Upload folder using huggingface_hub

model_index.json

@@ -1,7 +1,16 @@
 {
   "_class_name": "StableDiffusionXLPipeline",
-  "_diffusers_version": "0.21.2",
+  "_diffusers_version": "0.29.0",
+  "_name_or_path": "model",
+  "feature_extractor": [
+    null,
+    null
+  ],
   "force_zeros_for_empty_prompt": true,
+  "image_encoder": [
+    null,
+    null
+  ],
   "scheduler": [
     "diffusers",
     "EulerDiscreteScheduler"

scheduler/scheduler_config.json

@@ -1,18 +1,23 @@
 {
   "_class_name": "EulerDiscreteScheduler",
-  "_diffusers_version": "0.21.2",
+  "_diffusers_version": "0.29.0",
   "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",
+  "timestep_type": "discrete",
   "trained_betas": null,
   "use_karras_sigmas": false
 }

text_encoder/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "model/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -19,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float16",
-  "transformers_version": "4.33.1",
+  "transformers_version": "4.41.2",
   "vocab_size": 49408
 }

text_encoder_2/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "model/text_encoder_2",
   "architectures": [
     "CLIPTextModelWithProjection"
   ],
@@ -19,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 1280,
   "torch_dtype": "float16",
-  "transformers_version": "4.33.1",
+  "transformers_version": "4.41.2",
   "vocab_size": 49408
 }

tokenizer/tokenizer_config.json

@@ -1,33 +1,30 @@
 {
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|startoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "<|startoftext|>",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "<|endoftext|>",
   "errors": "replace",
   "model_max_length": 77,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "CLIPTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }

tokenizer_2/tokenizer_config.json

@@ -1,33 +1,38 @@
 {
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|startoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "<|startoftext|>",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "<|endoftext|>",
   "errors": "replace",
   "model_max_length": 77,
   "pad_token": "!",
   "tokenizer_class": "CLIPTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }

unet/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.21.2",
+  "_diffusers_version": "0.29.0",
+  "_name_or_path": "model/unet",
   "act_fn": "silu",
   "addition_embed_type": "text_time",
   "addition_embed_type_num_heads": 64,
@@ -50,6 +51,7 @@
   "resnet_out_scale_factor": 1.0,
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
   "sample_size": 128,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,

vae/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.21.2",
+  "_diffusers_version": "0.29.0",
+  "_name_or_path": "model/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -17,15 +18,20 @@
   "force_upcast": true,
   "in_channels": 3,
   "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
   "sample_size": 1024,
   "scaling_factor": 0.13025,
+  "shift_factor": null,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",
     "UpDecoderBlock2D"
-  ]
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
 }