I made a music video in Stable Diffusion AI… and it’s amazing!

I made a Music Video in Stable Diffusion AI with the Deforum SD Google Colab. I used Video Input with Video from Pexels, that I cut in Davinci Resolve to fit the music first and then rendered it Scene by Scene in SD Deforum Google Colab. I use the same prompt for most of the Video. Just in one Case I described the Scene to get a better Result. In Davinci Resolve i also added some zoom and movement to most shots to make the a bit more animated. The fading to Black and White and fading out effect is also done in Davinci Resolve and well as the rotation of the video in the second but last scene.

Music: Someone I Used to Know – Loving Caliber from Epidemic Sound

Join this channel to get access to perks:
https://www.youtube.com/channel/UCCKx8mAHiFus-XYQLy_WnaA/join

My Facebook group: https://www.facebook.com/groups/oliviotutorials.superfan/
My Newsletter: https://oliviotutorials.podia.com/newsletter
My Affinity Photo Creative Packs: https://gumroad.com/sarikasat
My Patreon Page: https://www.patreon.com/sarikas
All my Social Media Accounts: https://linktr.ee/oliviotutorials

100 Comments

  1. I've gotten into this AI Art passion of mine 3 months ago and just when I started to experiment with AI videos I see this masterpiece, this is just brilliant. the amount passion and pure experimenting that must have gone into this must have been astronomical. keep doing what your doing, your work is amazing. also I've learnt a lot from your videos already so thanks a bunch.

  2. Looking forward to see short films made entirely with Stable Diffusion coming out the coming weeks ^^ this strange kind of transition might only be a temporarily artifact with those early AIs, but at the same time thatā€™s also a very cool art style by the way

  3. I liked it a lot but I think it was not very creative because. In uncertain way it can be compared to someone applying filter to a stock video. It was a very beautiful AI art above those pre recorded video but it is only that

  4. Great video. It's the idea that counts. As someone who's worked in film for decades, this is revolutionary tech. I've been coding my own effects in the past, but it was all non-AI. Shader type stuff. I only dove into stable diffusion recently, and loving it. I've had so many scripts in the past, that I'd reject due to being too large in scope. Unfilmable on a short budget. Now I can use a handful of AI's to produce absolutely everything for me. One writes a script. Another one makes an animated storyboard, the 3rd does a synthesized voiceover in any accent. And it all looks fabulous even without the post treatment. I'm still trying to figure out what to do with things like the depth pass. How to tap into the OFlow they're using to mess with motion vectors a bit. I also see that nobody has written a camera animation tool. It's all done semi-manually with spline to keyframe converters. Coding a camera exporter for Maya should be the easiest to do. Then it would be possible to have a 3D video relay some of the camera information back to DS, allowing for higher coherence. Only been coding for a week, and I'm already overwhelmed with ideas. And I love watching videos like this, to know what the others are coming up with. 2 years ago to produce something like this would've taken a team of people months of work. Now stuff like this can be produced in 24 hours. Soon, the prompt response will be so quick, that they'll hook it up to voice recognition blocks and have live AI driven shows. Interactive randomly generated stories with illustrations. AI Dungeon already does that to an extent, but it's basic. Just imagine what tools we'll have in a year! I haven't had this much fun since DeepFaceLab came out.

  5. So moving and inspiring thanks for this šŸ™‚ I love ai art and have been messing with it for months can't wait to try this myself thanks for posting a guide and on fb šŸ˜Š

  6. When you think those people don't exist!
    I DON'T WANT TO LIVE IN I-ROBOOOT!!! šŸ¤ŖšŸ¤ŖšŸ¤ŖšŸ¤Ŗ
    Seriously…
    Will we be allowed to sue if one day we see our own face on a screen saying or doing something we disagree with ??
    Freeakyyyy …
    šŸ˜³šŸ˜³šŸ¤ØšŸ¤ØšŸ§šŸ¤¬šŸ§šŸ˜¶šŸ˜¶šŸ™ƒ
    Waiting for the making of šŸ˜
    Will you do the "bĆŖtisier" like Toystories šŸ•šŸ¦– šŸ¤  and Shreck šŸ¤¢šŸ§Œ ?

  7. You really should have separate channel for AI stuff. It was very cool to see Affinity tips and tricks but personally I cant stand more AI blurry nonsense. Glad you found new fascination – much luck. Sadly its time to unsub for me. I am not outraged, I am not writing this to make you mad. I know one person means nothing in the grand scheme of things. Just letting you that maybe separate channel would be good. I would gladly watch your Affinity videos when the AI rage passes.

  8. can you please make a tutorial on how to make one? I am a writer and I would love to make some of my creations come to life in a form of a video like this, please! are there any videos you recommend watching to learn this?

  9. Nice job being the first lid on the block t do this!

    It's pretty low hanging fruit though

    Foe each shot there's a prompt – 'barelegged girl shown from the waist down in a yellow summer frock walking away from the camera in a field of yellow flowers' or 'close-up of Caucasian hands flipping through square color photos' and a base image
    Then you run the software and generate 200 iterations
    Toss the bizarros and flip-book the rest and you have one shot
    20 or 30 more and you have a video!

    There will be a tsunami of this sort of quick 'n dirty work but in a month or so the really good stuff will come and it will dazzle!

  10. I don't think you can do that with stable diffusion, unless you make all the images by hand and then tell it to improve them, otherwise the generation would not have continuity and the same textures and shapes in the images

  11. As a fellow AI art enthusiast I am amazed of what youve done!
    But Im sure that from a mainstream point of view it still looks a bit like the character are cursed in the video haha.

    That a first step after only such a short amount of time this tech is out, I cant imagine what we are going to do in a year or more.

Leave a Reply

Your email address will not be published. Required fields are marked *

© 2024 AI Art Video Tutorials