Відео

Thats some gold rigth there. Thanks man

For the anime ones I tested, I added the phrase "The camera does not move" and that seemed to fix it. The prompts help guide the motion you want. If you don't want much motion, just describe the scene. Otherwise you should limit the prompt to a single action, such as "kicking legs", "talking to camera", or "riding bike". Those prompts worked the best for me. "Dancing" and "jumping jacks" didn't work as well.

Luma does really good at Pixar because it was originally an image to 3d generator and a lot of its data is based on that, same with the vector graphics.

check your gumroad site , tried to get prompt book but something wrong with site

Trying to use it but when the queue takes hours and you're limited to so few generations it's impossible to experiment and try to get good results

Like u said Leonardo is more friendly than MJ so why not making more tutorials video about Leonardo, I just purchased tokens for a month to try on…

Please add prompts to these references. That would be really helpful. Thanks

Great video ma man

definitly we need some controle - )

I hope Luma will get better at depicting anime scenes & nonhuman characters. It looks like it’s lacking in these areas.

It looks like Luma really needs some camera controls.

I tried hard to get an static camera shot but luma prefers dinamic shots always ignoring the prompts :/

I got a pro plan few days ago. Luma is a dud. Watermarks? No control over movement? It's so 2023

It blocks pictures sometimes. I hate censorship. There's no reason, one was a picture. Just a regular picture, a profile picture.

I just finished a vid. Did u try unticking the magic prompt box? I found it doesnt pan as crazy. I had a difficult shot where my soldiers were just doing goofy things. I unticked and typed slow motion, subtle camera movement and it worked ;)

the problem is you absolumtly not have any controls of what you are moving camera and subject and props....

even with a paid sub you can't get rid of what watermarks on the videos.

IA it's our future! Let's make a mutual subscribe🎉🎉🎉

3d works perfect , flat 2d images, not at all

It seem that if you turn off the enhance prompt button it reduces the motion blur and stops the camera from panning out of scene, that least turning enhance prompt makes anime generations look better when you do image to video.

Damn i,wish you added your prompts input to see what you wrote

Thanks for sharing! The results are very impressive. I haven’t figured out though how to download the videos it generates. If I click on the 3 dots it doesn’t give me any other option than reading speed. I am on a free plan. Any suggestion?

You can prompt the camera to stay still or pan slowly or zoom etc

This is what we needed. A service that puts real pressure on OpenAI

Thank you! Thank you really for all the knowledge you have passed on to us.

SORA Killer 🤣😂😅

Thanks for your research Tao, it really makes a difference to view it. I was wondering in your presentation of the various styles, are you using the enhance checked or not checked? Did you do a comparison for each style based on enhanced/Non-enhanced. I have been uploading my images and not using enhanced as I found that they follow my prompts and style of my images more closely. Like you, I notice that sometimes Luma turns an image into a cartoon which makes the video unusable.

Seems extremely promising! I'm somewhat disappointed that it struggles the most with anime-like styles, which I usually favor. Given how rapidly things progress, I'm eager to see how it develops over the next two months. Hell, probably the next couple of hours. 😅

I will try my own art and be nice if I have 2 minutes of my own animation and be cool file send as slides but or the movement and reads and o I see AI and finish more extended movie

Haha seem recognized the movie slots haa😊

Agreed on all. Really need better camera control.

it's a good start. luma works much better with reference images. I hope they work hard!

Nice work

so maybe i should go ahead and stick with runway ml for another 9 months. I am sure they will greatly improve by then

i work in hollywood. this is the end of human production. no reason to spend 100 million on a film , when you can spend way less. this is just the beta, its unreal.

🙃

Nice

Fantastic video! I have a question: If I already have a centered face, how can I generate multiple angles from it?

But this method is not working in my cell is it not for free Ai Leonardo users

Tao thank u for ur info❤🎉 is there a NSFW filter...? I have such problem with some images.

Thanks bro, edged aggressively to this.

Works used for the first time ua-cam.com/video/I4k1NMwoe8E/v-deo.html

Too much restriction so i wait for local version

Thank you for the tutorial! Did you do the final animation of your comic strip in Canva?

Keep on bro... Your running this channel right. Focus on subject... master it. UA-cam is insanely difficult to grow on these days. However if you can dominate a subject you will continue to grow. Your format is Very good... not loaded with BS or CTA... You might consider additional channels. Although time consuming... at this point if you want to get anywhere sustainable it's all about dominating a subject such as you are here. Anything AI related is likely to be hot for a while... Right now is election year with a lot of distractions but that will die down. Keep at it ... but only if you love doing it... when it becomes a Job... you will stress out every time UA-cam shifts in popular subjects of the day... Good Luck...

Number one....limit time 5s

Very grateful for your tutorial! I found that the characters’ fingers or toes were sometimes distorted even when I turned the motion strength to 1 for animation. Grateful if you can come up with a tutorial to help me fix this problem.

Anyone knows how to remove the Luma logo when downloading the video? Thanks.

I wish it was possible to create multiple personalization styles. I can’t see myself sticking to a single visual style.

If you're just trying to create a random video or of context - is cool. But if you're trying to create an actual video with a story, and even if you have created great images in midjourney to prompt with, the randomness of Luma, and the lack of control over what's coming out of the other side make it apoor bet. Runway is not nearly as impressive, but at least i know what I'm getting.