Upload StableDiffusionPipeline

model_index.json

@@ -32,6 +32,6 @@
   ],
   "vae": [
     "diffusers",
-    "AutoencoderTiny"
+    "AutoencoderKL"
   ]
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/clip-vit-base-patch32",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -8,17 +8,17 @@
   "dropout": 0.0,
   "eos_token_id": 2,
   "hidden_act": "quick_gelu",
-  "hidden_size": 512,
+  "hidden_size": 768,
   "initializer_factor": 1.0,
   "initializer_range": 0.02,
-  "intermediate_size": 2048,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 77,
   "model_type": "clip_text_model",
-  "num_attention_heads": 8,
+  "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 1,
-  "projection_dim": 512,
+  "projection_dim": 768,
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",
   "vocab_size": 49408

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c06e8e2f73be888f8026728b85703a2cbf6960a12ab47f4a9ba02fda4ae7674b
-size 252687056
+oid sha256:778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3
+size 492265168

tokenizer/special_tokens_map.json

@@ -9,21 +9,15 @@
   "eos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

tokenizer/tokenizer_config.json

@@ -12,7 +12,7 @@
     "49407": {
       "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:754373b0965197b80efabf313f5fc00f92a96ed552b1c08372c39d1d49d31de5
+oid sha256:5a8278e019b0d34c399e6d11ade61c7eb1bd83302b9b339ff5b8ea89259ecb14
 size 1344694984

vae/config.json

@@ -1,44 +1,34 @@
 {
-  "_class_name": "AutoencoderTiny",
+  "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.27.2",
-  "_name_or_path": "madebyollin/taesd",
-  "act_fn": "relu",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "act_fn": "silu",
   "block_out_channels": [
-    64,
-    64,
-    64,
-    64
+    128,
+    256,
+    512,
+    512
   ],
-  "decoder_block_out_channels": [
-    64,
-    64,
-    64,
-    64
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
   ],
-  "encoder_block_out_channels": [
-    64,
-    64,
-    64,
-    64
-  ],
-  "force_upcast": false,
+  "force_upcast": true,
   "in_channels": 3,
   "latent_channels": 4,
-  "latent_magnitude": 3,
-  "latent_shift": 0.5,
-  "num_decoder_blocks": [
-    3,
-    3,
-    3,
-    1
-  ],
-  "num_encoder_blocks": [
-    1,
-    3,
-    3,
-    3
-  ],
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
   "out_channels": 3,
-  "scaling_factor": 1.0,
-  "upsampling_scaling_factor": 2
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
 }

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:809df61d43507e70cdf6dfaa3bdea4d96fe2b1a5b212c9d9e2c6b3fa541aad71
-size 4903134
+oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
+size 167335342