Stable Audio Open v1.0 has been released by FAL, offering a new and powerful model for generating audio. The tool can create 30-second audio clips in just 2 seconds and is available on multiple platforms including @runpod_io's serverless L40. The model has also been integrated into Palladium, a free Blender add-on, enabling functionalities such as image-to-text-to-audio conversion. Users can test the model and explore its capabilities, which include multiplayer features and novel prompting techniques. Thanks to Ameerazam18 for merging the multiplayer PR to the Space, turning this exploration into a collective learning experience.
🎵 Stable Audio Open v1.0 is now available on 🥪 https://t.co/0BLihhtQE7 🥳 with @runpod_io serverless L40 🔥 Please try it 🐣 🌐page: https://t.co/wvXRhx18ai 🧬code: https://t.co/FqMAGtHAZL 🍇runpod: https://t.co/nwPFup2Vgl 🍊jupyter: https://t.co/SSU89Iy2yz https://t.co/gXp8ecnsEM https://t.co/oBILOnavqT
🎵 Stable Audio Open v1.0 is now available on 🥪 https://t.co/0BLihhtQE7 🥳 with @runpod_io serverless L40 🔥 Please try it 🐣 🌐page: https://t.co/wvXRhx18ai 🧬code: https://t.co/FqMAGtHAZL 🍇runpod: https://t.co/nwPFup2Vgl 🍊jupyter: please try it 🐣 https://t.co/SSU89Iy2yz https://t.co/c4L7ZPp4Om https://t.co/oBILOnavqT
Stable Audio Open implemented in the free Blender add-on, Palladium, so now you can do ex. image-to-text-to-audio: #b3d https://t.co/TSpmB5BKs4
Stable Audio Open Multiplayer is here! 🤼♂️ The model is powerful 🔊 but prompting it is very novel ✏️ Thanks @Ameerazam18 for merging my multiplayer PR to your Space - turning this exploration into a collective learning experience 🎓 ▷ https://t.co/k3Uzr1LCK8 https://t.co/6X8gc8iqE0
Stable Audio sounds like a game changer 🤯 https://t.co/WDKuOGfODO
You can already test "Stable Audio Open" here, by @FAL This 30-second audio took me 2 seconds to generate! https://t.co/w6hXAt8Fzf