Duplicate from johnowhitaker/chiptunes_test

Co-authored-by: Jonathan Whitaker <johnowhitaker@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,24 @@
+---
+license: mit
+tags:
+- pytorch
+- diffusers
+- unconditional-audio-generation
+- diffusion-models-class
+---
+
+# Model Card for Unit 4 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class)
+
+This model is a diffusion model for unconditional audio generation of music in the genre Chiptune / Glitch
+
+## Usage
+
+```python
+from IPython.display import Audio
+from diffusers import DiffusionPipeline
+
+pipe = DiffusionPipeline.from_pretrained("johnowhitaker/chiptunes_test")
+output = pipe()
+display(output.images[0])
+display(Audio(output.audios[0], rate=pipe.mel.get_sample_rate()))
+```

mel/mel_config.json

@@ -0,0 +1,11 @@
+{
+  "_class_name": "Mel",
+  "_diffusers_version": "0.12.0.dev0",
+  "hop_length": 512,
+  "n_fft": 2048,
+  "n_iter": 32,
+  "sample_rate": 22050,
+  "top_db": 80,
+  "x_res": 256,
+  "y_res": 256
+}

model_index.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "AudioDiffusionPipeline",
+  "_diffusers_version": "0.12.0.dev0",
+  "mel": [
+    "audio_diffusion",
+    "Mel"
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DModel"
+  ],
+  "vqvae": [
+    null,
+    null
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,13 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.12.0.dev0",
+  "beta_end": 0.02,
+  "beta_schedule": "linear",
+  "beta_start": 0.0001,
+  "clip_sample": true,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": true,
+  "steps_offset": 0,
+  "trained_betas": null
+}

unet/config.json

@@ -0,0 +1,45 @@
+{
+  "_class_name": "UNet2DModel",
+  "_diffusers_version": "0.12.0.dev0",
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/diffusers/models--teticio--audio-diffusion-ddim-256/snapshots/27d950ab03120124323d38b9609749bf4c6d25ed/unet",
+  "act_fn": "silu",
+  "add_attention": true,
+  "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,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 256,
+  "time_embedding_type": "positional",
+  "up_block_types": [
+    "UpBlock2D",
+    "AttnUpBlock2D",
+    "UpBlock2D",
+    "UpBlock2D",
+    "UpBlock2D",
+    "UpBlock2D"
+  ]
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fcded9f9d9f114d2d04d230e6f67b5d11ca733ec3a95ff5a3f96b38145ea544
+size 454848893