Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

same Blender prompt. same 12 seconds. and Astra’s output looks like it’s in a completely different class. this is why I’m getting more interested in these real software tests than generic benchmark scores. a model can look amazing on paper and still have huge capability gaps inside specific tools.

Wes Roth

37,786 subscribers

14,236 views • 19 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Image-to-3D tools are leveling up fast. I tested img2threejs by Nick on a Canyon gravel bike from just one image, and the result is already super promising. Still early, but you can clearly see where this is going. Next, I’m going to test the exact same image in Blender and compare the final output. Repo below 👇

Image-to-3D tools are leveling up fast. I tested img2threejs by Nick on a Canyon gravel bike from just one image, and the result is already super promising. Still early, but you can clearly see where this is going. Next, I’m going to test the exact same image in Blender and compare the final output. Repo below 👇

Givros

47,723 views • 2 months ago

Stop relying on generic AI output Train a model on your world, your character, your style, and reuse it forever That is the idea behind LTX Trainer, an open-source training framework that lets you train reusable IC-LoRAs for specific video transformations like colorization, deblur, decompression, reference sheet control, and a lot more Each LoRA gives the model a specific behavior it can repeat across clips, so your videos become more consistent, more controlled, and more connected to your own creative direction Check these amazing examples 👇🏻

Stop relying on generic AI output Train a model on your world, your character, your style, and reuse it forever That is the idea behind LTX Trainer, an open-source training framework that lets you train reusable IC-LoRAs for specific video transformations like colorization, deblur, decompression, reference sheet control, and a lot more Each LoRA gives the model a specific behavior it can repeat across clips, so your videos become more consistent, more controlled, and more connected to your own creative direction Check these amazing examples 👇🏻

Amira Zairi

28,574 views • 3 months ago

We are getting absurdly close to the point where “learning Blender” means learning how to direct an AI. A shot like this looks soft and playful on the surface, but under it is the usual 3D pain: modeling, layout, materials, lighting, atmosphere, animation, and endless tiny fixes until the frame stops looking dead. That is why Kimi K3 matters. With Blender MCP, you can describe a scene like a robotic goat walking through a dreamy field and let the model help build the environment, place the camera, shape the materials, script the motion, and iterate inside the real Blender project. The real shift is not text-to-image. It is text-to-workflow. Kimi K3 does not just give you a pretty output and disappear. It can help move the actual scene from rough setup to something that looks art-directed. Soon the hardest part of 3D will not be the software. It will be whether your imagination is good enough to deserve tools like this.

We are getting absurdly close to the point where “learning Blender” means learning how to direct an AI. A shot like this looks soft and playful on the surface, but under it is the usual 3D pain: modeling, layout, materials, lighting, atmosphere, animation, and endless tiny fixes until the frame stops looking dead. That is why Kimi K3 matters. With Blender MCP, you can describe a scene like a robotic goat walking through a dreamy field and let the model help build the environment, place the camera, shape the materials, script the motion, and iterate inside the real Blender project. The real shift is not text-to-image. It is text-to-workflow. Kimi K3 does not just give you a pretty output and disappear. It can help move the actual scene from rough setup to something that looks art-directed. Soon the hardest part of 3D will not be the software. It will be whether your imagination is good enough to deserve tools like this.

Rina

45,651 views • 2 months ago

First look at the TGL indoor golf arena! Are you more or less hyped? I’m starting to get interested, this looks cool. Justin Thomas and Justin Rose provide the tour. The screen is huge and it looks like a legit sports venue. If they can get some lively fans in there, it could be fun. I’m ready for casual night golf if it’s actually competitive. I see these guys caring, they have equity!

First look at the TGL indoor golf arena! Are you more or less hyped? I’m starting to get interested, this looks cool. Justin Thomas and Justin Rose provide the tour. The screen is huge and it looks like a legit sports venue. If they can get some lively fans in there, it could be fun. I’m ready for casual night golf if it’s actually competitive. I see these guys caring, they have equity!

Rick Golfs

125,555 views • 1 year ago

This AI puts a full production studio in one person’s hands, cinematic-level output. $0.35 per generation. Competitors charge 7× more for the same model. And it’s 70% off. Hollywood is cooked.

This AI puts a full production studio in one person’s hands, cinematic-level output. $0.35 per generation. Competitors charge 7× more for the same model. And it’s 70% off. Hollywood is cooked.

