Hugging Face's logo

teticio
/
audio-diffusion-256

Diffusers
TensorBoard
AudioDiffusionPipeline
audio
spectrograms
Model card Files Metrics Community
audio-diffusion-256
File size: 949 Bytes 
812ac9a
 
6cc0ed7
d89e0e9
812ac9a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
 
{
  "_class_name": "UNet2DModel",
  "_diffusers_version": "0.8.0.dev0",
  "_name_or_path": "/home/teticio/.cache/huggingface/diffusers/models--teticio--audio-diffusion-256/snapshots/01450560b35e76690e613b4c5e42d8133b9ca2d4/unet",
  "act_fn": "silu",
  "attention_head_dim": 8,
  "block_out_channels": [
    128,
    128,
    256,
    256,
    512,
    512
  ],
  "center_input_sample": false,
  "down_block_types": [
    "DownBlock2D",
    "DownBlock2D",
    "DownBlock2D",
    "DownBlock2D",
    "AttnDownBlock2D",
    "DownBlock2D"
  ],
  "downsample_padding": 1,
  "flip_sin_to_cos": true,
  "freq_shift": 0,
  "in_channels": 1,
  "layers_per_block": 2,
  "mid_block_scale_factor": 1,
  "norm_eps": 1e-05,
  "norm_num_groups": 32,
  "out_channels": 1,
  "sample_size": 256,
  "time_embedding_type": "positional",
  "up_block_types": [
    "UpBlock2D",
    "AttnUpBlock2D",
    "UpBlock2D",
    "UpBlock2D",
    "UpBlock2D",
    "UpBlock2D"
  ]
}