Instructions to use ACE-Step/ACE-Step-v1-3.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ACE-Step/ACE-Step-v1-3.5B with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ACE-Step/ACE-Step-v1-3.5B", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - ACE-Step
How to use ACE-Step/ACE-Step-v1-3.5B with ACE-Step:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Error while using it with transformer
#18
by atifjamilfunsol - opened
I am getting the below error:
Entry Not Found for url: https://huggingface.co/ACE-Step/ACE-Step-v1-3.5B/resolve/main/model_index.json.
My code:
from transformers import AutoModel
# Load the ACE-Step model directly
model = AutoModel.from_pretrained(
"ACE-Step/Ace-Step1.5",
trust_remote_code=True,
dtype="auto" # automatically chooses float16 or float32 depending on hardware
)
# Example: you would then feed your prompt to the model manually
text_prompt = "A relaxing piano melody with soft strings"
# ACE-Step custom code usually provides a .generate() method for music
audio_tensor = model.generate(text_prompt)
print("Audio generated as a tensor with shape:", audio_tensor.shape)