anthropic that finally is starting to understand how these generative AI models actually work instead of just calling them a black box. and big releases like Runway's Gen 4 foundational video model. And as you can see, I'm not exactly in my typical studio setup because I'm in San Diego, California right now. And it has been
Поиск по транскрипциям
gone out and said that well training a video model understanding video actually gives you an understanding of the world the company Runway ml which also runs a set of textto video tools has this to say we believe that the next major advancement in AI will come from systems that understand the visual world and its Dynamics which
going to be available for you to choose from over here you also get video generation models too you could see they have the top video generation models as well so Runway gen 3 one of my favorites cling you could choose those from here this one is actually really good too so you choose that you give...because if I click on it I have that same kind of Monica layout over here that I showed you on the website but it also pulled in the video over here and I could interact the video I could chat with it over here based on the model I have picked over here I could just click
since I was covering video generators right now let me click on just this section of it this gives you access to all the top video platforms so you'll see runways logo over here Google's logo over here so let me press create to show you what exactly you get so you see some of these new models...that I've seen out there so you could use it directly from here cling is really good yeah this is really good paika Runway gen 3 the newest Runway so all that is available but you can see all these new ones that pop up over here let me choose this one and you will use the exact same
there's very few people here. And so these guys will have got really good at using kind of hacking together uh the existing video generation tools like Sora and Runway and others. And they would have got really good at using them in that current form. But when we have a step change or a massive jump forward like
being raised continuously so one of the things that Founders often say it's like hiring is really difficult especially early stages and it was difficult for Runway as well and it still is but one of the things that I believe in is like it should always be hard because if it's too easy that means you could...they invest so much in it and they're now the world to valuable company right so to that you also have I was watching your videos and somewhere you me that Runway would never be more than 100 people or something and I think that ties back to you know your uses of AI maybe you can talk
quick releases. One from Luma Labs where they have their own video editing feature now just like Runway released last week. It looks very similar in practice where if you're on a paid plan, you can do these edits where you replace the background or add visual effects. This is a product category that is still just shaping
rate of 67%. Genmo AI's Mocky model, Mocky 1, released just last week, has already taken silver and is leading the open-source video generation model. And that puts Runway at number three, which has an ELO of 1,51 and a win rate of 61%. Now, this is pretty crazy because this kind of leaderboard is constantly changing...aren't sure with as to where this model comes from, but a wise tweet says that red pandas live in Asia and Chinese companies are crushing it with video generation. So his guess is that it's from a Chinese tech company like BU or Tencent. And I'd argue that is a pretty accurate guess. When we just
just bumped the discount for us. It's now 20% off for any new subscriber. Go try Gen 4. 5. Seeing is believing. Huge thanks to Runway ML for sponsoring today's video. Now, back to your regularly scheduled content. Welcome back, folks. There is a Blender MCP floating around that integrates with LLMs to essentially vibe code 3D assets
automatically lines up shots based on your script. It's got better magic mask features and you can train it on your voice for AI voiceovers. Video editing is getting crazy fast. Runway introduced
personal number one and most of the team agrees and that's because it brings a blend of a video generator that is s tier on the generation quality one might argue that maybe Runway gen free or one of the Chinese competitors are on the similar level but I think the platform they built here sora. com this...video we'll talk through them here in a second but really every week in my news Roundup I point out what new AI video features are available but really only Runway has been shipping features consistently this has it all so let's level the playing ground with a few facts Sora open AI state-of-the-art video
amazing tool that literally saves days the website packs a ton of useful features that can noticeably simplify video creation process from video to video diffusion and background removing to super slow motion bokeh with Runway ml you can automate previously difficult tasks and make your life easier the tool can detect scenes turn words into color correction blur faces...motion video without any effort or the background blur just mask the foreground objects and choose the blur amount easy I'm sure with Runway ml you will be able to create even more cool videos whether for yourself or client and the Simplicity and quality of results will make sure your salary only gets higher as you see there
right now what we are seeing in the early stages of AI shows us a very promising future especially with text to video and I know that yes what you're seeing behind you is footage from Runway but this is just to show you what is capable with text...video and the current stages that it is at because of course Nvidia haven't really released too much footage on their text to video AI software but this isn't about Runway because of course they're doing incredible things but this is about Nvidia and what is crazy about Nvidia is that with the entire event this small
well not state-ofthe-art yes but the ones that you can actually access like I'm not sure if you can access video yet but the point is that Runway doesn't have these capabilities I mean I guess you could say PE collabs doesn't have these kind of capabilities so it really does go to show that...China are making some significant breakthroughs here that I genuinely thought that P collabs and Runway would have made by now which is genuinely quite surprising so on the text to video aspect and I know I probably should have talk spoke about text to video later I just you know thought that this is pretty crazy because like
from techrunch product huntd threads YouTube reviews it's analyzing and here's the output top AI video tools 2025 Sora by openai realistic text to video weight list access price in TBA runway gen 3 $95 per month fast rendering popular with creators picabs free tier available strong for short form content user feedback highlights Sora leads on quality
right in. Runway ML has been a competitor in the video space for a long time now. They actually kind of had a head start in the higher fidelity AI video space initially, but here they are still pushing forward. The one thing about this model is that it has no audio generation, whereas a lot of other competitors...grit and reality that is typically a little bit more mellowed out and softened up in the VO3. 1s and Soras of the video space. If this style is your thing, it's available now through Runway ML's paid plan. This model does really, really well with image references. From what I've seen thus far, Nano Banana
golden retriever on the beach description. So they start with noise and slowly add pixels until the image looks similar to the ones it knows. Video tools stretch that trick through time. Sora runway pa hyper build clips frame by frame focusing on smooth motion. in video and visas skip synthesis. An LLM reads the text, grabs stock shots, adds
doing animated explainers, motion graphics, or anything abstract, Clling handles it well. Render time is usually 30 to 60 seconds for a 5-second clip. Runway Gen 3 best for editing existing video. If you have footage and you want to change the background, remove an object, or apply an effect, Runway's tool set is unmatched. It's less
actually generate images to video, right? So you can for example type in whatever image you want inside the chat here and then it will use runway to turn that image into a video as well and then it will pull out the request directly there. So that's another way you can use this as well
actually generate images to video, right? So you can for example type in whatever image you want inside the chat here and then it will use runway to turn that image into a video as well and then it will pull out the request directly there. So that's another way you can use this as well