Upload StableDiffusionXLPipeline

README.md

@@ -1,11 +1,12 @@
 ---
 license: creativeml-openrail-m
 tags:
-  - modelslab.com
-  - stable-diffusion-api
-  - text-to-image
-  - ultra-realistic
+- modelslab.com
+- stable-diffusion-api
+- text-to-image
+- ultra-realistic
 pinned: true
+library_name: diffusers
 ---
 
 # None API Inference

model_index.json

@@ -1,32 +1,36 @@
 {
-  "_class_name": "StableDiffusionPipeline",
+  "_class_name": "StableDiffusionXLPipeline",
   "_diffusers_version": "0.32.2",
-  "_name_or_path": "stablediffusionapi/duchaiten_anyunreal",
+  "_name_or_path": "stablediffusionapi/duchaiten-real3d-nsfw-xl",
   "feature_extractor": [
-    "transformers",
-    "CLIPFeatureExtractor"
-  ],
-  "image_encoder": [
     null,
     null
   ],
-  "requires_safety_checker": true,
-  "safety_checker": [
+  "force_zeros_for_empty_prompt": true,
+  "image_encoder": [
     null,
     null
   ],
   "scheduler": [
     "diffusers",
-    "PNDMScheduler"
+    "EulerDiscreteScheduler"
   ],
   "text_encoder": [
     "transformers",
     "CLIPTextModel"
   ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
   "tokenizer": [
     "transformers",
     "CLIPTokenizer"
   ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
   "unet": [
     "diffusers",
     "UNet2DConditionModel"

scheduler/scheduler_config.json

@@ -1,15 +1,25 @@
 {
-  "_class_name": "PNDMScheduler",
+  "_class_name": "EulerDiscreteScheduler",
   "_diffusers_version": "0.32.2",
   "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_type": "discrete",
+  "trained_betas": null,
+  "use_beta_sigmas": false,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/my_workspace/models_cache/hub/models--stablediffusionapi--duchaiten_anyunreal/snapshots/f663e1a7925f550e57a56b912d9c0c4069620629/text_encoder",
+  "_name_or_path": "/my_workspace/models_cache/hub/models--stablediffusionapi--duchaiten-real3d-nsfw-xl/snapshots/c6718f20b4455f646a06774ceacc72823a02c72b/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],

text_encoder/model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1aab7852ac2761d4fda7446158260e2c3d918ea15c40595fd4f49edbe6d0bfd
+oid sha256:32eba9a8104e585afb0421fb9f08870f725a62ba7b298abf83d646164acf08c6
 size 246144152

text_encoder_2/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/my_workspace/models_cache/hub/models--stablediffusionapi--duchaiten-real3d-nsfw-xl/snapshots/c6718f20b4455f646a06774ceacc72823a02c72b/text_encoder_2",
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "float16",
+  "transformers_version": "4.43.1",
+  "vocab_size": 49408
+}

text_encoder_2/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad5ce539c7271403f08cb716fcd55efa3602e06a41496a598063723a3d410f94
+size 1389382176

tokenizer_2/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "!",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_2/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_prefix_space": 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": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

unet/config.json

@@ -1,17 +1,20 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.32.2",
-  "_name_or_path": "/my_workspace/models_cache/hub/models--stablediffusionapi--duchaiten_anyunreal/snapshots/f663e1a7925f550e57a56b912d9c0c4069620629/unet",
+  "_name_or_path": "/my_workspace/models_cache/hub/models--stablediffusionapi--duchaiten-real3d-nsfw-xl/snapshots/c6718f20b4455f646a06774ceacc72823a02c72b/unet",
   "act_fn": "silu",
-  "addition_embed_type": null,
+  "addition_embed_type": "text_time",
   "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": null,
-  "attention_head_dim": 8,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
   "attention_type": "default",
   "block_out_channels": [
     320,
     640,
-    1280,
     1280
   ],
   "center_input_sample": false,
@@ -19,13 +22,12 @@
   "class_embeddings_concat": false,
   "conv_in_kernel": 3,
   "conv_out_kernel": 3,
-  "cross_attention_dim": 768,
+  "cross_attention_dim": 2048,
   "cross_attention_norm": null,
   "down_block_types": [
+    "DownBlock2D",
     "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "DownBlock2D"
+    "CrossAttnDownBlock2D"
   ],
   "downsample_padding": 1,
   "dropout": 0.0,
@@ -45,24 +47,27 @@
   "num_class_embeds": null,
   "only_cross_attention": false,
   "out_channels": 4,
-  "projection_class_embeddings_input_dim": null,
+  "projection_class_embeddings_input_dim": 2816,
   "resnet_out_scale_factor": 1.0,
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
   "reverse_transformer_layers_per_block": null,
-  "sample_size": 64,
+  "sample_size": 128,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,
   "time_embedding_dim": null,
   "time_embedding_type": "positional",
   "timestep_post_act": null,
-  "transformer_layers_per_block": 1,
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
   "up_block_types": [
-    "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D"
+    "UpBlock2D"
   ],
   "upcast_attention": false,
-  "use_linear_projection": false
+  "use_linear_projection": true
 }

unet/diffusion_pytorch_model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38552da53443b8f684af4184fa6dbae2e2df50a2a571ca36b3f479530b051045
-size 1719125304
+oid sha256:769c7acc3a2bc38592f5c362acab83e2bb3406d41b3c09cf039e2c89c3b5f429
+size 5135149760

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.32.2",
-  "_name_or_path": "/my_workspace/models_cache/hub/models--stablediffusionapi--duchaiten_anyunreal/snapshots/f663e1a7925f550e57a56b912d9c0c4069620629/vae",
+  "_name_or_path": "/my_workspace/models_cache/hub/models--stablediffusionapi--duchaiten-real3d-nsfw-xl/snapshots/c6718f20b4455f646a06774ceacc72823a02c72b/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -24,8 +24,8 @@
   "mid_block_add_attention": true,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 512,
-  "scaling_factor": 0.18215,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
   "shift_factor": null,
   "up_block_types": [
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:832e013753c33d89d1e4c7eb601d801f1626ed7f3107b2a5e8542308c7bfd143
+oid sha256:5ebe0b826867138fc37d4474983ef0b487cef39d8f3cd84228f3b5c5aba241d4
 size 167335342