Adding `diffusers` weights of this model (#1)

- Adding `diffusers` weights of this model (16ad0e9ad62848dd8c941c044134fada050c3945)

model_index.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "StableDiffusionXLPipeline",
-  "_diffusers_version": "0.19.0",
+  "_diffusers_version": "0.28.0.dev0",
   "feature_extractor": [
     null,
     null
@@ -12,7 +12,7 @@
   ],
   "scheduler": [
     "diffusers",
-    "EulerAncestralDiscreteScheduler"
+    "EDMDPMSolverMultistepScheduler"
   ],
   "text_encoder": [
     "transformers",

scheduler/scheduler_config.json

@@ -1,17 +1,31 @@
 {
-  "_class_name": "EulerAncestralDiscreteScheduler",
-  "_diffusers_version": "0.19.0",
+  "_class_name": "EDMDPMSolverMultistepScheduler",
+  "_diffusers_version": "0.28.0.dev0",
+  "algorithm_type": "dpmsolver++",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
+  "dynamic_thresholding_ratio": 0.995,
+  "euler_at_final": false,
+  "final_sigmas_type": "zero",
   "interpolation_type": "linear",
+  "lower_order_final": true,
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
+  "rho": 7.0,
   "sample_max_value": 1.0,
   "set_alpha_to_one": false,
+  "sigma_data": 0.5,
+  "sigma_max": 80.0,
+  "sigma_min": 0.002,
+  "sigma_schedule": "karras",
   "skip_prk_steps": true,
+  "solver_order": 2,
+  "solver_type": "midpoint",
   "steps_offset": 1,
+  "thresholding": false,
   "timestep_spacing": "leading",
-  "trained_betas": null
+  "trained_betas": null,
+  "use_karras_sigmas": false
 }

text_encoder/config.json

@@ -19,6 +19,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float16",
-  "transformers_version": "4.33.3",
+  "transformers_version": "4.41.1",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92ee41d9f833c7b6bb75512bc79c25e400a9f17152b53292afda8d3389f40d3
+size 246144152

text_encoder_2/config.json

@@ -19,6 +19,6 @@
   "pad_token_id": 1,
   "projection_dim": 1280,
   "torch_dtype": "float16",
-  "transformers_version": "4.33.3",
+  "transformers_version": "4.41.1",
   "vocab_size": 49408
 }

text_encoder_2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1b38d284ed24dd170563bbf610642074d2ecc51010660a7c2ccb3f83164759a
+size 1389382176

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 +1,6 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.19.0",
+  "_diffusers_version": "0.28.0.dev0",
   "act_fn": "silu",
   "addition_embed_type": "text_time",
   "addition_embed_type_num_heads": 64,
@@ -10,6 +10,7 @@
     10,
     20
   ],
+  "attention_type": "default",
   "block_out_channels": [
     320,
     640,
@@ -28,6 +29,7 @@
     "CrossAttnDownBlock2D"
   ],
   "downsample_padding": 1,
+  "dropout": 0.0,
   "dual_cross_attention": false,
   "encoder_hid_dim": null,
   "encoder_hid_dim_type": null,
@@ -48,6 +50,7 @@
   "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,

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a76cae4945eec355b90d3bfca73a458a2629f8c56c9ee94a90b3e5e1d38148a
+size 5135149760

vae/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.19.0",
+  "_diffusers_version": "0.28.0.dev0",
+  "_name_or_path": "../sdxl-vae/",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -17,6 +18,8 @@
   "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,

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcb60880a46b63dea58e9bc591abe15f8350bde47b405f9c38f4be70c6161e68
+size 167335342