正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Blendshape Viewer has been updated to V3. This tool lets you visualize which area of a model is affected by a blendshape, and change its value. From now on, you can press the ALT key to compare the blendshape. This version should also run faster on models with lots... show more

Haï~

13,591 subscribers

21,116 次观看 • 6 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Fluffgan Facetracking is here!! This is my own take on Fluffgan FT! Ears were done by Lunak! I love how this one turned out, I've been using the Fluffgan a LOT. The add-on also includes an optional face-edit blendshape! See reply for comparison. Public avatar on product page!

Royalty

16,687 次观看 • 4 个月前

The west presents to you two models of Islam, a Takfiri version and a secular version. This is exactly how the Syrian terrorist revolution transitioned; from Takfiri’s to a secular version of Islam which sits comfortably with the butcherers of Palestine.

The west presents to you two models of Islam, a Takfiri version and a secular version. This is exactly how the Syrian terrorist revolution transitioned; from Takfiri’s to a secular version of Islam which sits comfortably with the butcherers of Palestine.

Disputing Sunnah

23,851 次观看 • 20 天前

The value produced by models is getting so much better so fast that old hardware is actually getting *more* expensive to rent. 3 years ago, the best model you could run on a H100 chip was GPT-4. Now, you can run GPT-5.4 on it, which is smaller and cheaper to run while producing much more valuable tokens. w. Dylan Patel

The value produced by models is getting so much better so fast that old hardware is actually getting more expensive to rent. 3 years ago, the best model you could run on a H100 chip was GPT-4. Now, you can run GPT-5.4 on it, which is smaller and cheaper to run while producing much more valuable tokens. w. Dylan Patel

Dwarkesh Patel

78,277 次观看 • 4 个月前

I made a stick shift claude code app Its very fun, suppose you are working on a complex project with fable and suddenly you wanna change the model to sonnet to do a simple "can you git push this" Or "can you quickly change the color of this button" Its for everyone who loves driving a manual automatic mode coming soon. for the rest of you.

I made a stick shift claude code app Its very fun, suppose you are working on a complex project with fable and suddenly you wanna change the model to sonnet to do a simple "can you git push this" Or "can you quickly change the color of this button" Its for everyone who loves driving a manual automatic mode coming soon. for the rest of you.

Milind S

18,831 次观看 • 26 天前

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Santiago

164,162 次观看 • 2 年前

this ad is INSANE before you had to rely on boring stock footage clips to educate the viewer now you can visualize the invisible the pain. the mechanism. the science. all while keeping the viewer HOOKED

this ad is INSANE before you had to rely on boring stock footage clips to educate the viewer now you can visualize the invisible the pain. the mechanism. the science. all while keeping the viewer HOOKED

Tom Hallett

25,623 次观看 • 3 个月前

Slash AI costs by 99%, run 1000+ models on a single GPU! OpenLoRA lets you run thousands of models on one GPU instead of one per model, drastically cutting costs and boosting flexibility. Excited to work with Aethir, Hyperbolic for infrastructure and for verifiability. Watch the demo:

Slash AI costs by 99%, run 1000+ models on a single GPU! OpenLoRA lets you run thousands of models on one GPU instead of one per model, drastically cutting costs and boosting flexibility. Excited to work with Aethir, Hyperbolic for infrastructure and for verifiability. Watch the demo:

OpenLedger

155,290 次观看 • 1 年前

Tired of guessing which AI model is best? 🤔 We've got you covered! 👀 Here's a sneak peek of our new model comparison feature in action! Run the same prompt across multiple models and see which one works best for YOU. Which models are you excited to test? #Inferium #AI #Inference #Compare

Tired of guessing which AI model is best? 🤔 We've got you covered! 👀 Here's a sneak peek of our new model comparison feature in action! Run the same prompt across multiple models and see which one works best for YOU. Which models are you excited to test? #Inferium #AI #Inference #Compare

Inferium

12,329 次观看 • 1 年前

Most people think of rollbacks all wrong! They think the point of a rollback is to be quicker on your rollback than your opponent. The fact is, at the higher levels athleticism is pretty equal and you can’t rely on this! The way you should think of your rollback is by making your guy overrun you! Using the deception of hesitation moves, you can get a step and make your guy late. When he’s late, now he has to really accelerate to catch up. One key is using deception in your rollback posture to sell go while you’re rolling back. It doesn’t even matter if he’s faster than you, you’re still going to destroy him on your rollback if you can get him to overrun you! There are lots of different kinds of hesitations you can use, but this is more of a concept! Tell me if you know how to do this.

