If you’re loving my workflow, don’t forget to sprinkle some love my way with a ❤️ ! Your support means the world!

Stable Audio Open 1.0, generating stereo audio of up to 47 seconds at 44.1kHz straight from your text prompts! It features three key components: an autoencoder that compresses waveforms for easy handling, a T5-based text embedding to enhance text conditioning, and a transformer-based diffusion model working in the autoencoder's latent space. Dive into the future of audio creation!

Downloads:

/models/clip/

https://huggingface.co/.../blob/main/model.safetensorsrename "t5_base.safetensors"

/models/checkpoints/

https://huggingface.co/.../blob/main/model.safetensorsrename "stable-audio-open-1.0.safetensors"

____________________

ComfyUI

https://www.facebook.com/groups/comfyui