Instructions to use kashif/music-spectrogram-diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kashif/music-spectrogram-diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kashif/music-spectrogram-diffusion", 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
Update scheduler/scheduler_config.json
Browse files
scheduler/scheduler_config.json
CHANGED
|
@@ -1,11 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "DDPMScheduler",
|
| 3 |
-
"_diffusers_version": "0.
|
| 4 |
"beta_end": 0.02,
|
| 5 |
"beta_schedule": "squaredcos_cap_v2",
|
| 6 |
"beta_start": 0.0001,
|
| 7 |
"clip_sample": true,
|
| 8 |
"num_train_timesteps": 1000,
|
|
|
|
| 9 |
"trained_betas": null,
|
| 10 |
"variance_type": "fixed_large"
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "DDPMScheduler",
|
| 3 |
+
"_diffusers_version": "0.9.0",
|
| 4 |
"beta_end": 0.02,
|
| 5 |
"beta_schedule": "squaredcos_cap_v2",
|
| 6 |
"beta_start": 0.0001,
|
| 7 |
"clip_sample": true,
|
| 8 |
"num_train_timesteps": 1000,
|
| 9 |
+
"prediction_type": "epsilon",
|
| 10 |
"trained_betas": null,
|
| 11 |
"variance_type": "fixed_large"
|
| 12 |
}
|