Комментарии:
what about animatediff v4
ОтветитьLtx studio model is lot smaller and available right now.😊
Ответить"Do a barrel-roll". Nice to know the grey hairs aren't lying. XD
Ответить45GB of RAM excludes 99.999% of people. It is impressive, but 720p with that requirements is a little disappointing.
ОтветитьTim i live for the commentary I'm cry laughing lol AI it's just llike people too much on its mind lol like my clothes in laundry lol needs to go in dryer lol
ОтветитьWow tim please do the new minimax anime video the sketch option looks amazing and can't wait for 3d world access
Ответитьwe getting off the pay wheel!!!!!!!!!! runway has been so cocky, and the service has slipped so I left and boom this drops the next day!!!!!!!! I'm not being super fake positive I'm so glad to see things shift to us... i said it next year our agents will be running most of these tasks!!!!!!! Yesssssssssss its time for the ones who want wealth to build and put in an effort to hustle for yourself off your own mind and skills.
ОтветитьWe need chinese mobile number to use it .😢
ОтветитьRobot helmet 😂😂😂
ОтветитьKudos to you for being able to focus on her watch and fingers...
ОтветитьWhen you spotted that head...OMG 🤣🤣!!
Ответитьits weird how much these videos are starting to seem like dreams. Like they're images created based on what the universe looks like, but they don't have to follow any of the rules, so anything could happen.
Ответитьwow that was a huge update video, thank you for it !
ОтветитьBy 2025 the mis of 2025 we will get movie making model
Ответить12 gb vram quantization model someone make it happen for hunyuan ai video model please 🙏🏻
ОтветитьGreat video! I have no experience on github, so if you have any pointers or video tutorial recommendations, really wanna try this out! thanks Tim
ОтветитьThis is good👌Mochi 1 originally required 384 GB of VRAM and FOUR H100s to run.
The Hunyuan Video Model basically only requires 10% of that - and that's even without quantisation yet!
WorldLabs could be useful if you could export the generated world to Blender, for instance.
Ответитьgreat video thanks tim
Ответитьdopepics AI fixes this (AI Image Editor / Upscaler). New AI video from image
ОтветитьI appriciate the subtle humor of the intro logo animation...
Ответить80 Gigs of VRAM for Hunyuan! That's pretty insane for what it spits out. But on an Apple M4 computer it could work, not quitting your home lab. Will think twice about the RAM amount when I buy my next Mac.
ОтветитьFrom their github page: We have tested on a single H800/H20 GPU.
Minimum: The minimum GPU memory required is 60GB for 720px1280px129f and 45G for 544px960px129f.
Recommended: We recommend using a GPU with 80GB of memory for better generation quality.
What is the point?
Is there a program that can do text?
ОтветитьVideo memory usage is an issue. looking at what LTX-video can do with a fraction of video memory,
ОтветитьSome classic Tim-style jokes getting dropped in this episode. Too funny! 😂
ОтветитьThis model takes an insane amount of VRAM to run locally. Open source but an A100 will set you back $18,000.
ОтветитьIs hunyuan video not available to those outside China? I wanna make those weird videos I keep seeing on tiktok of speed morphing into a bunch of weird shit
ОтветитьThis is going to sound bad, but understand I don’t mean this to the extreme level, do we know of any video apps that can handle violence? I mean hand to hand combat and stuff, I DONT MEAN gratuitous gore. I’m talking about superhero levels of violence. Minimax was starting to get there… aaaaannnnddd they just dropped new terms and service that won’t allow for any of it. I tried to generate a body cam footage of a seat team infiltrating an abandoned warehouse and they said it was too much
ОтветитьI don’t even see nvidia graphics cards with more than 16GB memory available… What am I missing?
ОтветитьOh man, your commentary is comedy capers on steroids. Keep it up!
ОтветитьCan you do a video to let us know which one of these API websites like Pixeldogo, Krea, Davinci, Promai and etc etc are the most complete tool set?
ОтветитьIf SORA isn't open source, then I don't care. They waited too long to release it. If it isn't perfect and generating like 5-10 minute videos at a cheap cost then no one's paying for it.
ОтветитьI Love how you always post links to everything you talk about.. others dont
ОтветитьTim, I love how you're so thorough, get to the video quick and don't bombard half the video with ad-reads (at least not yet for the ads, lol) and your dad jokes bring a fun, enjoyable twist to your content than just reporting everything like it's the 9 o'clock news.
Keep up the good work buddy, I'll keep coming back for all the latest tea!
Is it Krea or Korea’s new image editor??????? One of those I'm not too sure I want to try out..... Lol Might want to check your main video description man..
ОтветитьOof I have a 4090 and can’t run this😂
ОтветитьHow you know that videos (all or some of them) were generated by Prompts and not Image To Video ?
Ответитьai image and video generation has plateaued
ОтветитьTencent = China
ОтветитьI just looked up what an 80gb graphics card would cost. Nv Tesla H100 80GB is $27,500 hahahaha. yea.... cool technology but guess doing something like that locally will be like 20 years down the line for hobbyists just wanting to play around with ai on their own pc's. Cool stuff though. maybe we'll see companies offering affordable sites to use it on a pay per use model or monthly subscription. if reasonable i'd be tempted to try it. Though honestly i'd just mess around for fun then stop after a day or 2.
ОтветитьSo how/where are folks getting 45 or 60gb video cards?
Ответитьman...too many people cant wait for these advancements to bleed on to 2025-2026 nsfw animie fantasy worlds
Ответить