Upload config.json with huggingface_hub
Browse files- config.json +101 -0
config.json
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "diffusion_cond",
|
| 3 |
+
"sample_size": 485100,
|
| 4 |
+
"sample_rate": 44100,
|
| 5 |
+
"video_fps": 5,
|
| 6 |
+
"audio_channels": 2,
|
| 7 |
+
"model": {
|
| 8 |
+
"pretransform": {
|
| 9 |
+
"type": "autoencoder",
|
| 10 |
+
"iterate_batch": true,
|
| 11 |
+
"config": {
|
| 12 |
+
"encoder": {
|
| 13 |
+
"type": "oobleck",
|
| 14 |
+
"requires_grad": false,
|
| 15 |
+
"config": {
|
| 16 |
+
"in_channels": 2,
|
| 17 |
+
"channels": 128,
|
| 18 |
+
"c_mults": [1, 2, 4, 8, 16],
|
| 19 |
+
"strides": [2, 4, 4, 8, 8],
|
| 20 |
+
"latent_dim": 128,
|
| 21 |
+
"use_snake": true
|
| 22 |
+
}
|
| 23 |
+
},
|
| 24 |
+
"decoder": {
|
| 25 |
+
"type": "oobleck",
|
| 26 |
+
"config": {
|
| 27 |
+
"out_channels": 2,
|
| 28 |
+
"channels": 128,
|
| 29 |
+
"c_mults": [1, 2, 4, 8, 16],
|
| 30 |
+
"strides": [2, 4, 4, 8, 8],
|
| 31 |
+
"latent_dim": 64,
|
| 32 |
+
"use_snake": true,
|
| 33 |
+
"final_tanh": false
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"bottleneck": {
|
| 37 |
+
"type": "vae"
|
| 38 |
+
},
|
| 39 |
+
"latent_dim": 64,
|
| 40 |
+
"downsampling_ratio": 2048,
|
| 41 |
+
"io_channels": 2
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"conditioning": {
|
| 45 |
+
"configs": [
|
| 46 |
+
{
|
| 47 |
+
"id": "video_prompt",
|
| 48 |
+
"type": "clip-with-sync-w-empty-feat",
|
| 49 |
+
"config": {
|
| 50 |
+
"clip_model_name": "clip-vit-base-patch32"
|
| 51 |
+
}
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"id": "text_prompt",
|
| 55 |
+
"type": "t5",
|
| 56 |
+
"config": {
|
| 57 |
+
"t5_model_name": "t5-base",
|
| 58 |
+
"max_length": 128
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"id": "audio_prompt",
|
| 63 |
+
"type": "mel_spec",
|
| 64 |
+
"config": {
|
| 65 |
+
"mel_spec_type": "mel_features",
|
| 66 |
+
"n_fft": 1024,
|
| 67 |
+
"hop_length": 256,
|
| 68 |
+
"win_length": 1024,
|
| 69 |
+
"n_mel_channels": 256,
|
| 70 |
+
"target_sample_rate": 24000
|
| 71 |
+
}
|
| 72 |
+
}
|
| 73 |
+
],
|
| 74 |
+
"cond_dim": 768
|
| 75 |
+
},
|
| 76 |
+
"diffusion": {
|
| 77 |
+
"cross_attention_cond_ids": ["video_prompt", "text_prompt", "audio_prompt"],
|
| 78 |
+
"global_cond_ids": [],
|
| 79 |
+
"type": "dit",
|
| 80 |
+
"gate": true,
|
| 81 |
+
"gate_type": "MAF",
|
| 82 |
+
"gate_type_config": {
|
| 83 |
+
"num_experts_per_modality": 64,
|
| 84 |
+
"num_heads": 24,
|
| 85 |
+
"num_fusion_layers": 8
|
| 86 |
+
},
|
| 87 |
+
"config": {
|
| 88 |
+
"io_channels": 64,
|
| 89 |
+
"embed_dim": 1536,
|
| 90 |
+
"depth": 24,
|
| 91 |
+
"num_heads": 24,
|
| 92 |
+
"cond_token_dim": 768,
|
| 93 |
+
"global_cond_dim": 768,
|
| 94 |
+
"project_cond_tokens": false,
|
| 95 |
+
"transformer_type": "continuous_transformer",
|
| 96 |
+
"video_fps": 5
|
| 97 |
+
}
|
| 98 |
+
},
|
| 99 |
+
"io_channels": 64
|
| 100 |
+
}
|
| 101 |
+
}
|