Most people think of rollbacks all wrong! They think the point of a rollback is to be quicker on your rollback than your opponent. The fact is, at the higher levels athleticism is pretty equal and you can’t rely on this! The way you should think of your rollback is by making your guy overrun you! Using the deception of hesitation moves, you can get a step and make your guy late. When he’s late, now he has to really accelerate to catch up. One key is using deception in your rollback posture to sell go while you’re rolling back. It doesn’t even matter if he’s faster than you, you’re still going to destroy him on your rollback if you can get him to overrun you! There are lots of different kinds of hesitations you can use, but this is more of a concept! Tell me if you know how to do this.

JM3 SPORTS

10,541 次观看 • 1 年前

AI has started building its own successors. It's happening right now. Humans still kick most of it off, but the models are already training the next models, and each version builds a better version faster than the last. We know what happens when something gets an advantage and the substrate is there... it proliferates incredibly fast. Soon it just runs the whole process itself. People are still debating whether AI takes your job. That's not the question. You can't compete with this intelligence at all. Next to it the human is negative value, the slowest one in the room. And this is the slowest it will ever move again. It's about to run on its own, faster than we can conceive of, and nobody's prepared for that. Wonderful conversation as ever with Emad.

AI has started building its own successors. It's happening right now. Humans still kick most of it off, but the models are already training the next models, and each version builds a better version faster than the last. We know what happens when something gets an advantage and the substrate is there... it proliferates incredibly fast. Soon it just runs the whole process itself. People are still debating whether AI takes your job. That's not the question. You can't compete with this intelligence at all. Next to it the human is negative value, the slowest one in the room. And this is the slowest it will ever move again. It's about to run on its own, faster than we can conceive of, and nobody's prepared for that. Wonderful conversation as ever with Emad.

Raoul Pal

63,554 次观看 • 6 天前

Few more feature highlights from the upcoming early access: Task Notes & World Map. Task Notes allows you to save task details from the traders. Since early access has +30 tasks, it seemed kind of necessary to have this tool, so you can check those details without the traders (once added to notes). World Map is a tool for checking out the accessible maps, zones and getting an overview of the game world. This tool has an item requirement, so you can only open the map view once compatible map item is equipped. Vostok area remains always unmapped, so you can only locate Area 05 maps with this tool. Visually the world view is also bit placeholder, but will probably do the job for now.

Few more feature highlights from the upcoming early access: Task Notes & World Map. Task Notes allows you to save task details from the traders. Since early access has +30 tasks, it seemed kind of necessary to have this tool, so you can check those details without the traders (once added to notes). World Map is a tool for checking out the accessible maps, zones and getting an overview of the game world. This tool has an item requirement, so you can only open the map view once compatible map item is equipped. Vostok area remains always unmapped, so you can only locate Area 05 maps with this tool. Visually the world view is also bit placeholder, but will probably do the job for now.

Road to Vostok

14,510 次观看 • 5 个月前

🚀 Introducing Spaghetti Models For Free A powerful way to track possible tropical storm paths and compare forecast scenarios. With this update, you can now: - View the latest and historical model runs - Filter models to focus on the guidance you trust - See and download intensity graphs to track trends over time Stay ahead of the storm with clearer insights than ever before. Check out the latest model run for Tropical Storm Fernand here: Available now for free on: iOS: Android: Browser: And to Plus/Pro subscribers using our Windows/Mac/Linux App

🚀 Introducing Spaghetti Models For Free A powerful way to track possible tropical storm paths and compare forecast scenarios. With this update, you can now: - View the latest and historical model runs - Filter models to focus on the guidance you trust - See and download intensity graphs to track trends over time Stay ahead of the storm with clearer insights than ever before. Check out the latest model run for Tropical Storm Fernand here: Available now for free on: iOS: Android: Browser: And to Plus/Pro subscribers using our Windows/Mac/Linux App

WeatherWise.app

36,159 次观看 • 11 个月前

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

280,005 次观看 • 1 年前

#Delhi- GTB hospital. Patients and relatives have to sit on the floors and tolerate #straydogs peeing on walls near them! This is what the value of #human life has been reduced to in this country! Go to a #government run #hospital and get bitten or infected by a #hellhound who is treated better than you! Criminal negligence by hospital #administration!

