The pace of ai is astounding. Rather than seeing models as this vs that I like to see them as tools in the toolbox, similar to you. Use em all depending on the needs of the task. Thanks for bringing this to our attention plus the demonstration and guide.
Really?? We've been stuck on three to four second length video generation now for about 2 years, and we're still stuck there. I'd really like someone to explain to me how 3 seconds of video is supposed to really do anything for anybody.
@ well I was speaking more about the quality of the generation, (in general, not this model exclusively) especially when using a lora. as opposed to will smith eating spaghetti from two or three years ago.
@@heshanlahiru2120 You could probably get Claude or Llama to write the prompts and keep appending to the clips. If it can pass the bar exam and ace the math Olympiad, it can probably think well enough to write a video script, given a few examples. It might even be able to tell whether the last frame degenerated too much and a clip needs to be done again. You just can't do it in a single model. Yet.
the "EmptyCosmosLatentVideo" and "CosmosImageToVideoLatent" nodes dont appear in comfyui manager to download, rendering the workflow dead. Edit... Not sure what happened. i went back to the window, and it was there, does comfyui update while in use?
Hi Sebastian, I keep getting a ksampler error: "Expected size for first two dimensions of batch2 tensor to be: [154, 768] but got: [154, 1024]." and I didn't alter the base workflow at all so not sure why this is happening
Can't get this to work at all, and I have the top of the line hardware out (4090, amd 9, etc.). Keep getting VAE header too large, or Clip header too large, or Unet too large.
Tried first video, was done in about an hour, tried another and left, turned out it took 7 hours, I don't think it is supposed to work like this. on 3090
Hello, I ran it on linux usind and AMD GPU 7900 XTX 24GB the sample prompt took me one hour to generate, probably doesn';t use my gpu and I will need an Nvidia por this.
I am so sorry, everyone. One time, I told Sabation in the comments that I liked his dad jokes, and he hasn't stopped since. I kind of blame myself. He should go back to talking about current events. Like, has he even said anything about that AI finetuned to be a stand-up comedian? It bombed so hard they had to rebuild half the data center.
@@havemoney I'm sorry, I misunderstand. Who is "her" and why does the model need to interact with the world? It's not going to be run on a physical robot hardware, is it?
@sebastiankamph Not all, at least the most popular ones because I just got into AI and I feel overwhelmed and not sure which ones to use and for what are they good
The pace of ai is astounding. Rather than seeing models as this vs that I like to see them as tools in the toolbox, similar to you. Use em all depending on the needs of the task. Thanks for bringing this to our attention plus the demonstration and guide.
Really?? We've been stuck on three to four second length video generation now for about 2 years, and we're still stuck there. I'd really like someone to explain to me how 3 seconds of video is supposed to really do anything for anybody.
@ well I was speaking more about the quality of the generation, (in general, not this model exclusively) especially when using a lora. as opposed to will smith eating spaghetti from two or three years ago.
@@aegisgfxwhy do you think you give a prompt and ai to genarate minutes long Videos. Ai can't do that. Ais can't think
@@heshanlahiru2120 You could probably get Claude or Llama to write the prompts and keep appending to the clips. If it can pass the bar exam and ace the math Olympiad, it can probably think well enough to write a video script, given a few examples. It might even be able to tell whether the last frame degenerated too much and a clip needs to be done again. You just can't do it in a single model. Yet.
@@heshanlahiru2120 hey It can't really do anything as far as I can tell. Again I ask people what is 3 seconds of video good for???
cant wait to see image to video workflows, thx for the video , looks good , ill try it on rtx 3060
You and me both!
tell me if it work on 3060 buddy!
It worked on an RTX 3060 with 32GB of ram at 3200MHz, it took 88 minutes to make the video that comes in the model in the video
@@thrasher7666 I think you used wrong models maybe fp16
@@solomslls no i used the fp8 model
love ur vids pls talk more about comparisons to other systems like example why someone would opt for this instead of competitors, its nsfw filters etc
Thanks Sebastian !
Happy to help! 🌟😊
GREAT explained ...
the "EmptyCosmosLatentVideo" and "CosmosImageToVideoLatent" nodes dont appear in comfyui manager to download, rendering the workflow dead. Edit... Not sure what happened. i went back to the window, and it was there, does comfyui update while in use?
it's crazy to be the first first time
I should start giving out awards! 🌟
@@sebastiankamph Don't encourage them! :D
@@tomaszwota1465 we never die... I guess
Thanks for another great video - I only have 8GB ram card - is it still worth trying?
It might work, but i've had Hunyuan work on a 8gb card. If this doesnt work, use that one.
