131–140 of 291 posts
That is a very cool UI; super fun to just hit random and find new niche genres/styles. I'd never heard of klezmer, for example, but such a nice style! I don't know if it's the music, but it's been a while since a website has put this big a grin on my face! I keep wanting to save some of the songs I hear. Damn, I don't think I would really be able to tell in a blind test that these were AI.
Earlier quoted context omitted.
Would you mind making these available to others?
Sure! I "re-mastered" my mini-album with v4.5 since that's more in the spirit of the discussion. https://suno.com/playlist/e6c3f3d1-a746-4106-bea1-e36073d227... Side note: It feels a little vulnerable to be sharing these. They genuinely helped me through difficult times and I wasn't really expecting anyone else to ever listen to them.
Earlier quoted context omitted.
Yeah, I find it funny that they have this super strong music generation model, but then they use what could only be GPT 3.5 for lyrics.
I think it's because, like a first year writing student trying poetry, it tries a little too hard to make the lyrics coherent and storytelling in a script read from a page. A lot of real song lyrics have a whole lot of repetition, non sequiturs, and break grammar rules to fit the meter better
The fact that LLMs compute an average of human culture is more apparent in music AIs than any other medium. You cannot get these things to do anything original, same as with images, designs and creative writing—and it's not an "intelligence" problem. I'm not sure if this is solvable, but I think it should be a bigger research topic. If anyone knows of any papers on this, I haven't found one yet (not sure what to sear…
Any musician will tell you most music isn't original. You just don't have the ear for it. You telling me Green Day's songs are all unique and original? Even jazz uses 6-2-5-1's over and over. Unless you only listen to avante garde prog rock or something, all of music is derivative. And that's ok. Every song being a unique snowflake isn't important. If you like it or it makes you feel something, that's all that matter…
You’re right!
> Even jazz uses 6-2-5-1's over and over.
You’re not even wrong! I wonder if jazz does anything else besides that?
Earlier quoted context omitted.
I mean there is a Cursor integration for Ableton Live: https://www.youtube.com/watch?v=QXSImhfS15k Plus Ableton Live itself has a lot of generative tools these days: https://www.youtube.com/watch?v=_RNXVfo-oLc But I honestly don't see the point. The journey is the whole point when making music or any art really. AI doesn't solve a problem here. There never has been one in the first place. There is more music out ther…
There’s not one right way you art. . . Plenty of artists like Warhol and Dali used mass production and automation. If you enjoy writing music your way, great. But I strongly disagree that it’s a mistake to enable people to approach it differently.
All my artists friends where criticizing it and I was thinking it was some form of Neo-Ludditism that they were following. Why not embrace progress? No one is stopping them to not use it but if it helps lower the barrier of entry isn't that great? Surely generative AI could be used to enhance of the workflow of an artist?
Oh, how I have been wrong. In reality it has only been used to replace artists. To devalue their work. It has not place in a artists pipeline.
https://aftermath.site/ai-video-game-development-art-vibe-co...
I think the use of generative AI or at least of generalist LLM's is something fundamentally different than artists embracing new media and new processes. Like digital drawing is still roughly the same process as drawing on paper. The process is largely the same and most skills carry over. You are still in control. Using a prompt to create images is something that is not drawing.
I also recommend:
Or, if I'm listening to music just for the vibe, I really don't care how it's created, as long as it doesn't offend me auditorially. I'm really not listening actively. So I suppose that's a bit of an indictment of myself, but I don't think it's a serious character flaw in myself. I should probably just try to pay more attention to the people around me at all times.
I have a lot of fun putting my own poetry in here and mashing it up with the styles that I enjoy listening to, or that I think would work well with the poem. Again, I don't want to like it, but I do.
One of Suno's biggest weakness is their lyrics generation, and that you can't generate lyrics without also generating a song. I think it's better to use a different LLM to generate and iterate on lyrics, which you can then pass to Suno in order to generate a final song. If anyone here has a subscription and they can spare the tokens, I think it would be fun if someone shared a song about Hacker News. I'm hoping that…
We can do better on user instruction for sure, duly noted. In my experience a lot of different stuff works (emotions, some musical direction sometimes, describing parts/layers of the track you want to exist, music-production-ish terminology, genres, stuff like intro/outro/chorus), but I think of it more as steering the space of the generated output rather than working 100% of the time. This can go in the style tags or in [brackets] in the lyrics. Definitely makes a difference in the outputs to be more descriptive with 4.5.
The fact that LLMs compute an average of human culture is more apparent in music AIs than any other medium. You cannot get these things to do anything original, same as with images, designs and creative writing—and it's not an "intelligence" problem. I'm not sure if this is solvable, but I think it should be a bigger research topic. If anyone knows of any papers on this, I haven't found one yet (not sure what to sear…
Earlier quoted context omitted.
You can do a lot more detailed prompts with v4.5 than previously and instructions in [brackets] also go a long way now.
Could you elaborate on the instructions in brackets part?
For example I was trying to steer a melodic techno prompt recently in a better direction by putting stuff like this upfront:
[intro - dramatic synths, pulsing techno bass]
[organic percussive samples]
[rolling galloping pulsing gritty bassline]
[soaring experimental synths, modulation heavy, echos, sound design, 3d sound]
[lush atmosphere, variation]
[hypnotic groovy arppegiation arps]
[sampled repetitive trippy vocal]
I also often use them to structure things around song structure like [intro], [break], [chorus], and even get more descriptive with these describing things or moments I'd like to happen. Again adherence is not perfect, but seems to help steer things.
One of my favorite tags I've seen is [Suck the entire song through vacuum] and well... I choose to believe, check out 1:29 https://suno.com/s/xdIDhlKQUed0Dp1I
Worth playing around with a bunch, especially if you're not quite getting something interesting or in the direction you want.
The biggest impact Generative Music had on my life was for wedding skits. Families that wanted a funny song about the bride filled with anecdotes didn't need talent anymore. The first time I heard it, it was incredible. The 2nd wedding that did it, it started to feel boring. The 3rd time, everyone hated it. Similar to image-generation, we're getting tired really fast of cookie-cutter art. I don't know how to feel abo…
AI art is like dreams. I'm amused by my own but never want to hear about anyone else's.
That's not a tool issue. It just means that working on a raised floor is not the same a being able to reach a higher ceiling.