𝐀𝐍𝐓𝐔𝐍𝐄𝐒

15,381 views • 5 months ago

Look at the difference the tool AND the prompt make. Bad generator + lazy prompt: stiff movement, dead eyes, that obvious "AI look" everyone scrolls past. Seedance + a detailed, structured prompt: natural movement, real lighting, real pacing — looks like it came off an actual production shoot. Same product photo. Completely different result. It's not one or the other. You need the right tool AND the right prompt to get agency-level output. Ready to see the exact setup? Check the comments 👇

Look at the difference the tool AND the prompt make. Bad generator + lazy prompt: stiff movement, dead eyes, that obvious "AI look" everyone scrolls past. Seedance + a detailed, structured prompt: natural movement, real lighting, real pacing — looks like it came off an actual production shoot. Same product photo. Completely different result. It's not one or the other. You need the right tool AND the right prompt to get agency-level output. Ready to see the exact setup? Check the comments 👇

Stijn Feijen

11,970 views • 2 months ago

Gavin Newsom made it a FELONY for anyone to investigate his rigged elections in California. Imagine 59,000 coin flips all landing the exact same way? This is what tyranny looks like. I’m more interested in what can be done to stop him?

Gavin Newsom made it a FELONY for anyone to investigate his rigged elections in California. Imagine 59,000 coin flips all landing the exact same way? This is what tyranny looks like. I’m more interested in what can be done to stop him?

Sherri™

30,202 views • 3 months ago

50% cheaper Claude inference with just one line of code change! - Remove → model="claude-opus-4-8" - Add → model="ship-like/claude-opus-4-8" I verified the cost saving in my own terminal by invoking the same Anthropic model with the same prompt. The underlying engineering by Ship is actually interesting, and the patterns can be used in any production LLM stack. Essentially, a trained model is a frozen artifact. Every request performs the same forward-pass, whether it extracts a date or refactors a module, because the compute decision was made at training time, before the request existed. Ship makes that decision at inference time instead. After seeing a request, it searches over executions, involving single models, cascades, ensembles, or harnesses with tools, and serves the cheapest one that will match the reference model's quality. This is not a basic router, because picking a cheaper model per query doesn't ensure the cheaper model preserves the original's behavior, like output shape, tool-call patterns, and refusals. Ship measures this equivalence directly. Outputs stay distributionally indistinguishable from the reference model, not token-identical, since two calls to the same model already differ, but they are indistinguishable in capability and behavior. Of course, some requests execute cheaply and some cost Ship more than the customer pays, but the price per request is still a flat 50% off either way, so the execution-cost variance moves off the application's bill entirely. The video below depicts the cost savings and output in my real invocation, and I partnered with the team to put this together.

50% cheaper Claude inference with just one line of code change! - Remove → model="claude-opus-4-8" - Add → model="ship-like/claude-opus-4-8" I verified the cost saving in my own terminal by invoking the same Anthropic model with the same prompt. The underlying engineering by Ship is actually interesting, and the patterns can be used in any production LLM stack. Essentially, a trained model is a frozen artifact. Every request performs the same forward-pass, whether it extracts a date or refactors a module, because the compute decision was made at training time, before the request existed. Ship makes that decision at inference time instead. After seeing a request, it searches over executions, involving single models, cascades, ensembles, or harnesses with tools, and serves the cheapest one that will match the reference model's quality. This is not a basic router, because picking a cheaper model per query doesn't ensure the cheaper model preserves the original's behavior, like output shape, tool-call patterns, and refusals. Ship measures this equivalence directly. Outputs stay distributionally indistinguishable from the reference model, not token-identical, since two calls to the same model already differ, but they are indistinguishable in capability and behavior. Of course, some requests execute cheaply and some cost Ship more than the customer pays, but the price per request is still a flat 50% off either way, so the execution-cost variance moves off the application's bill entirely. The video below depicts the cost savings and output in my real invocation, and I partnered with the team to put this together.

Akshay 🚀

64,482 views • 2 months ago

1/ AI video is getting crowded. What matters now isn’t just who can generate a cool clip, it’s which tools actually fit real production workflows. LTX-2.3 inside LTX Studio feels like a meaningful step in that direction. Open weights and local runs are impressive, but LTX Studio Pro is where the model really unlocks its full quality. Some amazing examples:

1/ AI video is getting crowded. What matters now isn’t just who can generate a cool clip, it’s which tools actually fit real production workflows. LTX-2.3 inside LTX Studio feels like a meaningful step in that direction. Open weights and local runs are impressive, but LTX Studio Pro is where the model really unlocks its full quality. Some amazing examples:

Chubby♨️

14,406 views • 6 months ago

KIMI K3 VS OPUS 4.8 SIMULATING A 3D PARTICLE SYSTEM same prompt, same target: thousands of particles reacting to gravity and to each other in real time → K3: more organic distribution, smoother motion, particles actually cluster and drift like something physical → Opus: more rigid pattern, less natural, movement reads more like a grid than a simulation K3: $0.65 in API. Opus 4.8: ~$1.30 this is simulated physics, not just aesthetics, and it's the kind of detail that separates a demo from something you'd actually ship

