Text-to-Audio
Transformers
Diffusers
Safetensors
ACE-Step
feature-extraction
audio
music
text2music
custom_code
Instructions to use ACE-Step/Ace-Step1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ACE-Step/Ace-Step1.5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="ACE-Step/Ace-Step1.5", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ACE-Step/Ace-Step1.5", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Instrumental-only support?
#6
by marksverdhei - opened
Ace step 1 did fine on music with vocals but pretty poorly on instrumental electronic music / synthwave / drum and bass / breakcore genre.
I'm wondering if any of the 1.5 family support generating instrumental tracks with
no vocal or if that just throws the model off. If it does, is there any specific prompt we should use
to indicate or just leave the lyrics empty?
E.g. suno uses
[Instrumental]
As lyrics for this.
And thank you for releasing an open-source music generation model!
Ok literally just tried the HF space and it answered my question. Cheers!
marksverdhei changed discussion status to closed