upload files

beats/microsoft-deberta-v3-large.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1498d38c9cff8fb278b0d2e7a40a7b01c90e78caf9edba137258a35987849e9
+size 1744651736

chords/flan-t5-large.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d73492576022d13ac89e2c20c2e08c87a87f0edc164d5c883c3c7e32024a8e8
+size 3132793669

config.json

@@ -0,0 +1 @@
+{"text_encoder_name": "google/flan-t5-large", "scheduler_name": "stabilityai/stable-diffusion-2-1", "unet_model_name": null, "unet_model_config_path": "configs/music_diffusion_model_config.json", "snr_gamma": 5.0}

configs/main_config.json

@@ -0,0 +1 @@
+{"text_encoder_name": "google/flan-t5-large", "scheduler_name": "stabilityai/stable-diffusion-2-1", "unet_model_name": null, "unet_model_config_path": "configs/music_diffusion_model_config.json", "snr_gamma": 5.0}

configs/music_diffusion_model_config.json

@@ -0,0 +1,47 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.10.0.dev0",
+  "act_fn": "silu",
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "cross_attention_dim": 1024,
+  "down_block_types": [
+    "CrossAttnDownBlock2DMusic",
+    "CrossAttnDownBlock2DMusic",
+    "CrossAttnDownBlock2DMusic",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 8,
+  "layers_per_block": 2,
+  "mid_block_type": "UNetMidBlock2DCrossAttnMusic",
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 8,
+  "sample_size": [32, 2],
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2DMusic",
+    "CrossAttnUpBlock2DMusic",
+    "CrossAttnUpBlock2DMusic"
+  ],
+  "use_linear_projection": true,
+  "upcast_attention": true
+}

configs/stft_config.json

@@ -0,0 +1 @@
+{"filter_length": 1024, "hop_length": 160, "win_length": 1024, "n_mel_channels": 64, "sampling_rate": 16000, "mel_fmin": 0, "mel_fmax": 8000}

configs/vae_config.json

@@ -0,0 +1 @@
+{"image_key": "fbank", "subband": 1, "embed_dim": 8, "time_shuffle": 1, "ddconfig": {"double_z": true, "z_channels": 8, "resolution": 256, "downsample_time": false, "in_channels": 1, "out_ch": 1, "ch": 128, "ch_mult": [1, 2, 4], "num_res_blocks": 2, "attn_resolutions": [], "dropout": 0.0}, "scale_factor": 0.9227914214134216}

ldm/pytorch_model_ldm.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7cad0ff3dd6b346898b12b2e3627e8262684646ff82f59d0a69891e42fcaa66
+size 7051656406

stft/pytorch_model_stft.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8674a4cc9755fafa48350bfa3412cf9b9a0d357d18289dbfd86f0fb34e1ca4db
+size 8537803

vae/pytorch_model_vae.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d49e1881f38bd4f4fcaaf1c56686c02fb15f75e80dec5f773ae235b2cf1b61b
+size 442713669