upload v5

model_index.json

@@ -1,6 +1,6 @@
 {
     "_class_name": "StableDiffusionPipeline",
-    "_diffusers_version": "0.14.0",
+    "_diffusers_version": "0.16.1",
     "feature_extractor": [
         null,
         null

scheduler/scheduler_config.json

@@ -1,11 +1,12 @@
 {
   "_class_name": "DEISMultistepScheduler",
-  "_diffusers_version": "0.14.0",
+  "_diffusers_version": "0.16.1",
   "algorithm_type": "deis",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
+  "clip_sample_range": 1.0,
   "dynamic_thresholding_ratio": 0.995,
   "lower_order_final": true,
   "num_train_timesteps": 1000,

text_encoder/config.json

@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
+  "transformers_version": "4.29.2",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6616a88b06f75b17494a785b77c64275f1273fb39adfe61a9634b3036e771f2
-size 492265874
+oid sha256:2ecd28cf71659828ac7605c2ef3a5b02f99d68d53c8e40a310571cfef875d84a
+size 492265880

tokenizer/tokenizer_config.json

@@ -8,6 +8,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
   "eos_token": {
     "__type": "AddedToken",
@@ -19,9 +20,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "openai/clip-vit-large-patch14",
   "pad_token": "<|endoftext|>",
-  "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",
   "unk_token": {
     "__type": "AddedToken",

unet/config.json

@@ -1,7 +1,9 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.14.0",
+  "_diffusers_version": "0.16.1",
   "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
   "attention_head_dim": 8,
   "block_out_channels": [
     320,
@@ -11,9 +13,11 @@
   ],
   "center_input_sample": false,
   "class_embed_type": null,
+  "class_embeddings_concat": false,
   "conv_in_kernel": 3,
   "conv_out_kernel": 3,
   "cross_attention_dim": 768,
+  "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
@@ -22,10 +26,12 @@
   ],
   "downsample_padding": 1,
   "dual_cross_attention": false,
+  "encoder_hid_dim": null,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 4,
   "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
   "mid_block_scale_factor": 1,
   "mid_block_type": "UNetMidBlock2DCrossAttn",
   "norm_eps": 1e-05,
@@ -34,9 +40,13 @@
   "only_cross_attention": false,
   "out_channels": 4,
   "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
   "sample_size": 64,
   "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
   "time_embedding_type": "positional",
   "timestep_post_act": null,
   "up_block_types": [

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:516efc6c08f766249ed04966625c547fcbcecb54ed2bd95cca454055f8d541e7
-size 3438167540
+oid sha256:e949a65f12ee40a9231df8aff55588b5631e4065c8e72b990f4025f886b19553
+size 3438167536

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.14.0",
+  "_diffusers_version": "0.16.1",
   "act_fn": "silu",
   "block_out_channels": [
     128,

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1d993488569e928462932c8c38a0760b874d166399b14414135bd9c42df5815
+oid sha256:55ad9628530430eed28c01dcf3c971a29ffe5d657856cb054728b6c956da3037
 size 334643276