KIMI K3 VS OPUS 4.8 SIMULATING A 3D PARTICLE SYSTEM same prompt, same target: thousands of particles reacting to gravity and to each other in real time → K3: more organic distribution, smoother motion, particles actually cluster and drift like something physical → Opus: more rigid pattern, less natural, movement reads more like a grid than a simulation K3: $0.65 in API. Opus 4.8: ~$1.30 this is simulated physics, not just aesthetics, and it's the kind of detail that separates a demo from something you'd actually ship

Jade

32,766 views • 2 months ago

Gas prices right now look very different depending on where you live… A woman in California is showing what she’s paying - and it’s getting people talking. Some areas are seeing a little relief… others are pretty much the same. Same country… very different numbers at the pump. Be real - ⛽ What are YOU paying per gallon right now? 📍 Has it dropped where you are… or stayed about the same? ⬇️ 🇺🇸

Gas prices right now look very different depending on where you live… A woman in California is showing what she’s paying - and it’s getting people talking. Some areas are seeing a little relief… others are pretty much the same. Same country… very different numbers at the pump. Be real - ⛽ What are YOU paying per gallon right now? 📍 Has it dropped where you are… or stayed about the same? ⬇️ 🇺🇸

Tony Lane 🇺🇸

17,255 views • 5 months ago

Kimi K3 vs GPT-5.6 vs Claude Fable 5 A game is one of the hardest places to fake working code. A web app can hide bugs behind a polished screenshot. A game can't. Bad collision, clipping, jitter, broken physics, awkward controls, or a snowboard sinking into the terrain become obvious within seconds. That's why I like using games to evaluate coding models. I gave Kimi K3 a single prompt to build a snowboard game in Godot, and just 20 seconds of gameplay told me more than a page of benchmark scores ever could. Benchmarks matter, but watching a model build something interactive reveals a different side of its capabilities. If the gameplay feels right, the systems work together, and the experience holds up under real input, that's a much more convincing demonstration than any leaderboard.

Kimi K3 vs GPT-5.6 vs Claude Fable 5 A game is one of the hardest places to fake working code. A web app can hide bugs behind a polished screenshot. A game can't. Bad collision, clipping, jitter, broken physics, awkward controls, or a snowboard sinking into the terrain become obvious within seconds. That's why I like using games to evaluate coding models. I gave Kimi K3 a single prompt to build a snowboard game in Godot, and just 20 seconds of gameplay told me more than a page of benchmark scores ever could. Benchmarks matter, but watching a model build something interactive reveals a different side of its capabilities. If the gameplay feels right, the systems work together, and the experience holds up under real input, that's a much more convincing demonstration than any leaderboard.

FHILY👑

36,766 views • 2 months ago

Walkies and talkies. One of the longer shots I did on Fixed I think. I have one more in this sequence with the exact same framing. Looks like they are walking on a treadmill haha

Walkies and talkies. One of the longer shots I did on Fixed I think. I have one more in this sequence with the exact same framing. Looks like they are walking on a treadmill haha

Ole

109,005 views • 1 year ago

✨ Every time the video models get better, the try on model on Photo AI also becomes a lot more useful, as a large % of my customers now are e-commerce store And showing clothes in a video is nice for sales! With AI this means stores don't need to do expensive shoots flying a model and entire camera and light crew around the world They can just upload a few photos of their models, then upload the clothes, and describe the setting (like a beach in Thailand) and in less than 10 seconds it's generated, for a video in less than a minute! Below is the input: a dress laid flat, and output: a full video shoot

✨ Every time the video models get better, the try on model on Photo AI also becomes a lot more useful, as a large % of my customers now are e-commerce store And showing clothes in a video is nice for sales! With AI this means stores don't need to do expensive shoots flying a model and entire camera and light crew around the world They can just upload a few photos of their models, then upload the clothes, and describe the setting (like a beach in Thailand) and in less than 10 seconds it's generated, for a video in less than a minute! Below is the input: a dress laid flat, and output: a full video shoot

@levelsio

334,317 views • 1 year ago

Most video tools can generate clips. Very few can maintain identity. That has been the real bottleneck in AI video creation. Kling O1 changes that. For the first time, creators can carry a character, style, and visual language across scenes without constant fixes. You can reference past clips, assets, or images and the output stays consistently on-model. No visual drift. No rework loops. No “this doesn’t look like the last shot” moments. It feels less like prompting a tool and more like working with a creative collaborator that remembers context. The impact is practical, not theoretical: → Faster production cycles → Lower iteration costs → Noticeably higher output quality This is what mature AI tooling looks like. Not louder features. Not bigger claims. Just reliability where it actually matters. Consistency is no longer the problem.

