Instructions to use MLXCreator/MLXCreator-ACEStep-1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use MLXCreator/MLXCreator-ACEStep-1.5 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("MLXCreator/MLXCreator-ACEStep-1.5", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - MLX
How to use MLXCreator/MLXCreator-ACEStep-1.5 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir MLXCreator-ACEStep-1.5 MLXCreator/MLXCreator-ACEStep-1.5
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "_class_name": "AutoencoderOobleck", | |
| "_diffusers_version": "0.34.0", | |
| "_name_or_path": "/root/data/repo/gongjunmin/ACE-Step-1.5/checkpoints/vae/", | |
| "audio_channels": 2, | |
| "channel_multiples": [ | |
| 1, | |
| 2, | |
| 4, | |
| 8, | |
| 16 | |
| ], | |
| "decoder_channels": 128, | |
| "decoder_input_channels": 64, | |
| "downsampling_ratios": [ | |
| 2, | |
| 4, | |
| 4, | |
| 6, | |
| 10 | |
| ], | |
| "encoder_hidden_size": 128, | |
| "sampling_rate": 48000 | |
| } | |