Upload folder using huggingface_hub

model_index.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "StableDiffusionPipeline",
   "_diffusers_version": "0.35.0.dev0",
-  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "_name_or_path": "panopstor/EveryDream",
   "feature_extractor": [
     "transformers",
     "CLIPImageProcessor"
@@ -10,14 +10,14 @@
     null,
     null
   ],
-  "requires_safety_checker": false,
+  "requires_safety_checker": true,
   "safety_checker": [
-    null,
-    null
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
   ],
   "scheduler": [
     "diffusers",
-    "DDIMScheduler"
+    "PNDMScheduler"
   ],
   "text_encoder": [
     "transformers",

scheduler/scheduler_config.json

@@ -1,20 +1,15 @@
 {
-  "_class_name": "DDIMScheduler",
+  "_class_name": "PNDMScheduler",
   "_diffusers_version": "0.35.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
-  "clip_sample_range": 1.0,
-  "dynamic_thresholding_ratio": 0.995,
   "num_train_timesteps": 1000,
-  "prediction_type": "v_prediction",
-  "rescale_betas_zero_snr": false,
-  "sample_max_value": 1.0,
+  "prediction_type": "epsilon",
   "set_alpha_to_one": false,
   "skip_prk_steps": true,
   "steps_offset": 1,
-  "thresholding": false,
   "timestep_spacing": "leading",
   "trained_betas": null
 }

text_encoder/config.json

@@ -6,18 +6,18 @@
   "bos_token_id": 0,
   "dropout": 0.0,
   "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_size": 1024,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
   "initializer_factor": 1.0,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 77,
   "model_type": "clip_text_model",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 23,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
-  "projection_dim": 512,
+  "projection_dim": 768,
   "torch_dtype": "float16",
   "transformers_version": "4.54.1",
   "vocab_size": 49408

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc1827c465450322616f06dea41596eac7d493f4e95904dcb51f0fc745c4e13f
-size 680820392
+oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+size 246144152

tokenizer/special_tokens_map.json

@@ -13,7 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "!",
+  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer/tokenizer_config.json

@@ -1,14 +1,6 @@
 {
   "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,
@@ -33,7 +25,7 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 77,
-  "pad_token": "!",
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "CLIPTokenizer",
   "unk_token": "<|endoftext|>"
 }

unet/config.json

@@ -1,17 +1,12 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.35.0.dev0",
-  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "_name_or_path": "panopstor/EveryDream",
   "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,
   "addition_time_embed_dim": null,
-  "attention_head_dim": [
-    5,
-    10,
-    20,
-    20
-  ],
+  "attention_head_dim": 8,
   "attention_type": "default",
   "block_out_channels": [
     320,
@@ -24,7 +19,7 @@
   "class_embeddings_concat": false,
   "conv_in_kernel": 3,
   "conv_out_kernel": 3,
-  "cross_attention_dim": 1024,
+  "cross_attention_dim": 768,
   "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
@@ -55,7 +50,7 @@
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
   "reverse_transformer_layers_per_block": null,
-  "sample_size": 96,
+  "sample_size": 64,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,
   "time_embedding_dim": null,
@@ -69,5 +64,5 @@
     "CrossAttnUpBlock2D"
   ],
   "upcast_attention": false,
-  "use_linear_projection": true
+  "use_linear_projection": false
 }

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a88e02b1b52e2bdcbb163fde457268f1007777c673ec1f3b730a74514812476
-size 3463726504
+oid sha256:f63e255fe984cc21991673e698133a97352d6c2bc78c5bd6fd24839e05486f66
+size 3438167536

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.35.0.dev0",
-  "_name_or_path": "/home/user/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2/snapshots/1e128c8891e52218b74cde8f26dbfc701cb99d79/vae",
+  "_name_or_path": "/home/user/.cache/huggingface/hub/models--panopstor--EveryDream/snapshots/7db5503224558411b84f2099e1342c360f0b8987/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -24,7 +24,7 @@
   "mid_block_add_attention": true,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 768,
+  "sample_size": 512,
   "scaling_factor": 0.18215,
   "shift_factor": null,
   "up_block_types": [