vision space—to even get close to real life. We did an initial attempt: Whole-Body Conditioned Egocentric Video Prediction. In collaboration with @dans_t123 , Amir Bar, Yann LeCun , trevordarrell and Jitendra MALIK. (For more details, check: What we did is very simple: Predict Egocentric Video from human Actions (PEVA) - Given the past video and a future action represented by relative 3D body pose, PEVA predicts how the world looks next—from the first-person view. By conditioning on kinematic pose trajectories, structured by the joint hierarchy of the body, it learns how physical actions shape perception.

Yutong Bai

179,696 görüntüleme • 1 yıl önce

Wow. Recreating the Shawshank Redemption prison in 3D from a single video, in real time (!) Just read the MASt3R-SLAM paper and it's pretty neat. These folks basically built a real-time dense SLAM system on top of MASt3R, which is a transformer-based neural network that can do 3d reconstruction and localization from uncalibrated image pairs. The cool part is they don't need a fixed camera model -- it just works with arbitrary cameras -- think different focal lengths, sensor sizes, even handling zooming in video (FMV drone video anyone?!). If you've done photogrammetry or played with NeRFs you know that is a HUGE deal. They've solved some tricky problems like efficient point matching and tracking, plus they've figured out how to fuse point clouds and handle loop closures in real-time. Their system runs at about 15 FPS on a 4090 and produces both camera poses and dense geometry. When they know the camera calibration, they get SOTA results across several benchmarks, but even without calibration, they still perform well. What's interesting is the approach -- most recent SLAM work has built on DROID-SLAM's architecture, but these folks went a different direction by leveraging a strong 3D reconstruction prior. Seems to give them more coherent geometry, which makes sense since that's what MASt3R was designed for. For anyone who cares about monocular SLAM and 3D reconstruction, this feels like a significant step toward plug-and-play dense SLAM without calibration headaches -- perfect for drones, robots, AR/VR -- the works!
0:29

Wow. Recreating the Shawshank Redemption prison in 3D from a single video, in real time (!) Just read the MASt3R-SLAM paper and it's pretty neat. These folks basically built a real-time dense SLAM system on top of MASt3R, which is a transformer-based neural network that can do 3d reconstruction and localization from uncalibrated image pairs. The cool part is they don't need a fixed camera model -- it just works with arbitrary cameras -- think different focal lengths, sensor sizes, even handling zooming in video (FMV drone video anyone?!). If you've done photogrammetry or played with NeRFs you know that is a HUGE deal. They've solved some tricky problems like efficient point matching and tracking, plus they've figured out how to fuse point clouds and handle loop closures in real-time. Their system runs at about 15 FPS on a 4090 and produces both camera poses and dense geometry. When they know the camera calibration, they get SOTA results across several benchmarks, but even without calibration, they still perform well. What's interesting is the approach -- most recent SLAM work has built on DROID-SLAM's architecture, but these folks went a different direction by leveraging a strong 3D reconstruction prior. Seems to give them more coherent geometry, which makes sense since that's what MASt3R was designed for. For anyone who cares about monocular SLAM and 3D reconstruction, this feels like a significant step toward plug-and-play dense SLAM without calibration headaches -- perfect for drones, robots, AR/VR -- the works!

Bilawal Sidhu

704,241 görüntüleme • 1 yıl önce

Only if education could be this interactive ❤️‍🔥 I've had a looong wish to build something genuinely useful through vibe coding, and I finally did it. A 3D human anatomy application built with Three.js using GPT 5.6 Sol. It all started with a single design image that I created using GPT Image 2.0. I then used it to generate every 3D organ image, one by one. Next, I converted each of those images into 3D models using Tripo (and no, they didn't sponsor this 😄). After that, I opened Codex, wrote a master prompt based on the design, and gave it the prompt, the design image, and all the 3D models. Codex built the first version beautifully, but there was one big problem. Every single 3D model was nearly 120-150 MB. That obviously wasn't practical for the web and was giving a performance of 16fps. After a few iterations, Codex optimized each model down to roughly 2–5.5 MB while preserving the visual quality, reducing the total asset size from ~900 MB to just 28.6 MB. And each model loads on demand. Along the way, Codex also generated those anatomical illustrations showing where each organ sits in the human body, and even created the interactive hotspot markers that explain different parts of every organ. It handled all of that. The process wasn't exactly one shot, but it also wasn't difficult. You just have to do it step by step. It genuinely felt like building something that could make learning anatomy much more engaging. The inspiration came from Dilum Sanjaya's 3D animal plant cell project. I remember seeing it and thinking, "I want to build something like this one day." And I did it :D Live: Code:
0:43