#Delhi- GTB hospital. Patients and relatives have to sit on the floors and tolerate #straydogs peeing on walls near them! This is what the value of #human life has been reduced to in this country! Go to a #government run #hospital and get bitten or infected by a #hellhound who is treated better than you! Criminal negligence by hospital #administration!

StrayDogFreeMumbai

22,249 次观看 • 5 个月前

This is the craziest model you'll see this week! This model powers Figma. It's also behind Wayfair and a bunch of major e-commerce retailers. This model is a PIXEL-PERFECT image editing model. Literally, "pixel perfect". The model is capable of modifying one image while keeping everything else untouched. It's a model designed, developed, and deployed by the research team at Jasper. This beats OpenAI models, Nano Banana, and every single general image model I've seen so far. It's up to 100x less expensive to run, and up to 10X faster. I recorded a quick video to show you how impressive this is. There's a ton of research behind this model. I'm adding two links below so you can read about how this model works, specifically about "Latent Bridge Matching" and "Flash Diffusion".

This is the craziest model you'll see this week! This model powers Figma. It's also behind Wayfair and a bunch of major e-commerce retailers. This model is a PIXEL-PERFECT image editing model. Literally, "pixel perfect". The model is capable of modifying one image while keeping everything else untouched. It's a model designed, developed, and deployed by the research team at Jasper. This beats OpenAI models, Nano Banana, and every single general image model I've seen so far. It's up to 100x less expensive to run, and up to 10X faster. I recorded a quick video to show you how impressive this is. There's a ton of research behind this model. I'm adding two links below so you can read about how this model works, specifically about "Latent Bridge Matching" and "Flash Diffusion".

Santiago

25,848 次观看 • 9 个月前

Antigravity's computer use has also been massively upgraded with Gemini 3 Flash. It is both faster and better at doing long agentic tasks using the browser. Here's Antigravity doing deep research on the Pareto frontier of models and writing code to visualize the result.

Antigravity's computer use has also been massively upgraded with Gemini 3 Flash. It is both faster and better at doing long agentic tasks using the browser. Here's Antigravity doing deep research on the Pareto frontier of models and writing code to visualize the result.

Varun Mohan

156,937 次观看 • 7 个月前

In a previous video we had a look at the Modeling Cloth add-on. Did you know it also has a tool that can fill any outline with geometry? This can be very handy for creating pieces of cloth from a pattern. #B3D #Blender #Blender3D Get the newest version of the add-on here (tested with Blender 4.1.1)

In a previous video we had a look at the Modeling Cloth add-on. Did you know it also has a tool that can fill any outline with geometry? This can be very handy for creating pieces of cloth from a pattern. #B3D #Blender #Blender3D Get the newest version of the add-on here (tested with Blender 4.1.1)

Jan van den Hemel

44,041 次观看 • 2 年前

Pocket TTS goes multilingual! Now you can use our 100M-parameter models to generate speech in six languages, fast enough to run real-time without a GPU. We also improved the quality of the English model while keeping the same size. And all of this is open-source.

Pocket TTS goes multilingual! Now you can use our 100M-parameter models to generate speech in six languages, fast enough to run real-time without a GPU. We also improved the quality of the English model while keeping the same size. And all of this is open-source.

kyutai

29,601 次观看 • 2 个月前

Fantasy v3 is Officially Live on Base! Fantasy Top has officially completed its migration to Base. Players can now enter a faster, smoother, and fully upgraded gaming experience. As part of this launch, the redesigned Free-to-Play game is now live. It’s been purposefully built to welcome new users, simplify onboarding, and introduce more people to the core gameplay. Learn more about the direction below

Fantasy v3 is Officially Live on Base! Fantasy Top has officially completed its migration to Base. Players can now enter a faster, smoother, and fully upgraded gaming experience. As part of this launch, the redesigned Free-to-Play game is now live. It’s been purposefully built to welcome new users, simplify onboarding, and introduce more people to the core gameplay. Learn more about the direction below

fantasy.top

250,628 次观看 • 1 年前