Audio-to-Audio
Diffusers
Safetensors
SpanSynthEditPipeline
audio
music
midi
midi-to-audio
flow-matching
Instructions to use mimbres/spansynth-edit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use mimbres/spansynth-edit with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("mimbres/spansynth-edit", 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
Download codec/config.json from mimbres/spansynth-edit: direct link, hf CLI and curl.
- Browser
- Download file 778 Bytes
-
https://huggingface.co/mimbres/spansynth-edit/resolve/main/codec/config.json
- Command line
-
hf download hf://mimbres/spansynth-edit/codec/config.json
-
curl -L -o config.json https://huggingface.co/mimbres/spansynth-edit/resolve/main/codec/config.json
778 Bytes
| { | |
| "_class_name": "HeartCodecModel", | |
| "_diffusers_version": "0.40.0", | |
| "codec_config": { | |
| "causal": true, | |
| "channel_mults": [ | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2 | |
| ], | |
| "config_source_notes": null, | |
| "default_kernel_size": 7, | |
| "delay_kernel_size": 5, | |
| "downsample_factors": [ | |
| 3, | |
| 4, | |
| 4, | |
| 4, | |
| 5 | |
| ], | |
| "downsample_kernel_sizes": [ | |
| 6, | |
| 8, | |
| 8, | |
| 8, | |
| 10 | |
| ], | |
| "init_channel": 64, | |
| "latent_hidden_dim": 128, | |
| "mode": "pre_proj", | |
| "num_bands": 1, | |
| "num_samples": 2, | |
| "res_kernel_size": 7, | |
| "sample_rate": 48000, | |
| "upsample_factors": [ | |
| 5, | |
| 4, | |
| 4, | |
| 4, | |
| 3 | |
| ], | |
| "upsample_kernel_sizes": [ | |
| 10, | |
| 8, | |
| 8, | |
| 8, | |
| 6 | |
| ] | |
| } | |
| } | |