epoch 5

model_index.json

@@ -1,21 +1,22 @@
 {
-  "_class_name": "FlaxStableDiffusionPipeline",
-  "_diffusers_version": "0.16.0.dev0",
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.16.1",
   "feature_extractor": [
     "transformers",
     "CLIPFeatureExtractor"
   ],
+  "requires_safety_checker": true,
   "safety_checker": [
     null,
     null
   ],
   "scheduler": [
     "diffusers",
-    "FlaxDDPMScheduler"
+    "DDPMScheduler"
   ],
   "text_encoder": [
     "transformers",
-    "FlaxT5EncoderModel"
+    "T5EncoderModel"
   ],
   "tokenizer": [
     "transformers",
@@ -23,10 +24,10 @@
   ],
   "unet": [
     "diffusers",
-    "FlaxUNet2DConditionModel"
+    "UNet2DConditionModel"
   ],
   "vae": [
     "diffusers",
-    "FlaxAutoencoderKL"
+    "AutoencoderKL"
   ]
 }

scheduler/scheduler_config.json

@@ -1,12 +1,16 @@
 {
-  "_class_name": "FlaxDDPMScheduler",
-  "_diffusers_version": "0.16.0.dev0",
+  "_class_name": "DDPMScheduler",
+  "_diffusers_version": "0.16.1",
   "beta_end": 0.012,
   "beta_schedule": "squaredcos_cap_v2",
   "beta_start": 0.00085,
-  "clip_sample": true,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
+  "thresholding": false,
   "trained_betas": null,
   "variance_type": "fixed_small"
 }

text_encoder/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "/content/sd1.5-t5-e5/text_encoder",
   "architectures": [
     "T5EncoderModel"
   ],
@@ -53,7 +54,8 @@
     }
   },
   "tie_word_embeddings": false,
-  "transformers_version": "4.26.1",
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
   "use_cache": true,
   "vocab_size": 32128
 }

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cefecc3f95ba94b85d01b1ea2e017c76918d66151cd11df2acb3e747935ad78
+size 438550729

tokenizer/tokenizer_config.json

@@ -101,13 +101,12 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
+  "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
   "model_max_length": 512,
-  "name_or_path": "/home/user/data_dump/sd1.5-t5-e4",
   "pad_token": "<pad>",
   "sp_model_kwargs": {},
-  "special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-base/snapshots/650d7745bf1e502d6949b22cc19155cd656d3d4e/special_tokens_map.json",
   "tokenizer_class": "T5Tokenizer",
   "unk_token": "<unk>"
 }

unet/config.json

@@ -1,7 +1,10 @@
 {
-  "_class_name": "FlaxUNet2DConditionModel",
-  "_diffusers_version": "0.16.0.dev0",
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.16.1",
+  "_name_or_path": "/content/sd1.5-t5-e5/unet",
   "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
   "attention_head_dim": 8,
   "block_out_channels": [
     320,
@@ -10,7 +13,12 @@
     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",
@@ -19,22 +27,37 @@
   ],
   "downsample_padding": 1,
   "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 4,
   "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_class_embeds": null,
   "only_cross_attention": false,
   "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
   "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,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
+  "upcast_attention": false,
   "use_linear_projection": false,
   "use_memory_efficient": false,
   "use_memory_efficient_attention": false

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b4068e2856c9f60553f23b7f007dc804fe24094679e15bbdaf4bf1c551c52c7
+size 3438366373

vae/config.json

@@ -1,6 +1,7 @@
 {
-  "_class_name": "FlaxAutoencoderKL",
-  "_diffusers_version": "0.16.0.dev0",
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.16.1",
+  "_name_or_path": "/content/sd1.5-t5-e5/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,

vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af27ea858349760ebe3311953e0bfe8d6fd257dc9537ae0b2b938c262132a2c6
+size 334711857