upload_audiox-mmdit
Browse files- VAE.ckpt +3 -0
- config.json +136 -0
- model.ckpt +3 -0
VAE.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02e8a84bd5c1ee8a812609b03286ec85b856cb3ee8cd607083563de67347e621
|
| 3 |
+
size 624540628
|
config.json
ADDED
|
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "audio_autoencoder_v2",
|
| 64 |
+
"config": {
|
| 65 |
+
"sample_rate": 44100,
|
| 66 |
+
"pretransform_config": {
|
| 67 |
+
"type": "autoencoder",
|
| 68 |
+
"iterate_batch": true,
|
| 69 |
+
"config": {
|
| 70 |
+
"encoder": {
|
| 71 |
+
"type": "oobleck",
|
| 72 |
+
"requires_grad": false,
|
| 73 |
+
"config": {
|
| 74 |
+
"in_channels": 2,
|
| 75 |
+
"channels": 128,
|
| 76 |
+
"c_mults": [1, 2, 4, 8, 16],
|
| 77 |
+
"strides": [2, 4, 4, 8, 8],
|
| 78 |
+
"latent_dim": 128,
|
| 79 |
+
"use_snake": true
|
| 80 |
+
}
|
| 81 |
+
},
|
| 82 |
+
"decoder": {
|
| 83 |
+
"type": "oobleck",
|
| 84 |
+
"config": {
|
| 85 |
+
"out_channels": 2,
|
| 86 |
+
"channels": 128,
|
| 87 |
+
"c_mults": [1, 2, 4, 8, 16],
|
| 88 |
+
"strides": [2, 4, 4, 8, 8],
|
| 89 |
+
"latent_dim": 64,
|
| 90 |
+
"use_snake": true,
|
| 91 |
+
"final_tanh": false
|
| 92 |
+
}
|
| 93 |
+
},
|
| 94 |
+
"bottleneck": {
|
| 95 |
+
"type": "vae"
|
| 96 |
+
},
|
| 97 |
+
"latent_dim": 64,
|
| 98 |
+
"downsampling_ratio": 2048,
|
| 99 |
+
"io_channels": 2
|
| 100 |
+
}
|
| 101 |
+
},
|
| 102 |
+
"pretransform_ckpt_path": "./model/VAE.ckpt",
|
| 103 |
+
"latent_seq_len": 215,
|
| 104 |
+
"mask_ratio_start": 0,
|
| 105 |
+
"mask_ratio_end": 0
|
| 106 |
+
}
|
| 107 |
+
}
|
| 108 |
+
],
|
| 109 |
+
"cond_dim": 768
|
| 110 |
+
},
|
| 111 |
+
"diffusion": {
|
| 112 |
+
"cross_attention_cond_ids": ["video_prompt", "text_prompt", "audio_prompt"],
|
| 113 |
+
"global_cond_ids": [],
|
| 114 |
+
"type": "mmdit",
|
| 115 |
+
"gate": true,
|
| 116 |
+
"gate_type": "MAF",
|
| 117 |
+
"gate_type_config": {
|
| 118 |
+
"num_experts_per_modality": 64,
|
| 119 |
+
"num_heads": 24,
|
| 120 |
+
"num_fusion_layers": 8
|
| 121 |
+
},
|
| 122 |
+
"config": {
|
| 123 |
+
"io_channels": 64,
|
| 124 |
+
"embed_dim": 1536,
|
| 125 |
+
"depth": 24,
|
| 126 |
+
"num_heads": 24,
|
| 127 |
+
"cond_token_dim": 768,
|
| 128 |
+
"global_cond_dim": 768,
|
| 129 |
+
"project_cond_tokens": false,
|
| 130 |
+
"transformer_type": "continuous_transformer",
|
| 131 |
+
"video_fps": 5
|
| 132 |
+
}
|
| 133 |
+
},
|
| 134 |
+
"io_channels": 64
|
| 135 |
+
}
|
| 136 |
+
}
|
model.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b20ef15c59f33d7daae3601cee32c61212cf256edc7576c2c5db9390299aa66c
|
| 3 |
+
size 10843616882
|