Комментарии:
Minimax really shines with image to video. Enjoying bringing my drawings to life
ОтветитьThe fact that the AI knew about a teseract is really scary!
ОтветитьNo Img-2-video support. It's basically rolling the dice and therefore expensive + useless for specific purposes.
ОтветитьSeeing all these AI image and video generators... The more I believe in the simulation theory. watch your backs people going into the future.
Ответитьso how do u get consistent results to create a short movie? and how do you remove the watermark?
ОтветитьMini Max understanding of complex prompting Is up there with Dall-E. It's able to follow complex prompts fairly well compare to other video models. It's definitely up there with Dall E. If they add Image to video then it will stay goated for a while. And the fact they use license characters from video games is Insane. But as long as they keep it private, It shouldn't be a problem with the copy right laws.
ОтветитьI want an api for this so I can send prompts and receive and file outputs AUTOMATICALLY !!!!!!!!!!!!!!!
ОтветитьHey matt! idk if you're aware of this but there is an ai ad going around with you're ai voice. It's on a channel called
"Notd Network"
always keeping us up to date with the latest and greatest. keep it up matt <3
ОтветитьLooks like we're slowly getting there with the AI video stuff. Impressive indeed.
ОтветитьSo it is arriving the moment we can say, SORA is officially... Over
ОтветитьYou should have tried will smith eats spaghetti its the only gen that can do it realistic
ОтветитьMinimax is 100% better than gen 3 amd every other generator, its the only generator that meets my perfectionist standards of realism and quality and ip
ОтветитьGimme local, or it will be too nerfed for fun
Ответитьwe are so cooked :D
Ответитьyeah if it cant do img2vid i dont giv a shit
Ответитьturn the title names off in vlc
ОтветитьAre you recommending people give their phone number to the ccp?? 😬
Ответитьzzzzz generating like 10frames of video who cares
Ответитьopenai rlly fell off
ОтветитьSee I thought the minimax 4D cube generation was a lot more interesting, it looked like a physical 4D object that rotated in 4D space as he moved it around whereas runway was a movie SFX "ooh fancy hypercube thingy". Could also be down to their interpretations of the prompt though
ОтветитьI'd advise people to read carefully over the terms of service for Minimax. They outright prohibit using their platform to make anything that contradicts the Chinese system or anything that goes against their "one China" philosophy. No seriously, this was taken right out of the TOS for things they outright forbid:
Contents of splitting the country
8. Opposing, attacking, or distorting "One China" or "One Country, Two Systems";
9. Any words, deeds, activities or signs that reflect Taiwan independence, Hong Kong independence, Tibetan independence, Xinjiang independence, etc., including video materials, works, voice, speech, pictures, text, reactionary flags, slogans and other forms (except for the rebroadcast of news reports from central news organizations);
10. Programs, entertainment reports, and works produced or participated in by artists and organizations that hold splitting positions such as Taiwan independence, Hong Kong independence, Tibetan independence, and Xinjiang independence;
11. Descriptions of territorial and historical events that do not conform to national conclusions;
how many seconds per clip? you need more time available at least 30 seconds
ОтветитьDamn that,s incredible.
Ответитьltx though it is difficult to get things right it is a step in the right direction. minimax looks doomed. I dont think it will ever get right. I think ltx will get things right at some point. they need to be able to fix the hands and everything else early stable diffusion models got wrong.
ОтветитьThere's also Luma Dream Machine. And also CogVideoX that can be run locally, I tried it. Not as good as the ones reviewed here.
Ответитьguys Im starting out as an AI enthusiast, would love your feedback as i make similar stuff!
Ответить"I won't show you my phone number on screen ..... but I'll give it to China."
Ответитьwell you dont even need a account to create something
ОтветитьThere's an option in VLC to disable the file name showing when playing.
ОтветитьHow do I sign up with a US number?
ОтветитьI was able to make a video without signing up!
ОтветитьThe Tom Cruse clip was probably trying to recrate the computer from Minority Report.
ОтветитьThe site linked seems to be all in some Asian language.
ОтветитьThe one with the iPhone is scary, I really would have a hard time guessing it was AI if I just saw that by itself
ОтветитьImagine if AI would set up a project for e.g. unreal engine 5 with textures, models, and let you render it, so the concistancy would be 100% but the idea, models, etc would be serverd up for you.
ОтветитьWe can tell it Was trained on TENET
ОтветитьSora becomes the "IMPOSSIBLE BURGER" (vegan) of the AI text to video models, you can wait forever for it to get released near you or instead simply buy a 3rd party other brand of vegan burger that is on par or at least close enough to it.
ОтветитьHow'd you get it in English??
ОтветитьMan I’m Never going to live this whole Tom Cruise thing down.
Ответить