How to use tinytrashlabs/dia2-1b-mlx-bf16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir dia2-1b-mlx-bf16 tinytrashlabs/dia2-1b-mlx-bf16
How to use tinytrashlabs/dia2-1b-mlx-bf16 with Dia2:
from dia2 import Dia2, GenerationConfig, SamplingConfig dia = Dia2.from_repo("tinytrashlabs/dia2-1b-mlx-bf16", device="cuda", dtype="bfloat16") config = GenerationConfig( cfg_scale=2.0, audio=SamplingConfig(temperature=0.8, top_k=50), use_cuda_graph=True, ) result = dia.generate("[S1] Hello Dia2!", config=config, output_wav="hello.wav", verbose=True)
The community tab is the place to discuss and collaborate with the HF community!
