End of training

checkpoint-8000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3023889b16f442027e00b953815bb310d2bd985ec7f3c98aad988e22e849f2
+size 2422804150

checkpoint-8000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d2ddcb38420f097322cd1e6a824ae66146edd733f7947abd7beb64b6b1e399
+size 14408

checkpoint-8000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:277aa13cb2ec6fbc8e4950a74aadb07696752963130be9aa03b65700e040b1b0
+size 988

checkpoint-8000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efff19450f55a9358b76f3e5170171942761d1c5b9128683028d0c09b8a24573
+size 1000

checkpoint-8000/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/ricardo/Documents/PhD/fixed/diffusion-models_master/results/fusion_2-1-base/checkpoint-4000",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0",
+  "vocab_size": 49408
+}

checkpoint-8000/text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f11af7ac76b00694e46def1aa36c6533900fdf64035820d21eed35bac86f833c
+size 1361596304

checkpoint-8000/unet/config.json

@@ -0,0 +1,73 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.29.0",
+  "_name_or_path": "/home/ricardo/Documents/PhD/fixed/diffusion-models_master/results/fusion_2-1-base/checkpoint-4000",
+  "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_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": 1024,
+  "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,
+  "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,
+  "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": 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,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": true
+}

checkpoint-8000/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9410122175de91cb1954a4d42716da1f2c394877a6ed19792b04a9897c3c693
+size 3463726504

model_index.json

@@ -1,11 +1,15 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.21.4",
+  "_diffusers_version": "0.29.0",
   "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
   "feature_extractor": [
     null,
     null
   ],
+  "image_encoder": [
+    null,
+    null
+  ],
   "requires_safety_checker": false,
   "safety_checker": [
     null,

scheduler/scheduler_config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.21.4",
+  "_diffusers_version": "0.29.0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
+  "_name_or_path": "/home/ricardo/Documents/PhD/fixed/diffusion-models_master/results/fusion_2-1-base/checkpoint-4000",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 512,
   "torch_dtype": "float32",
-  "transformers_version": "4.27.1",
+  "transformers_version": "4.41.0",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8af30f6daf070d44aa08db0cc597a492bafb4cfe3ebee6e5110521be164a799b
-size 1361597016
+oid sha256:e6daf04536e685a10d3f185e0415a416d3d7bfe17e29ddcb9e35c0838e082824
+size 1361596304

tokenizer/tokenizer_config.json

@@ -1,33 +1,38 @@
 {
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|startoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "<|endoftext|>",
   "errors": "replace",
   "model_max_length": 77,
-  "pad_token": "<|endoftext|>",
-  "special_tokens_map_file": "./special_tokens_map.json",
+  "pad_token": "!",
   "tokenizer_class": "CLIPTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }

unet/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.21.4",
-  "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
+  "_diffusers_version": "0.29.0",
+  "_name_or_path": "/home/ricardo/Documents/PhD/fixed/diffusion-models_master/results/fusion_2-1-base/checkpoint-4000",
   "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,
@@ -54,6 +54,7 @@
   "resnet_out_scale_factor": 1.0,
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
   "sample_size": 64,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9d8f7e91adad21cfe56a2ec95818664ca48766df7153c2a169423d19559e6f7
+oid sha256:7e7d077089f61607e1b0533aa6cd353a5cd3fa02c180f442877bdc68e1623250
 size 3463726504

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.21.4",
+  "_diffusers_version": "0.29.0",
   "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
   "act_fn": "silu",
   "block_out_channels": [
@@ -18,15 +18,20 @@
   "force_upcast": true,
   "in_channels": 3,
   "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
   "sample_size": 768,
   "scaling_factor": 0.18215,
+  "shift_factor": null,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",
     "UpDecoderBlock2D"
-  ]
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
 }