Only if education could be this interactive ❤️‍🔥 I've had a looong wish to build something genuinely useful through vibe coding, and I finally did it. A 3D human anatomy application built with Three.js using GPT 5.6 Sol. It all started with a single design image that I created using GPT Image 2.0. I then used it to generate every 3D organ image, one by one. Next, I converted each of those images into 3D models using Tripo (and no, they didn't sponsor this 😄). After that, I opened Codex, wrote a master prompt based on the design, and gave it the prompt, the design image, and all the 3D models. Codex built the first version beautifully, but there was one big problem. Every single 3D model was nearly 120-150 MB. That obviously wasn't practical for the web and was giving a performance of 16fps. After a few iterations, Codex optimized each model down to roughly 2–5.5 MB while preserving the visual quality, reducing the total asset size from ~900 MB to just 28.6 MB. And each model loads on demand. Along the way, Codex also generated those anatomical illustrations showing where each organ sits in the human body, and even created the interactive hotspot markers that explain different parts of every organ. It handled all of that. The process wasn't exactly one shot, but it also wasn't difficult. You just have to do it step by step. It genuinely felt like building something that could make learning anatomy much more engaging. The inspiration came from Dilum Sanjaya's 3D animal plant cell project. I remember seeing it and thinking, "I want to build something like this one day." And I did it :D Live: Code:

The Bugged Dev

2,102,329 görüntüleme • 1 ay önce

[NEW] a16z a16z speedrun 🧊 request for startups: Vibe Creation Platforms We've seen Vibe Coding platforms like Lovable and Bolt emerge for application development serving non-coding consumers --> We'll soon see VIBE CREATION as an entirely new consumer experience for crafting video, visual stories, games, and more The platform will require an end-to-end workflow orchestrated by AI agents --> Today, we have the infrastructure with foundation models across modalities, but most consumers won't jump from model site to model site to then stitch their creations together The winning solution will help consumers go from idea to first draft in minutes while enabling finer creative control for those that seek it --> This is how we go from AI internet memes to compelling human stories AI Vibe Creation platforms are designed for fun and creative flow. They remove the million knobs and sliders professional creators have come to expect --> They feel more like a game than a tool a16z speedrun has already invested in a few teams exploring this space: - VIDEO: Hedra (animated characters), intangible (canva for 3D) - GAMING: Rosebud AI (game generation), Nilo Technologies (3D worldbuilding) - IMAGE: (infinite canvas), Blank (instagram for AI), - VISUAL STORIES: Komiko (anime), Sekai (tiktok for interactive stories) We believe there will be many great vibe creation platforms to be built across medium (video, music, game, etc), genre/niche (anime, 3D, sports) and platform (mobile, web, XR) if you're building in this space, DM us and apply for speedrun!
1:51

[NEW] a16z a16z speedrun 🧊 request for startups: Vibe Creation Platforms We've seen Vibe Coding platforms like Lovable and Bolt emerge for application development serving non-coding consumers --> We'll soon see VIBE CREATION as an entirely new consumer experience for crafting video, visual stories, games, and more The platform will require an end-to-end workflow orchestrated by AI agents --> Today, we have the infrastructure with foundation models across modalities, but most consumers won't jump from model site to model site to then stitch their creations together The winning solution will help consumers go from idea to first draft in minutes while enabling finer creative control for those that seek it --> This is how we go from AI internet memes to compelling human stories AI Vibe Creation platforms are designed for fun and creative flow. They remove the million knobs and sliders professional creators have come to expect --> They feel more like a game than a tool a16z speedrun has already invested in a few teams exploring this space: - VIDEO: Hedra (animated characters), intangible (canva for 3D) - GAMING: Rosebud AI (game generation), Nilo Technologies (3D worldbuilding) - IMAGE: (infinite canvas), Blank (instagram for AI), - VISUAL STORIES: Komiko (anime), Sekai (tiktok for interactive stories) We believe there will be many great vibe creation platforms to be built across medium (video, music, game, etc), genre/niche (anime, 3D, sports) and platform (mobile, web, XR) if you're building in this space, DM us and apply for speedrun!

