Upload with huggingface_hub

feature_extractor/preprocessor_config.json

@@ -1,28 +1,28 @@
 {
-    "crop_size": {
-      "height": 224,
-      "width": 224
-    },
-    "do_center_crop": true,
-    "do_convert_rgb": true,
-    "do_normalize": true,
-    "do_rescale": true,
-    "do_resize": true,
-    "feature_extractor_type": "CLIPFeatureExtractor",
-    "image_mean": [
-      0.48145466,
-      0.4578275,
-      0.40821073
-    ],
-    "image_processor_type": "CLIPImageProcessor",
-    "image_std": [
-      0.26862954,
-      0.26130258,
-      0.27577711
-    ],
-    "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "size": {
-      "shortest_edge": 224
-    }
-  }
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

model_index.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.10.2",
+  "_diffusers_version": "0.11.1",
   "feature_extractor": [
     null,
     null
@@ -12,7 +12,7 @@
   ],
   "scheduler": [
     "diffusers",
-    "DDIMScheduler"
+    "PNDMScheduler"
   ],
   "text_encoder": [
     "transformers",
@@ -30,4 +30,4 @@
     "diffusers",
     "AutoencoderKL"
   ]
-}
+}

scheduler/scheduler_config.json

@@ -1,6 +1,6 @@
 {
-  "_class_name": "DDIMScheduler",
-  "_diffusers_version": "0.10.2",
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.11.1",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
@@ -11,4 +11,4 @@
   "skip_prk_steps": true,
   "steps_offset": 1,
   "trained_betas": null
-}
+}

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a0e89c58d325d78fa948f70e2f162941223786783d6e1994d86b6f2b635ef44
-size 492307041
+oid sha256:a24f52aaf1c79a0b1264eaf0d21f016ea6f7cbe7ff6927436696e01ddca38f56
+size 492305335

tokenizer/tokenizer_config.json

@@ -19,7 +19,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "dreamlike-art/dreamlike-diffusion-1.0",
+  "name_or_path": "openai/clip-vit-large-patch14",
   "pad_token": "<|endoftext|>",
   "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",

unet/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.10.2",
+  "_diffusers_version": "0.11.1",
   "act_fn": "silu",
   "attention_head_dim": 8,
   "block_out_channels": [
@@ -10,6 +10,7 @@
     1280
   ],
   "center_input_sample": false,
+  "class_embed_type": null,
   "cross_attention_dim": 768,
   "down_block_types": [
     "CrossAttnDownBlock2D",
@@ -24,12 +25,14 @@
   "in_channels": 4,
   "layers_per_block": 2,
   "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
   "norm_eps": 1e-05,
   "norm_num_groups": 32,
   "num_class_embeds": null,
   "only_cross_attention": false,
   "out_channels": 4,
-  "sample_size": 80,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 64,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
@@ -38,4 +41,4 @@
   ],
   "upcast_attention": false,
   "use_linear_projection": false
-}
+}

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bf4e2d66f92e62071443dfe0d258b3d52c9e58bb40a8e730daea97e8fe58f28
-size 3438375973
+oid sha256:ddb35e6290df5168888b2e6bddd2d5979141ab551fcb1dd9247bd9fe291c69d1
+size 3438354725

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.10.2",
+  "_diffusers_version": "0.11.1",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -19,11 +19,11 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 256,
+  "sample_size": 512,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",
     "UpDecoderBlock2D"
   ]
-}
+}

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6e817ec7c5c6641c0000a1a7fc7893f6625251131f33f7bb034c55e5d949455
-size 167404145
+oid sha256:b8cf5b49d164db18a485d392b2d9a9b4e3636d70613cb756d2e1bc460dd13161
+size 334707217