Are you tired of pictures created by artificial intelligence? So what about music?
Haebom
Created by
Haebom
Created at
Adobe’s research division recently announced a new experimental tool, Project Music GenAI Control, that will further advance the future of music creation. The technology has the potential to revolutionize the way music is made by giving users the ability to generate personalized audio and music through text prompts, and then edit it in detail later.
Adobe research scientist Nicholas Bryan says the project shows that generative AI can act as a co-creator in a user’s creative process, opening up new possibilities for custom music creation for broadcasters, podcasters, and anyone else with a diverse audio need.
DITTO- Diffusion Inference-Time T -Optimization for Music Generation.pdf5.108405MB
Adobe has also introduced commercially safe and popular AI technology in the field of image generation through a generative AI model called Firefly. Adobe is committed to the responsible development of AI technology, and recently added a digital watermark function to all generated content to verify the source of digital content. All image generation functions available in Photoshop and Express were based on this model.
According to the released footage and recently published research, Project Music GenAI Control allows users to generate music from simple text prompts such as “powerful rock,” “happy dance,” and “sad jazz.” The generated music can be finely tuned to the user’s liking, including tempo, structure, and intensity, and includes editing features such as melody transformation and repeatable loop creation.
The tool breaks away from traditional manual editing methods, allowing users to easily create and adjust the exact part of music they want. Bryan emphasized that the technology allows for “pixel-level control” over music, allowing creators to shape and adjust their audio more deeply.
If I dare to imagine, it would be amazing if it were integrated into Adobe's Premiere Pro or Audition app. Now that I think about it, there used to be a service called Adobe Soundbooth... If it comes out, it might make MIDI composition easier than GarageBand.
In fact, if you are bored while waiting, try Suno AI. It is the most fun service among T2A (Text-to-Audio). It is a unique friend that composes, writes lyrics, and provides vocal guidance to fit the genre and mood of a song that is about 1 minute long, complete with lyrics.
Subscribe to 'haebom'
📚 Welcome to Haebom's archives. --- I post articles related to IT 💻, economy 💰, and humanities 🎭. If you are curious about my thoughts, perspectives or interests, please subscribe. Would you like to be notified when new articles are posted? 🔔 Yes, that means subscribe. haebom@kakao.com