Troy Kirwin

138,788 görüntüleme • 1 yıl önce

Jason Ma reveals the first true scaling law in robotics: robots trained on 1 million hours of first-person human video predictably get better without ever seeing robot data "Yesterday we announced our new flagship robot foundation model called Dyna-2. It's very significant for the entire field for many different reasons. First of all, it's the first robot foundation model trained on at least one million hours of data. That in itself is a very challenging infrastructure challenge." "What we demonstrated is that even if the one million hours of data is entirely first-person video of humans doing manipulation tasks, we actually see scaling law for transferring to robot embodiments that the model has never seen before." "By training on more human data, we actually see predictable performance improvement on robots. That's a big deal because the biggest challenge facing robot foundation models is that we don't have enough data." "Unlike language models, there are just not enough robotics data out there, and it's very difficult to collect these robot data. Only by passively observing humans doing things can we scale this kind of data, and this is the first time we showed there is a lot of improvement that can transfer." Jason Ma Dyna Robotics
1:14

Jason Ma reveals the first true scaling law in robotics: robots trained on 1 million hours of first-person human video predictably get better without ever seeing robot data "Yesterday we announced our new flagship robot foundation model called Dyna-2. It's very significant for the entire field for many different reasons. First of all, it's the first robot foundation model trained on at least one million hours of data. That in itself is a very challenging infrastructure challenge." "What we demonstrated is that even if the one million hours of data is entirely first-person video of humans doing manipulation tasks, we actually see scaling law for transferring to robot embodiments that the model has never seen before." "By training on more human data, we actually see predictable performance improvement on robots. That's a big deal because the biggest challenge facing robot foundation models is that we don't have enough data." "Unlike language models, there are just not enough robotics data out there, and it's very difficult to collect these robot data. Only by passively observing humans doing things can we scale this kind of data, and this is the first time we showed there is a lot of improvement that can transfer." Jason Ma Dyna Robotics

MTS

17,740 görüntüleme • 1 ay önce

How many of you actually know how "what you eat" grows? 🤔 I never learned crop science in school. I learned it by walking around our farm with my father, who showed me different crops and explained how they grow. But not everyone has access to a farm, so I built a 3D Crop Science application in Three.js using Claude Opus 5 to make that learning experience more visual and interactive. It is an exploration of different types of seeds where each seed has three different stages. The first stage shows the whole seed. The second stage is a cross section that shows what is inside the seed and how it grows. The third stage shows the germination phase through a 3D model. There are 24 models in total. The original models were 1,349.6 MB, which Claude optimized down to just 11.6 MB in total. All of the 3D models were generated using Tripo. Claude also created visual information for each seed showing details like seed type, storage tissue and germination phase. Each seed also has a YouTube video that shows how it actually grows in the real world. There is also a section showing where each seed is commonly grown using both a 3D globe and a flat map. You can explore different regions and click on specific areas to see more information about where that seed is grown. The entire experience is fully responsive and also includes quizzes that you can take in both normal and 3D formats. I strongly believe education becomes much more effective when you can see, interact, watch and explore instead of relying only on textbooks. Live: Code:
1:14

How many of you actually know how "what you eat" grows? 🤔 I never learned crop science in school. I learned it by walking around our farm with my father, who showed me different crops and explained how they grow. But not everyone has access to a farm, so I built a 3D Crop Science application in Three.js using Claude Opus 5 to make that learning experience more visual and interactive. It is an exploration of different types of seeds where each seed has three different stages. The first stage shows the whole seed. The second stage is a cross section that shows what is inside the seed and how it grows. The third stage shows the germination phase through a 3D model. There are 24 models in total. The original models were 1,349.6 MB, which Claude optimized down to just 11.6 MB in total. All of the 3D models were generated using Tripo. Claude also created visual information for each seed showing details like seed type, storage tissue and germination phase. Each seed also has a YouTube video that shows how it actually grows in the real world. There is also a section showing where each seed is commonly grown using both a 3D globe and a flat map. You can explore different regions and click on specific areas to see more information about where that seed is grown. The entire experience is fully responsive and also includes quizzes that you can take in both normal and 3D formats. I strongly believe education becomes much more effective when you can see, interact, watch and explore instead of relying only on textbooks. Live: Code:

The Bugged Dev

45,081 görüntüleme • 1 ay önce