False. It's finetuned on spectograms of songs from diff music genres
MULTIMODAL AI
-
Stable Diffusion artifacts and training distribution drift analysis
By
–
Yep, resembles the artifacts I had here. I get a lot of zig zags too.
— Gene Kogan (@genekogan) 16 décembre 2022
I think our working hypothesis was that the output image gradually careens out of the training distribution, so even after noising it, SD doesn't quite know what to do with it.https://t.co/r1YZNzonfUYep, resembles the artifacts I had here. I get a lot of zig zags too. I think our working hypothesis was that the output image gradually careens out of the training distribution, so even after noising it, SD doesn't quite know what to do with it.
-
Riffusion Model Generates Music From Spectrograms Using Stable Diffusion
By
–
This space by @fffiloni powered by the Riffusion model by Seth Forsgren and Hayk Martiros to create music from spectrogram with stable diffusion is awesome! https://
huggingface.co/spaces/fffilon
i/spectrogram-to-music
… -
Riffusion Generates Surprisingly Good AI Music from Text Prompts
By
–
I can't stop playing with Riffusion. The music is surprisingly good. Credit to @JasonKuperberg for the prompt "Taylor Swift pop punk song" https://
riffusion.com/?&prompt=Taylo
r+Swift+pop+punk+song
… -
LoFi Generator AI Audio Quality Issues Criticized
By
–
hmm not good tho? https://
lofigenerator.com this sounds horrible -
Stable Diffusion Generates Music by Learning Images of Sheet Music
By
–
wait lol so turns out the solve to AI music generation wasnt novel approaches to learning the underlying structures of music
— swyx 🐣 (@swyx) 15 décembre 2022
it was taking #StableDiffusion and finetuning for IMAGES OF MUSIC
and THAT WORKS?!?
synesthetes could never 🤯 https://t.co/zSfpFqsP3N pic.twitter.com/8gTbG5ZZuHwait lol so turns out the solve to AI music generation wasnt novel approaches to learning the underlying structures of music it was taking #StableDiffusion and finetuning for IMAGES OF MUSIC and THAT WORKS?!? synesthetes could never
-
AI-Generated Lo-Fi Beats Could Dominate the Genre Completely
By
–
I could see LO FI be the first genre to be completely taken over by AI beats (LO FAI?), it's relatively simple, predictable and barely any vocals, could make a 24/7 livestream of perpetually generated LO FAI: https://t.co/3Urr3YHEKx pic.twitter.com/rNYI8taMsD
— @levelsio (@levelsio) 15 décembre 2022I could see LO FI be the first genre to be completely taken over by AI beats (LO FAI?), it's relatively simple, predictable and barely any vocals, could make a 24/7 livestream of perpetually generated LO FAI: https://
riffusion.com/?&prompt=lo-fi
+beat+for+the+holidays
… -
Dreambooth Outpainting Results for People Generation
By
–
I don't use SD for it 😛 can you show me your outpaint results for people from Dreambooth?
-
Werner Deploys Samsara AI Dashboard Cameras Across 8,500 Trucks
By
–
Truckload carrier
@One_Werner
tapped @Samsara for the rollout of dashboard cameras with #AI capabilities and computer vision that can perform object detection and live analysis in its 8,500 trucks
@bellelin_
#CIO #IoT -
Music Generation via Stable Diffusion Spectogram Finetuning
By
–
🤯🤯🤯
— @levelsio (@levelsio) 15 décembre 2022
Music generated by finetuning Stable Diffusion on spectograms then generating any song possiblehttps://t.co/UEn5J5dWI3 pic.twitter.com/AAvf7vOhqSMusic generated by finetuning Stable Diffusion on spectograms then generating any song possible http://
riffusion.com