KEWL - Echosphere (Music Video)

Animated AI background video generated in Deforum Stable Diffusion. Compositing, lyrics and audio reactive effects edited in After Effects.
Music 🎵
KEWL - Echosphere
Playlists 🤘
Lyric Videos: • Lyric Videos
Lyrics 🎶
Take a step into the hum of the wires
Shadows stretch like digital fires
We’re bound by threads of forgotten sound
A maze of echoes pulling us down
Through the glass, your reflection lies
Splintered truths in synthetic skies
No cure for the static that clings to your frame
No map to guide us, just the void we claim
Drive it home
Bury the body in its glow
Fractured tone
Left to wander what we’ll never know
In the echosphere
Every thought is an anchor, pulling near
Lost in the hollow hum
Chasing the ghost of what we’ve become
They’re whispering in the cracks of the seams
A fragile network of dismantled dreams
We weave these wires like webs in the dark
Trace the patterns where the fractures spark
The edge is sharp, but it feels alive
A neon hymn in which we survive
Through all the voices tearing away
I’d rather be lost than choose to obey
Drive it home
Bury the body in its glow
Fractured tone
Left to wander what we’ll never know
In the echosphere
Every thought is an anchor, pulling near
Lost in the hollow hum
Chasing the ghost of what we’ve become
The void calls your name
We’re alone, but the song feels the same
Static fills the air
And we fall, we fall
Just to pretend we were there
Drive it home
Bury the body in its glow
Fractured tone
Left to wander what we’ll never know
In the echosphere
Every thought is an anchor, pulling near
Lost in the hollow hum
Chasing the ghost of what we’ve become
Tools 🛠️
Background made in Automatic1111 Stable Diffusion Deforum extension with help from ChatGPT.
Edited in Adobe Premiere Pro and After Effects.
Process 🪄
1. Finding fitting stable diffusion prompts for the music video.
I ask ChatGPT to give me fitting prompts based on the lyrics I feed it. I test the outputs and make changes based on the results from img2img generations with Stable Diffusion. I also try out different models and Loras to find outputs I like.
2. Getting music reactive keyframes for the animation.
I give the song to this audio keyframe tool: www.chigozie.c... and give it suitable functions for the values I want. I personally use 25 frames per second, something like “0.60 - x^6” for strength schedule and “1 + x*10” for Translation Z in 3D mode. I often play around with these settings and also give the 3D rotations different functions to react to.
3. Setting up a render in Deforum.
Now I enter the keyframes and prompts into Deforum to start generating an animation. I usually do this 4 times with slightly tweaked settings and prompts to get different results to work with later.
4. Editing in Premiere Pro.
To get a more dynamic video, I cut between the different animations in a multicam sequence, picking the best parts and cutting to the music.
5. Finishing up in After Effects.
In After Effects I manually add the lyrics, timing and dividing them as I see fit. I also add a bunch of effects like additional 3D camera movements, shakes, overlays, particles, blur and chromatic aberration. Most of these are made to react to the music through generated audio keyframes.
#lyrics #lyricvideo #lyricsvideo