Text-to-Audio
Diffusers
Safetensors
English
StableDiffusionPipeline
audio
audio-generation
diffusion
one-step-diffusion
variational-score-distillation
auffusion
Instructions to use dinhhung1508/SwiftAudio with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use dinhhung1508/SwiftAudio with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("dinhhung1508/SwiftAudio", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| { | |
| "resblock": "1", | |
| "num_gpus": 0, | |
| "batch_size": 16, | |
| "learning_rate": 0.0002, | |
| "adam_b1": 0.8, | |
| "adam_b2": 0.99, | |
| "lr_decay": 0.999, | |
| "seed": 1234, | |
| "upsample_rates": [ | |
| 5, | |
| 4, | |
| 4, | |
| 2 | |
| ], | |
| "upsample_kernel_sizes": [ | |
| 11, | |
| 8, | |
| 8, | |
| 4 | |
| ], | |
| "upsample_initial_channel": 512, | |
| "resblock_kernel_sizes": [ | |
| 3, | |
| 7, | |
| 11 | |
| ], | |
| "resblock_dilation_sizes": [ | |
| [ | |
| 1, | |
| 3, | |
| 5 | |
| ], | |
| [ | |
| 1, | |
| 3, | |
| 5 | |
| ], | |
| [ | |
| 1, | |
| 3, | |
| 5 | |
| ] | |
| ], | |
| "segment_size": 5120, | |
| "num_mels": 256, | |
| "num_freq": 2049, | |
| "n_fft": 2048, | |
| "hop_size": 160, | |
| "win_size": 1024, | |
| "sampling_rate": 16000, | |
| "fmin": 0, | |
| "fmax": null, | |
| "fmax_for_loss": null, | |
| "num_workers": 4, | |
| "dist_config": { | |
| "dist_backend": "nccl", | |
| "dist_url": "tcp://localhost:54321", | |
| "world_size": 1 | |
| } | |
| } |