@@Dj-McculloughI love the idea, but is Hunyuan trustworthy?
@@Dj-Mccullough Yeah so far I don't seem to have had problems generally, may be slower but so what. Thanks for reply.
Thank you!
Hi Sebastian, I keep getting a ksampler error: "Expected size for first two dimensions of batch2 tensor to be: [154, 768] but got: [154, 1024]." and I didn't alter the base workflow at all so not sure why this is happening
Thanks for this cool tutorial . In ksampler - sampler name - you have "res_multistep" what is it ? i don't have this sampler
also might make sense to lower resolution and then have a flow to grab each frame and then upscale?
w8 for 5090
wie erhält man die workflows? öffnen geht nicht. reinziehen in comfyui geht auch nicht.
how exactly do I adjust the number of frames per second generated with cosmo? the frame rate on the save to WEBP node? or elsewhere in the workflow?
Hello, Empty Cosmos Latent Video seems to be missing, how can I fix it?
Same issue here
I take that back, after a restart of the UI all looks OK
Still missing for me also ltxvideoconditioning 🤷🏾♂️
Any chance this will work in A1111?
ello, Empty Cosmos Latent Video seems to be missing, how can I fix it?
Can't get this to work at all, and I have the top of the line hardware out (4090, amd 9, etc.). Keep getting VAE header too large, or Clip header too large, or Unet too large.
seb can you do lora training guide for kohoya ss ?
Thanks! 👍 Half hour with a 4060 16gb. Nice, but ... how can i save and play the vid? It is a WebP file
Ok, i use a online webp > mp4 converter 🤗
Glad you got it sorted. You can actually save mp4 straight from the video combine node from vhs.
hey with an rtx 4090 it takes like 16 min per standard setting generaation. Is that normal? Feels so slow
Took me almost exactly 10 minutes on my 4090
Tried first video, was done in about an hour, tried another and left, turned out it took 7 hours, I don't think it is supposed to work like this. on 3090
Is it possible to load a Flux LoRA into the model and use that character's face?
hi eror help please
KSampler
Expected size for first two dimensions of batch2 tensor to be: [256, 4096] but got: [256, 1024].
my system RTX 4080 Süper / amd ryzen 7800x3d / 32 gb ram 7800 mhz
so with 8g vram , it will be too slow ?
Hello, I ran it on linux usind and AMD GPU 7900 XTX 24GB the sample prompt took me one hour to generate, probably doesn';t use my gpu and I will need an Nvidia por this.
yeah you need CUDA from an Nvidia GPU, AMD cards are slow with current software
It says in the docs it takes bout an hr even for 24gb gou
@ sad, because image waiting one hour for a video you don’t like to make corrections lol
How long did it take to run locally for you?
least 30 mins
10 minutes on the dot, give or take a few seconds.
@@sebastiankamph hardware = 4090? or did you do it with an online service w/ beefier hardware?
Hi, Seba! Is there any way to run this with an AMD 6900 XT?
does it do image to video
I am so sorry, everyone. One time, I told Sabation in the comments that I liked his dad jokes, and he hasn't stopped since. I kind of blame myself.
He should go back to talking about current events.
Like, has he even said anything about that AI finetuned to be a stand-up comedian? It bombed so hard they had to rebuild half the data center.
You need try some controlnets, or some refiner to try to fix your hair Sebastian
hey guy, thanks! you doing ok?
Same concern here.
the end result is so MEH that it doesn't feel like it's worth it at all though
The model focuses on creating realistic data and not a cat in the hat, it has a problem with fantasy
Interesting! Does it have good realistic detail then?
@@fluffsquirrel her specialty is teaching robots to interact with the real world
@@havemoney I'm sorry, I misunderstand. Who is "her" and why does the model need to interact with the world? It's not going to be run on a physical robot hardware, is it?
Many new AI tools. so fast.
Surely it is better than Hunyuan Video😂
Best? I think even ltx drop it
Can you make a video explaining all the AI tools and pros/cons of each for example D-ID, Synthesia, Runaway etc
AAALLLLL the AI tools? That'll be a 3 year long video.
@sebastiankamph Not all, at least the most popular ones because I just got into AI and I feel overwhelmed and not sure which ones to use and for what are they good
Too big, too slow. We need faster models like LTX-Video to be improved.
Don't waste your time, render is ugly. Hunyuan stills better
I got some pretty good generations out of it, at much better speeds than Hunyuan.
@@sebastiankamph i ve tested both...Sorry Hunyuan is better with a good workflow
You should show it too!@@sebastiankamph
If you want crappy looking drawings, it excels at it. Even LTX is better
@@ronbere how do you mean "with a good workflow"?