Future is NOW. AI video with Deforum stable diffusion. #ai #trending
This is what my experiments look like for now.
I shot a video with Iphone 13 pro in cinematic mode, then I passed it through AI using Deforum_Stable_Diffusion_0.7, this is a notebook in google collab.
After some research and time spent with stable diffusion model I was not happy that I can’t really control any results much and I stumbled into Analog_Diffusion model. I added that model as a custom to Deforum notebook and since then I am pleased with results.
For the deforum settings you can ask me in comments, they are different for video and animation, also las image of video I’ve used as an init image for animation sequence. I create content with 12 frames per second, I noticed that 24 and 25 fps i can’t really make smooth. Smoothness is big deal here.)
I render everything with euler sampler, 120-180 steps with strength , means I am applying around 60 steps to the pictures, as I noticed 60 steps of euler is giving you nice looking picture already.
Then I wrote an animation sequence about 8 precise prompts long and added camera movement with a formula. Then I edited them together and made a sound, I had original voice in the video but I changed it with AI voice from and then enhanced it through
(I don’t really know how to post url’s here, but I will learn).
I can really recommend Adobe Enhancer, it makes nice voice even if you record it with mobile phone as I did.
Then I use Davinci resolve and Adobe Audition to make sound design, I make render of 12 frames per second and then interpolate it through Davinci with Optical Flow, Enhanced better settings. I’ve tried time warp but I didn’t notice any drastic changes in the picture and decided that it is not worth it.
It took me some time to make sound design and match it with voice, and I decided that a little psychedelic and glitchy sound will do the best, I want to create atmosphere of organic digital world.
Please like, share and subscribe. I need some conversations that will motivate me to continue working on it, but now I am passionate about it as never.
#shorts #stablediffusion #deforum #midjourney #analogdiffusion #animation #fashion #technology
1 view
4
0
2 days ago 00:09:38 1
Google’s AI Search Shocks the World: The Ultimate ChatGPT Challenger!
2 days ago 01:10:01 1
David Guetta | United at Home - Paris Edition from the Louvre
2 days ago 00:01:20 1
MK is tired of their bickering [Shadowpeach] (LMK animatic)
2 days ago 00:01:29 1
Top New Young Prnstars Part 67 Hottest New Faces
2 days ago 00:11:00 1
Guided Wim Hof Method Breathing
2 days ago 00:51:11 1
The Awakening - Warhammer 40K FanAnimation short movie -
2 days ago 00:04:29 1
Океан Ельзи - Не твоя війна | Ne tvoya viyna (official video)
2 days ago 02:21:14 1
Ignition Coil - Sphere Of Deep | Dj Set By Johnny M | Deep / Dub / Atmospheric
2 days ago 00:01:21 1
Top New Young Prnstars Part 66 Hottest New Faces
2 days ago 00:35:01 1
Prophecies - Spiritual States with Kabbalist Dr. Michael Laitman
2 days ago 01:18:36 1
Meshuggah - Summer Breeze 2024 - ARTE Concert
2 days ago 00:08:01 1
DIY Square Pipe Clamps - Welding DIY Project
2 days ago 01:16:06 1
Doctor DIED 3 TIMES: Now Knows We Have It COMPLETELY BACKWARDS! Dr. Lotte Valentin
2 days ago 00:02:21 1
AI Video Cyberpunk Dystopia | Neon Rebirth: Cybernetic Evolution
2 days ago 00:04:38 1
POWERWOLF - Demons Are A Girl’s Best Friend (Official Video) | Napalm Records
2 days ago 00:28:58 1
Serbia – Uncovering Europe’s MOST CONTROVERSIAL Country! 🇷🇸
2 days ago 00:07:10 1
La Tahzen (ENGLISH) | Mevlânâ Celâleddîn-i Rûmî
2 days ago 00:02:31 1
[Cantonese vs Mandarin Differences] Part 1: Pronunciation (SIDE-BY-SIDE COMPARISON)
2 days ago 00:57:40 1
Imperialism, social democracy, and fascism – Garland Nixon & Joti Brar, ep 22
2 days ago 00:01:25 1
Den of Wolves – Tech Demo Showcase | Unite 2024 (Unity Developer Conference)
2 days ago 00:02:06 4
THE DEFIANT Gameplay Trailer 4K (New FPS Game 2025)