Updated json files

model_index.json

@@ -1,10 +1,14 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.9.0.dev0",
+  "_diffusers_version": "0.11.0.dev0",
+  "feature_extractor": [
+    "transformers",
+    "CLIPFeatureExtractor"
+  ],
   "requires_safety_checker": false,
   "scheduler": [
     "diffusers",
-    "PNDMScheduler"
+    "DDIMScheduler"
   ],
   "text_encoder": [
     "transformers",

scheduler/scheduler_config.json

@@ -1,13 +1,13 @@
 {
-  "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.9.0.dev0",
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.11.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
   "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
   "set_alpha_to_one": false,
-  "skip_prk_steps": true,
   "steps_offset": 1,
   "trained_betas": null
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/content/models/VintageStyle",
+  "_name_or_path": "openai/clip-vit-large-patch14",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -19,7 +19,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "projection_dim": 768,
-  "torch_dtype": "float16",
-  "transformers_version": "4.24.0",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0.dev0",
   "vocab_size": 49408
 }

tokenizer/tokenizer_config.json

@@ -19,7 +19,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "/content/stable-diffusion-custom/tokenizer",
+  "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

@@ -1,7 +1,6 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.9.0.dev0",
-  "_name_or_path": "/content/stable-diffusion-custom",
+  "_diffusers_version": "0.11.0.dev0",
   "act_fn": "silu",
   "attention_head_dim": 8,
   "block_out_channels": [
@@ -30,12 +29,13 @@
   "num_class_embeds": null,
   "only_cross_attention": false,
   "out_channels": 4,
-  "sample_size": 32,
+  "sample_size": 64,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
+  "upcast_attention": false,
   "use_linear_projection": false
 }

vae/config.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.9.0.dev0",
-  "_name_or_path": "/content/stable-diffusion-custom/vae",
+  "_diffusers_version": "0.11.0.dev0",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -20,7 +19,7 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 256,
+  "sample_size": 512,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",