Upload folder using huggingface_hub

model_index.json

@@ -1,10 +1,10 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.40.0",
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "_diffusers_version": "0.37.1",
+  "_name_or_path": "stabilityai/sd-turbo",
   "feature_extractor": [
-    "transformers",
-    "CLIPImageProcessor"
+    null,
+    null
   ],
   "image_encoder": [
     null,
@@ -12,12 +12,12 @@
   ],
   "requires_safety_checker": true,
   "safety_checker": [
-    "stable_diffusion",
-    "StableDiffusionSafetyChecker"
+    null,
+    null
   ],
   "scheduler": [
     "diffusers",
-    "PNDMScheduler"
+    "EulerDiscreteScheduler"
   ],
   "text_encoder": [
     "transformers",

nova_gen_config.json

@@ -0,0 +1 @@
+{"base_model_id": "stabilityai/sd-turbo"}

scheduler/scheduler_config.json

@@ -1,15 +1,25 @@
 {
-  "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.40.0",
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.37.1",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
+  "final_sigmas_type": "zero",
+  "interpolation_type": "linear",
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
   "set_alpha_to_one": false,
+  "sigma_max": null,
+  "sigma_min": null,
   "skip_prk_steps": true,
   "steps_offset": 1,
-  "timestep_spacing": "leading",
-  "trained_betas": null
+  "timestep_spacing": "trailing",
+  "timestep_type": "discrete",
+  "trained_betas": null,
+  "use_beta_sigmas": false,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
 }

text_encoder/config.json

@@ -7,18 +7,18 @@
   "dropout": 0.0,
   "dtype": "float16",
   "eos_token_id": 2,
-  "hidden_act": "quick_gelu",
-  "hidden_size": 768,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
   "initializer_factor": 1.0,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 77,
   "model_type": "clip_text_model",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
   "pad_token_id": 1,
-  "projection_dim": 768,
-  "transformers_version": "5.16.1",
+  "projection_dim": 512,
+  "transformers_version": "5.0.0",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
-size 246144152
+oid sha256:bc1827c465450322616f06dea41596eac7d493f4e95904dcb51f0fc745c4e13f
+size 680820392

tokenizer/tokenizer.json

@@ -1,22 +1,24 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 77,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": {
-    "strategy": {
-      "Fixed": 77
-    },
+    "strategy": "BatchLongest",
     "direction": "Right",
     "pad_to_multiple_of": null,
-    "pad_id": 49407,
+    "pad_id": 0,
     "pad_type_id": 0,
-    "pad_token": "<|endoftext|>"
+    "pad_token": "!"
   },
   "added_tokens": [
+    {
+      "id": 0,
+      "content": "!",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
     {
       "id": 49406,
       "content": "<|startoftext|>",
@@ -32,7 +34,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     }
   ],

tokenizer/tokenizer_config.json

@@ -2,13 +2,13 @@
   "add_prefix_space": false,
   "backend": "tokenizers",
   "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "is_local": true,
-  "local_files_only": false,
   "model_max_length": 77,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "!",
   "tokenizer_class": "CLIPTokenizer",
   "unk_token": "<|endoftext|>"
 }

unet/config.json

@@ -1,12 +1,17 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.40.0",
-  "_name_or_path": "/root/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/451f4fe16113bff5a5d2269ed5ad43b0592e9a14/unet",
+  "_diffusers_version": "0.37.1",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--sd-turbo/snapshots/b261bac6fd2cf515557d5d0707481eafa0485ec2/unet",
   "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,
   "addition_time_embed_dim": null,
-  "attention_head_dim": 8,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
   "attention_type": "default",
   "block_out_channels": [
     320,
@@ -19,7 +24,7 @@
   "class_embeddings_concat": false,
   "conv_in_kernel": 3,
   "conv_out_kernel": 3,
-  "cross_attention_dim": 768,
+  "cross_attention_dim": 1024,
   "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
@@ -63,6 +68,6 @@
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
-  "upcast_attention": false,
-  "use_linear_projection": false
+  "upcast_attention": null,
+  "use_linear_projection": true
 }

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c83908253f9a64d08c25fc90874c9c8aef9a329ce1ca5fb909d73b0c83d1ea21
-size 1719125304
+oid sha256:40ec400881e27d1376c7c95c5bd495f407b33756e80eb6365e301c33a07af6e5
+size 1731904736

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.40.0",
-  "_name_or_path": "/root/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/451f4fe16113bff5a5d2269ed5ad43b0592e9a14/vae",
+  "_diffusers_version": "0.37.1",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--sd-turbo/snapshots/b261bac6fd2cf515557d5d0707481eafa0485ec2/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -24,7 +24,7 @@
   "mid_block_add_attention": true,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 512,
+  "sample_size": 768,
   "scaling_factor": 0.18215,
   "shift_factor": null,
   "up_block_types": [

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
+oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
 size 167335342