Upload StableDiffusionXLInpaintPipeline

feature_extractor/preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPFeatureExtractor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

model_index.json

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

scheduler/scheduler_config.json

@@ -1,23 +1,23 @@
 {
-  "_class_name": "EulerDiscreteScheduler",
+  "_class_name": "DEISMultistepScheduler",
   "_diffusers_version": "0.30.3",
+  "algorithm_type": "deis",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
-  "final_sigmas_type": "zero",
-  "interpolation_type": "linear",
+  "dynamic_thresholding_ratio": 0.995,
+  "lower_order_final": true,
   "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/suraj_huggingface_co/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/bf714989e22c57ddc1c453bf74dab4521acb81d8/text_encoder",
+  "_name_or_path": "/home/patrick/.cache/huggingface/hub/models--lykon-models--dreamshaper-8-inpainting/snapshots/15dcb9dec91a39ee498e3917c9ef6174b103862d/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],

unet/config.json

@@ -1,7 +1,6 @@
 {
   "_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,
@@ -24,7 +23,6 @@
   "conv_out_kernel": 3,
   "cross_attention_dim": 2048,
   "cross_attention_norm": null,
-  "decay": 0.9999,
   "down_block_types": [
     "DownBlock2D",
     "CrossAttnDownBlock2D",
@@ -38,26 +36,22 @@
   "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": 128,
+  "sample_size": 64,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,
   "time_embedding_dim": null,
@@ -73,8 +67,6 @@
     "CrossAttnUpBlock2D",
     "UpBlock2D"
   ],
-  "upcast_attention": null,
-  "update_after_step": 0,
-  "use_ema_warmup": false,
+  "upcast_attention": false,
   "use_linear_projection": true
 }

vae/config.json

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