Upload StableDiffusionXLInpaintPipeline

model_index.json

@@ -2,8 +2,8 @@
   "_class_name": "StableDiffusionXLInpaintPipeline",
   "_diffusers_version": "0.30.3",
   "feature_extractor": [
-    "transformers",
-    "CLIPFeatureExtractor"
+    null,
+    null
   ],
   "force_zeros_for_empty_prompt": true,
   "image_encoder": [
@@ -13,23 +13,23 @@
   "requires_aesthetics_score": false,
   "scheduler": [
     "diffusers",
-    "DEISMultistepScheduler"
+    "EulerDiscreteScheduler"
   ],
   "text_encoder": [
     "transformers",
     "CLIPTextModel"
   ],
   "text_encoder_2": [
-    null,
-    null
+    "transformers",
+    "CLIPTextModelWithProjection"
   ],
   "tokenizer": [
     "transformers",
     "CLIPTokenizer"
   ],
   "tokenizer_2": [
-    null,
-    null
+    "transformers",
+    "CLIPTokenizer"
   ],
   "unet": [
     "diffusers",

scheduler/scheduler_config.json

@@ -1,23 +1,23 @@
 {
-  "_class_name": "DEISMultistepScheduler",
+  "_class_name": "EulerDiscreteScheduler",
   "_diffusers_version": "0.30.3",
-  "algorithm_type": "deis",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
-  "dynamic_thresholding_ratio": 0.995,
-  "lower_order_final": true,
+  "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,
-  "solver_order": 2,
-  "solver_type": "logrho",
   "steps_offset": 1,
-  "thresholding": false,
   "timestep_spacing": "leading",
+  "timestep_type": "discrete",
   "trained_betas": null,
   "use_karras_sigmas": false
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/patrick/.cache/huggingface/hub/models--lykon-models--dreamshaper-8-inpainting/snapshots/15dcb9dec91a39ee498e3917c9ef6174b103862d/text_encoder",
+  "_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/bf714989e22c57ddc1c453bf74dab4521acb81d8/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],

text_encoder_2/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/bf714989e22c57ddc1c453bf74dab4521acb81d8/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": "4.44.2",
+  "vocab_size": 49408
+}

text_encoder_2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f92221e08b6de7337c9ce2098716ecbbc02bac9feb5922ec0b5f6263888268a5
+size 1389382176

tokenizer_2/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "!",
+  "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

@@ -1,6 +1,7 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.30.3",
+  "_name_or_path": "valhalla/sdxl-inpaint-ema",
   "act_fn": "silu",
   "addition_embed_type": "text_time",
   "addition_embed_type_num_heads": 64,
@@ -23,6 +24,7 @@
   "conv_out_kernel": 3,
   "cross_attention_dim": 2048,
   "cross_attention_norm": null,
+  "decay": 0.9999,
   "down_block_types": [
     "DownBlock2D",
     "CrossAttnDownBlock2D",
@@ -36,22 +38,26 @@
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 9,
+  "inv_gamma": 1.0,
   "layers_per_block": 2,
   "mid_block_only_cross_attention": null,
   "mid_block_scale_factor": 1,
   "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "min_decay": 0.0,
   "norm_eps": 1e-05,
   "norm_num_groups": 32,
   "num_attention_heads": null,
   "num_class_embeds": null,
   "only_cross_attention": false,
+  "optimization_step": 37000,
   "out_channels": 4,
+  "power": 0.6666666666666666,
   "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,
@@ -67,6 +73,8 @@
     "CrossAttnUpBlock2D",
     "UpBlock2D"
   ],
-  "upcast_attention": false,
+  "upcast_attention": null,
+  "update_after_step": 0,
+  "use_ema_warmup": false,
   "use_linear_projection": true
 }

vae/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.30.3",
+  "_name_or_path": "madebyollin/sdxl-vae-fp16-fix",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -14,7 +15,7 @@
     "DownEncoderBlock2D",
     "DownEncoderBlock2D"
   ],
-  "force_upcast": true,
+  "force_upcast": false,
   "in_channels": 3,
   "latent_channels": 4,
   "latents_mean": null,