Upload StableDiffusionCLAPPipeline

audio_encoder/config.json

@@ -1,49 +1,29 @@
 {
-  "_name_or_path": "dhuck/stable-diffusion-clap/audio_encoder",
-  "aff_block_r": 4,
+  "_name_or_path": "laion/larger_clap_music",
   "architectures": [
-    "ClapAudioModel"
+    "ClapModel"
   ],
-  "attention_probs_dropout_prob": 0.0,
-  "depths": [
-    2,
-    2,
-    12,
-    2
-  ],
-  "drop_path_rate": 0.0,
-  "enable_fusion": false,
-  "enable_patch_layer_norm": true,
-  "flatten_patch_embeds": true,
-  "fusion_type": null,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "audio_config": {
+    "depths": [
+      2,
+      2,
+      12,
+      2
+    ],
+    "hidden_size": 1024,
+    "model_type": "clap_audio_model",
+    "patch_embeds_hidden_size": 128
+  },
+  "hidden_size": 768,
   "initializer_factor": 1.0,
-  "layer_norm_eps": 1e-05,
-  "mlp_ratio": 4.0,
-  "model_type": "clap_audio_model",
-  "num_attention_heads": [
-    4,
-    8,
-    16,
-    32
-  ],
-  "num_classes": 527,
-  "num_hidden_layers": 4,
-  "num_mel_bins": 64,
-  "patch_embed_input_channels": 1,
-  "patch_embeds_hidden_size": 128,
-  "patch_size": 4,
-  "patch_stride": [
-    4,
-    4
-  ],
+  "logit_scale_init_value": 14.285714285714285,
+  "model_type": "clap",
+  "num_hidden_layers": 16,
   "projection_dim": 512,
   "projection_hidden_act": "relu",
-  "qkv_bias": true,
-  "spec_size": 256,
+  "text_config": {
+    "model_type": "clap_text_model"
+  },
   "torch_dtype": "float32",
-  "transformers_version": "4.37.1",
-  "window_size": 8
+  "transformers_version": "4.37.1"
 }

audio_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0542c0ea071de5a84232c0394c42c9ffffc6dd422e0a364685ade6021172888d
-size 271931456
+oid sha256:013f1d40b8981b5dd741c0ccc444ae6cf8485d7cd4333892bcb2c6e8c3047064
+size 776327440

model_index.json

@@ -1,10 +1,10 @@
 {
   "_class_name": "StableDiffusionCLAPPipeline",
   "_diffusers_version": "0.25.0.dev0",
-  "_name_or_path": "dhuck/stable-diffusion-clap",
+  "_name_or_path": "stabilityai/stable-diffusion-2-1",
   "audio_encoder": [
     "transformers",
-    "ClapAudioModel"
+    "ClapModel"
   ],
   "audio_processor": [
     "transformers",

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "dhuck/stable-diffusion-clap/text_encoder",
+  "_name_or_path": "/home/dhuck/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1/snapshots/5cae40e6a2745ae2b01ad92ae5043f95f23644d6/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],

tokenizer/special_tokens_map.json

@@ -13,13 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "!",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "!",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

unet/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.25.0.dev0",
-  "_name_or_path": "dhuck/stable-diffusion-clap/unet",
+  "_name_or_path": "stabilityai/stable-diffusion-2-1",
   "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90c904a46af0e172d59ee379709f77cf2e53012706c4935bd73e4593d672132e
+oid sha256:ddb59fe25f5428e6cf3a4d522a98ab977e72e85fca5863f04230c0bf6f288aef
 size 3509909336

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.25.0.dev0",
-  "_name_or_path": "dhuck/stable-diffusion-clap/vae",
+  "_name_or_path": "/home/dhuck/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1/snapshots/5cae40e6a2745ae2b01ad92ae5043f95f23644d6/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,