Upload folder using huggingface_hub

feature_extractor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

model_index.json

@@ -1,8 +1,16 @@
 {
-  "_class_name": "StableDiffusionXLPipeline",
+  "_class_name": "StableDiffusionPipeline",
   "_diffusers_version": "0.23.1",
-  "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
-  "force_zeros_for_empty_prompt": true,
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
   "scheduler": [
     "diffusers",
     "DDIMScheduler"
@@ -11,18 +19,10 @@
     "transformers",
     "CLIPTextModel"
   ],
-  "text_encoder_2": [
-    "transformers",
-    "CLIPTextModelWithProjection"
-  ],
   "tokenizer": [
     "transformers",
     "CLIPTokenizer"
   ],
-  "tokenizer_2": [
-    "transformers",
-    "CLIPTokenizer"
-  ],
   "unet": [
     "diffusers",
     "UNet2DConditionModel"

safety_checker/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/home/grads/azhang42/hf_cache/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/safety_checker",
+  "architectures": [
+    "StableDiffusionSafetyChecker"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "dropout": 0.0,
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 12
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0",
+  "vision_config": {
+    "dropout": 0.0,
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14
+  }
+}

safety_checker/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ecdfa243b170f9b4cb3eefaf0f64552ef78fc0bf0eb1c5b9675308447184f6
+size 608016280

scheduler/scheduler_config.json

@@ -7,7 +7,6 @@
   "clip_sample": false,
   "clip_sample_range": 1.0,
   "dynamic_thresholding_ratio": 0.995,
-  "interpolation_type": "linear",
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
   "rescale_betas_zero_snr": false,
@@ -17,6 +16,5 @@
   "steps_offset": 1,
   "thresholding": false,
   "timestep_spacing": "trailing",
-  "trained_betas": null,
-  "use_karras_sigmas": false
+  "trained_betas": null
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/grads/azhang42/hf_cache/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/text_encoder",
+  "_name_or_path": "/home/grads/azhang42/hf_cache/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],

unet/config.json

@@ -1,20 +1,17 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.23.1",
-  "_name_or_path": "/home/grads/azhang42/hf_cache/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/unet",
+  "_name_or_path": "/home/grads/azhang42/hf_cache/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/unet",
   "act_fn": "silu",
-  "addition_embed_type": "text_time",
+  "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": 256,
-  "attention_head_dim": [
-    5,
-    10,
-    20
-  ],
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
   "attention_type": "default",
   "block_out_channels": [
     320,
     640,
+    1280,
     1280
   ],
   "center_input_sample": false,
@@ -22,12 +19,13 @@
   "class_embeddings_concat": false,
   "conv_in_kernel": 3,
   "conv_out_kernel": 3,
-  "cross_attention_dim": 2048,
+  "cross_attention_dim": 768,
   "cross_attention_norm": null,
   "down_block_types": [
-    "DownBlock2D",
     "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D"
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
   ],
   "downsample_padding": 1,
   "dropout": 0.0,
@@ -47,27 +45,24 @@
   "num_class_embeds": null,
   "only_cross_attention": false,
   "out_channels": 4,
-  "projection_class_embeddings_input_dim": 2816,
+  "projection_class_embeddings_input_dim": null,
   "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,
   "time_embedding_type": "positional",
   "timestep_post_act": null,
-  "transformer_layers_per_block": [
-    1,
-    2,
-    10
-  ],
+  "transformer_layers_per_block": 1,
   "up_block_types": [
+    "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
-    "UpBlock2D"
+    "CrossAttnUpBlock2D"
   ],
-  "upcast_attention": null,
-  "use_linear_projection": true
+  "upcast_attention": false,
+  "use_linear_projection": false
 }

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26b5da455e0f7506464ef990d13bf28df9c0dec771c2625e07f338f7e6e6ecfa
-size 5922395792
+oid sha256:b074fc94f4047d5c24fc405c4593b0bfcb6b707c5177975158a7ee7a8e806f97
+size 1988214992

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.23.1",
-  "_name_or_path": "/home/grads/azhang42/hf_cache/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/vae",
+  "_name_or_path": "/home/grads/azhang42/hf_cache/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -21,8 +21,8 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 1024,
-  "scaling_factor": 0.13025,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcb60880a46b63dea58e9bc591abe15f8350bde47b405f9c38f4be70c6161e68
+oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
 size 167335342