MusicLM is wild. Very realistic and versatile, can condition on text, images, and other audio. Coolest feature: hum or whistle a melody, input some text (e.g. "string quartet") and it spits out a string quartet playing that melody! https://
google-research.github.io/seanet/musiclm
/examples/
…
@genekogan
-
MusicLM: Google’s AI Generates Music From Text and Audio
By
–
-
Eden Team Develops Online Interface for Real2Real Technology
By
–
The Eden team is working on an online interface to make these. More info soon.
— Gene Kogan (@genekogan) 19 janvier 2023
Kudos to @xsteenbrugge for perfecting #real2real! No telling where these go after another year of R&D. https://t.co/vor3ZSjzXIThe Eden team is working on an online interface to make these. More info soon. Kudos to @xsteenbrugge for perfecting #real2real! No telling where these go after another year of R&D.
-
DDC/CI Monitor Compatibility and Linux HDMI Integration
By
–
this looks promising. do all monitors support DDC/CI? and how do you interface with it if a linux machine is connected HDMI to it?
-
Remote Monitor Control: Programmatic Power On/Off Solutions
By
–
Can anyone recommend a way to remotely/programatically turn on and off an external monitor?
-
Tech-Optimistic Internet: Leveraging Digital Tools While Honoring Human Nature
By
–
our goal with @Mars_College is kind of this. very tech-optimistic, but use the internet for what it’s good for, untangle from that the things it can’t fulfill by itself (nature and humans)
-
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.
-
ChatGPT Technical Details Related to InstructGPT Research
By
–
relatively few technical details have been released so far, but chatgpt is related to instructgpt https://
arxiv.org/abs/2203.02155 -
DALL-E Windows Midjourney Mac Stable Diffusion Linux
By
–
DALL-E = Windows
Midjourney = Mac
Stable Diffusion = Linux -
Interview on Abraham AI and Generative AI Space Insights
By
–
Nice interview with me about @abraham_ai_ and some thoughts on the emerging generative AI space. This interview was actually done in June, which is why Stable Diffusion is conspicuously missing
-
Diffusion Models for Audio: Denoising as Subtractive Synthesis
By
–
Always thought diffusion was best suited for audio. Denoising = subtractive synthesis.