Beware though, in total I think we made around 3000 − 4000 song-generations to get the 15 that we felt happy about here. My guess is total effort per song was still somewhere in the 5-10 hours range or so, if you include all the dead ends and things that never worked out.
Hah, I’ve listened to Half an hour before Dawn in San Francisco a lot and I only realized just now that the AI by itself read “65,000,000” as “sixty-five thousand thousand”, which I always thought was an intentional poetic choice
And wow, huh, I definitely didn’t anticipate it took that much effort. Do you guys have any tips or anything you feel you learned about prompting Suno effectively that you can pass on from all that time spent with it?
Thanks for the album and all the work you put into it, too—I’ve listened to it a bunch over the last few days, and been moved by many parts of it, and am just generally grateful it exists :)
I think by far the biggest piece of advice I can give is “just press the generate button 3 times every time you finish a prompt”. The second biggest is “when you listen to the beginning of a song and it isn’t good, just skip it. You can continue generating from any point in a song, but you cannot take the middle or the end of any song, so if the beginning doesn’t work, you won’t be able to change it”.
Annotations in lyrics are very helpful. Most of our songs have things like “[instrument solo]” and various instructions like that written into the lyrics. They don’t get reliably observed, but good enough to steer the song.
Beyond that, it really depends on the song. I have a lot of detailed taste about what genres work well and which ones don’t, but that’s harder to quickly summarize.
Cherry-picking FTW. I wonder if Udio would be any easier than Suno, due to reportedly higher quality and backwards extension, although it wouldn’t have been available at the time.
I played around yesterday with Udio for like half an hour, but couldn’t get even the start of any usable song out of it.
It seems to me like the sample rate and artifacts are much less bad in Udio than Suno, but it seems to mess up the lyrics much more, and seems a lot less clever about how to fit the music around the lyrics. But I also might have just gotten some bad samples, not sure. I was hoping to play around a bit more.
Here is the Suno playlist which I think has all the styles and lyrics and prompts: https://app.suno.ai/playlist/ee2e7993-c6bc-4c7c-9975-db489ba0652a/
Beware though, in total I think we made around 3000 − 4000 song-generations to get the 15 that we felt happy about here. My guess is total effort per song was still somewhere in the 5-10 hours range or so, if you include all the dead ends and things that never worked out.
Hah, I’ve listened to Half an hour before Dawn in San Francisco a lot and I only realized just now that the AI by itself read “65,000,000” as “sixty-five thousand thousand”, which I always thought was an intentional poetic choice
Great, thank you!
And wow, huh, I definitely didn’t anticipate it took that much effort. Do you guys have any tips or anything you feel you learned about prompting Suno effectively that you can pass on from all that time spent with it?
Thanks for the album and all the work you put into it, too—I’ve listened to it a bunch over the last few days, and been moved by many parts of it, and am just generally grateful it exists :)
I think by far the biggest piece of advice I can give is “just press the generate button 3 times every time you finish a prompt”. The second biggest is “when you listen to the beginning of a song and it isn’t good, just skip it. You can continue generating from any point in a song, but you cannot take the middle or the end of any song, so if the beginning doesn’t work, you won’t be able to change it”.
Annotations in lyrics are very helpful. Most of our songs have things like “[instrument solo]” and various instructions like that written into the lyrics. They don’t get reliably observed, but good enough to steer the song.
Beyond that, it really depends on the song. I have a lot of detailed taste about what genres work well and which ones don’t, but that’s harder to quickly summarize.
Cherry-picking FTW. I wonder if Udio would be any easier than Suno, due to reportedly higher quality and backwards extension, although it wouldn’t have been available at the time.
I played around yesterday with Udio for like half an hour, but couldn’t get even the start of any usable song out of it.
It seems to me like the sample rate and artifacts are much less bad in Udio than Suno, but it seems to mess up the lyrics much more, and seems a lot less clever about how to fit the music around the lyrics. But I also might have just gotten some bad samples, not sure. I was hoping to play around a bit more.
Thank you again, much appreciated.
@Raemon told me to be aggressive with things like new lines and ellipses to alter the pacing.
Thank you, appreciate the tips.