End of training

model_index.json

@@ -1,21 +1,13 @@
 {
-  "_class_name": "FlaxStableDiffusionPipeline",
+  "_class_name": "UTTIPipeline",
   "_diffusers_version": "0.22.0.dev0",
-  "feature_extractor": [
-    "transformers",
-    "CLIPImageProcessor"
-  ],
-  "safety_checker": [
-    "stable_diffusion",
-    "FlaxStableDiffusionSafetyChecker"
-  ],
   "scheduler": [
-    "diffusers",
-    "FlaxPNDMScheduler"
+    null,
+    null
   ],
   "text_encoder": [
     "transformers",
-    "FlaxCLIPTextModel"
+    "CLIPTextModel"
   ],
   "tokenizer": [
     "transformers",
@@ -23,10 +15,6 @@
   ],
   "unet": [
     "diffusers",
-    "FlaxUNet2DConditionModel"
-  ],
-  "vae": [
-    "diffusers",
-    "FlaxAutoencoderKL"
+    "UNet2DConditionModel"
   ]
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/clip-vit-large-patch14",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -19,7 +19,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "projection_dim": 512,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.33.1",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+size 246144152

unet/config.json

@@ -1,34 +1,60 @@
 {
-  "_class_name": "FlaxUNet2DConditionModel",
+  "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.22.0.dev0",
+  "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,
   "addition_time_embed_dim": null,
   "attention_head_dim": 8,
+  "attention_type": "default",
   "block_out_channels": [
     320,
     640,
     1280,
     1280
   ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
   "cross_attention_dim": 768,
+  "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
     "DownBlock2D"
   ],
+  "downsample_padding": 1,
   "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
-  "in_channels": 4,
+  "in_channels": 3,
   "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
   "num_attention_heads": null,
+  "num_class_embeds": null,
   "only_cross_attention": false,
-  "out_channels": 4,
+  "out_channels": 3,
   "projection_class_embeddings_input_dim": null,
-  "sample_size": 64,
-  "split_head_dim": false,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 32,
+  "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,
   "up_block_types": [
     "UpBlock2D",
@@ -36,6 +62,6 @@
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
-  "use_linear_projection": false,
-  "use_memory_efficient_attention": false
+  "upcast_attention": false,
+  "use_linear_projection": false
 }

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bbb9f6dce4605ddffcac9228979fc02d7fdcf8c8d8a40f594ecba1f6b8689b
+size 3438144492