gougouccnu/stable-audio-open-1.0 🔢📝 → 🖼️

▶️ 581 runs 📅 Jan 2025 ⚙️ Cog 0.13.6
music-generation sound-effect-generation text-to-audio

About

Example Output

Prompt:

"A toilet flushing."

Output

Example output

Performance Metrics

7.73s Prediction Time
370.79s Total Time
All Input Parameters
{
  "seed": -1,
  "steps": 100,
  "prompt": "A toilet flushing.",
  "cfg_scale": 6,
  "sigma_max": 500,
  "sigma_min": 0.03,
  "batch_size": 1,
  "sampler_type": "dpmpp-3m-sde",
  "seconds_start": 0,
  "seconds_total": 8,
  "negative_prompt": "",
  "init_noise_level": 1
}
Input Parameters
seed Type: integerDefault: -1
steps Type: integerDefault: 100
prompt (required) Type: string
cfg_scale Type: numberDefault: 6
sigma_max Type: integerDefault: 500
sigma_min Type: numberDefault: 0.03
batch_size Type: integerDefault: 1
sampler_type Type: stringDefault: dpmpp-3m-sde
seconds_start Type: integerDefault: 0
seconds_total Type: integerDefault: 8Range: ∞ - 47
negative_prompt Type: stringDefault:
init_noise_level Type: numberDefault: 1
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
Prompt: A toilet flushing.
2887216820
/src/stable_audio_tools/models/conditioners.py:314: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead.
with torch.cuda.amp.autocast(dtype=torch.float16) and torch.set_grad_enabled(self.enable_grad):
/src/stable_audio_tools/inference/sampling.py:177: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead.
with torch.cuda.amp.autocast():
  0%|          | 0/100 [00:00<?, ?it/s]/root/.pyenv/versions/3.10.15/lib/python3.10/contextlib.py:103: FutureWarning: `torch.backends.cuda.sdp_kernel()` is deprecated. In the future, this context manager will be removed. Please see `torch.nn.attention.sdpa_kernel()` for the new context manager, with updated signature.
self.gen = func(*args, **kwds)
  1%|          | 1/100 [00:00<00:23,  4.27it/s]
  3%|▎         | 3/100 [00:00<00:11,  8.17it/s]
  5%|▌         | 5/100 [00:00<00:09, 10.50it/s]
  7%|▋         | 7/100 [00:00<00:07, 11.79it/s]
  9%|▉         | 9/100 [00:00<00:07, 12.69it/s]
 11%|█         | 11/100 [00:00<00:06, 13.32it/s]
 13%|█▎        | 13/100 [00:01<00:06, 13.46it/s]
 15%|█▌        | 15/100 [00:01<00:06, 13.65it/s]
 17%|█▋        | 17/100 [00:01<00:05, 14.15it/s]
 19%|█▉        | 19/100 [00:01<00:05, 14.50it/s]
 21%|██        | 21/100 [00:01<00:05, 14.73it/s]
 23%|██▎       | 23/100 [00:01<00:05, 14.91it/s]
 25%|██▌       | 25/100 [00:01<00:05, 14.90it/s]
 27%|██▋       | 27/100 [00:02<00:04, 14.98it/s]
 29%|██▉       | 29/100 [00:02<00:04, 14.95it/s]
 31%|███       | 31/100 [00:02<00:04, 15.03it/s]
 33%|███▎      | 33/100 [00:02<00:04, 15.05it/s]
 35%|███▌      | 35/100 [00:02<00:04, 15.13it/s]
 37%|███▋      | 37/100 [00:02<00:04, 15.13it/s]
 39%|███▉      | 39/100 [00:02<00:04, 15.15it/s]
 41%|████      | 41/100 [00:02<00:03, 15.20it/s]
 43%|████▎     | 43/100 [00:03<00:03, 15.31it/s]
 45%|████▌     | 45/100 [00:03<00:03, 15.23it/s]
 47%|████▋     | 47/100 [00:03<00:03, 15.33it/s]
 49%|████▉     | 49/100 [00:03<00:03, 15.30it/s]
 51%|█████     | 51/100 [00:03<00:03, 15.38it/s]
 53%|█████▎    | 53/100 [00:03<00:03, 15.29it/s]
 55%|█████▌    | 55/100 [00:03<00:02, 15.31it/s]
 57%|█████▋    | 57/100 [00:03<00:02, 15.25it/s]
 59%|█████▉    | 59/100 [00:04<00:02, 15.20it/s]
 61%|██████    | 61/100 [00:04<00:02, 15.03it/s]
 63%|██████▎   | 63/100 [00:04<00:02, 15.17it/s]
 65%|██████▌   | 65/100 [00:04<00:02, 14.64it/s]
 67%|██████▋   | 67/100 [00:04<00:02, 14.60it/s]
 69%|██████▉   | 69/100 [00:04<00:02, 14.43it/s]
 71%|███████   | 71/100 [00:04<00:01, 14.57it/s]
 73%|███████▎  | 73/100 [00:05<00:01, 14.57it/s]
 75%|███████▌  | 75/100 [00:05<00:01, 14.81it/s]
 77%|███████▋  | 77/100 [00:05<00:01, 14.81it/s]
 79%|███████▉  | 79/100 [00:05<00:01, 14.98it/s]
 81%|████████  | 81/100 [00:05<00:01, 15.16it/s]
 83%|████████▎ | 83/100 [00:05<00:01, 15.24it/s]
 85%|████████▌ | 85/100 [00:05<00:00, 15.34it/s]
 87%|████████▋ | 87/100 [00:06<00:00, 15.44it/s]
 89%|████████▉ | 89/100 [00:06<00:00, 15.35it/s]
 91%|█████████ | 91/100 [00:06<00:00, 15.42it/s]
 93%|█████████▎| 93/100 [00:06<00:00, 15.37it/s]
 95%|█████████▌| 95/100 [00:06<00:00, 15.34it/s]
 97%|█████████▋| 97/100 [00:06<00:00, 15.43it/s]/root/.pyenv/versions/3.10.15/lib/python3.10/site-packages/torchsde/_brownian/brownian_interval.py:599: UserWarning: Should have ta>=t0 but got ta=0.029999999329447746 and t0=0.03.
warnings.warn(f"Should have ta>=t0 but got ta={ta} and t0={self._start}.")
 99%|█████████▉| 99/100 [00:06<00:00, 15.43it/s]
100%|██████████| 100/100 [00:06<00:00, 14.61it/s]
Version Details
Version ID
0f69810d42dd9098b8d20d0c8db087fbfd5ccd1704eef0a99a48c7325ab7fc3a
Version Created
January 8, 2025
Run on Replicate →