Most video tools can generate clips. Very few can maintain identity. That has been the real bottleneck in AI video creation. Kling O1 changes that. For the first time, creators can carry a character, style, and visual language across scenes without constant fixes. You can reference past clips, assets, or images and the output stays consistently on-model. No visual drift. No rework loops. No “this doesn’t look like the last shot” moments. It feels less like prompting a tool and more like working with a creative collaborator that remembers context. The impact is practical, not theoretical: → Faster production cycles → Lower iteration costs → Noticeably higher output quality This is what mature AI tooling looks like. Not louder features. Not bigger claims. Just reliability where it actually matters. Consistency is no longer the problem.

Darshal Jaitwar

141,038 views • 8 months ago

Being a model is not as easy as it looks. Imagine having to stand on your tiptoes in heels like this, keep your balance, strike the perfect pose, and still make it look effortless.

Being a model is not as easy as it looks. Imagine having to stand on your tiptoes in heels like this, keep your balance, strike the perfect pose, and still make it look effortless.

Nathasia

271,835 views • 4 months ago

New version based on the previous prompt👀 Made in Higgsfield AI 🧩 Seedance 2.0 Only changed the location + outfit. This time I also wrote the exact lyric timing in the prompt ⏲️ By the way, this is a softer and more emotional take on the same song. Which version do you like more?

New version based on the previous prompt👀 Made in Higgsfield AI 🧩 Seedance 2.0 Only changed the location + outfit. This time I also wrote the exact lyric timing in the prompt ⏲️ By the way, this is a softer and more emotional take on the same song. Which version do you like more?

Kiber Alla

18,170 views • 2 months ago

Americans have started to notice that companies sell the exact same products to men as they do women, but the women’s version cost more This is called “Pinkflation” or the “Pink Tax” This is a real and well documented fact Example Tweezers: Brands like Revlon, Tweezerman and more frequently sell basically identical stainless steel tweezers with only cosmetic differences like color and packaging. They markup the women’s line Women’s tweezers can be $18+ while men’s might be $12, but they’re the same It’s not just tweezers Studies from NYC Consumer Affairs and more have found women pay 13%+ more on average for similar personal care items like razors, deodorant, shampoo, and grooming tools Some women’s products have slight design tweaks but many don’t, many just change the color It’s just another corporate scam in America that’s somehow legal

Americans have started to notice that companies sell the exact same products to men as they do women, but the women’s version cost more This is called “Pinkflation” or the “Pink Tax” This is a real and well documented fact Example Tweezers: Brands like Revlon, Tweezerman and more frequently sell basically identical stainless steel tweezers with only cosmetic differences like color and packaging. They markup the women’s line Women’s tweezers can be $18+ while men’s might be $12, but they’re the same It’s not just tweezers Studies from NYC Consumer Affairs and more have found women pay 13%+ more on average for similar personal care items like razors, deodorant, shampoo, and grooming tools Some women’s products have slight design tweaks but many don’t, many just change the color It’s just another corporate scam in America that’s somehow legal

Wall Street Apes

76,460 views • 4 months ago

Blender just became a prompt box. Kimi K3 + Blender MCP can take a simple text prompt and build an entire 3D scene for you. terrain, buildings, lighting, materials, camera movement, animation, even the Python scripts holding everything together. but the crazy part isn’t just that it can build the scene. Kimi can inspect what it created, understand what looks wrong, then go back into Blender and fix the actual scene before rendering again. the camera can be clipping through a tree, the lighting can feel off, the city can look too artificial, and instead of starting over, Kimi can make the changes directly inside Blender. and because everything is happening in Blender, you’re not left with a locked AI-generated video. you get the actual 3D scene. every object, material, light, camera and keyframe stays editable. a few years ago, creating something like this could take weeks of modeling, scripting, lighting and animation. now you can describe the world, let Kimi build the first 90%, and spend your time making the final 10% actually look good. that’s what makes Kimi K3 + Blender MCP so interesting. it’s getting dangerously close to text-to-3D, except the result is a real Blender project you can keep editing.

Blender just became a prompt box. Kimi K3 + Blender MCP can take a simple text prompt and build an entire 3D scene for you. terrain, buildings, lighting, materials, camera movement, animation, even the Python scripts holding everything together. but the crazy part isn’t just that it can build the scene. Kimi can inspect what it created, understand what looks wrong, then go back into Blender and fix the actual scene before rendering again. the camera can be clipping through a tree, the lighting can feel off, the city can look too artificial, and instead of starting over, Kimi can make the changes directly inside Blender. and because everything is happening in Blender, you’re not left with a locked AI-generated video. you get the actual 3D scene. every object, material, light, camera and keyframe stays editable. a few years ago, creating something like this could take weeks of modeling, scripting, lighting and animation. now you can describe the world, let Kimi build the first 90%, and spend your time making the final 10% actually look good. that’s what makes Kimi K3 + Blender MCP so interesting. it’s getting dangerously close to text-to-3D, except the result is a real Blender project you can keep editing.

MIKE

10,434 views • 1 month ago