End of training

checkpoint-1000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2837b44ae569e1ec810f422b6f007ae6e9eff8b7b067c1c68026a91b9f5718a2
+size 20541266058

checkpoint-1000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:970f6a0ac0186a1b1670a17014c8a04aa2b49f7e483c7039d281803985cf0540
+size 14408

checkpoint-1000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cce50ed778d5738b3afa3503cdb404ebe08bd37f51cf090b758c61cf8e876d8
+size 1000

checkpoint-1000/unet/config.json

@@ -0,0 +1,73 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "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": 8,
+  "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": 2816,
+  "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,
+  "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
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

checkpoint-1000/unet/diffusion_pytorch_model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:551cc57557101aa2fa272d1e7ccf769df8ef32381e24f279e111f74f94ca2aae
+size 9988185240

checkpoint-1000/unet/diffusion_pytorch_model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bbfe671d5bc7b9d9307757545a059d66171d3354a4ec981e44264bd3f5bae8d
+size 281938304

logs/instruct-pix2pix-xl/1736095241.9403296/events.out.tfevents.1736095241.DESKTOP-FG95EGE.19476.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17e96c7a5e11ebe09b658389af8cd6bde3b3725b1f4c5a23ccc3dc2d35e2264a
+size 2552

logs/instruct-pix2pix-xl/1736095241.9448347/hparams.yml

@@ -0,0 +1,55 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 1000
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.05
+crops_coords_top_left_h: 0
+crops_coords_top_left_w: 0
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: dataset/metadata.csv
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 5.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 1000
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 53
+num_validation_images: 4
+original_image_column: input_image
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
+pretrained_vae_model_name_or_path: null
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 256
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+vae_precision: fp32
+val_image_url_or_path: null
+validation_prompt: null
+validation_steps: 100
+variant: null

logs/instruct-pix2pix-xl/events.out.tfevents.1736095241.DESKTOP-FG95EGE.19476.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ca0b6000528e701cc0a3de3a8b1a0d2bdf0fbdee7ac94619dc42edbf242109b
+size 48961

model_index.json

@@ -1,32 +1,28 @@
 {
-  "_class_name": "StableDiffusionInstructPix2PixPipeline",
+  "_class_name": "StableDiffusionXLInstructPix2PixPipeline",
   "_diffusers_version": "0.33.0.dev0",
-  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
-  "feature_extractor": [
-    "transformers",
-    "CLIPImageProcessor"
-  ],
-  "image_encoder": [
-    null,
-    null
-  ],
-  "requires_safety_checker": true,
-  "safety_checker": [
-    "stable_diffusion",
-    "StableDiffusionSafetyChecker"
-  ],
+  "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
+  "force_zeros_for_empty_prompt": true,
   "scheduler": [
     "diffusers",
-    "PNDMScheduler"
+    "EulerDiscreteScheduler"
   ],
   "text_encoder": [
     "transformers",
     "CLIPTextModel"
   ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
   "tokenizer": [
     "transformers",
     "CLIPTokenizer"
   ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
   "unet": [
     "diffusers",
     "UNet2DConditionModel"

scheduler/scheduler_config.json

@@ -1,15 +1,25 @@
 {
-  "_class_name": "PNDMScheduler",
+  "_class_name": "EulerDiscreteScheduler",
   "_diffusers_version": "0.33.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
+  "final_sigmas_type": "zero",
+  "interpolation_type": "linear",
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
   "set_alpha_to_one": false,
+  "sigma_max": null,
+  "sigma_min": null,
   "skip_prk_steps": true,
   "steps_offset": 1,
   "timestep_spacing": "leading",
-  "trained_betas": null
+  "timestep_type": "discrete",
+  "trained_betas": null,
+  "use_beta_sigmas": false,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
+  "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -19,7 +19,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "projection_dim": 768,
-  "torch_dtype": "float16",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.46.3",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
-size 246144152
+oid sha256:03532a1b8bb2f02b16b9b290273caf9c8793a0a268517c104eee30f7d1829120
+size 246144352

text_encoder_2/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "vocab_size": 49408
+}

text_encoder_2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4ba596d8c78b5509aafd523f619e13aa129ae1a886a1e92766d7cddd9706f3c
+size 1389382688

tokenizer/tokenizer_config.json

@@ -19,7 +19,7 @@
     }
   },
   "bos_token": "<|startoftext|>",
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
   "eos_token": "<|endoftext|>",
   "errors": "replace",

tokenizer_2/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_2/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "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,
+      "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": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

unet/config.json

@@ -1,17 +1,20 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.33.0.dev0",
-  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
+  "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
   "act_fn": "silu",
-  "addition_embed_type": null,
+  "addition_embed_type": "text_time",
   "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": null,
-  "attention_head_dim": 8,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
   "attention_type": "default",
   "block_out_channels": [
     320,
     640,
-    1280,
     1280
   ],
   "center_input_sample": false,
@@ -19,13 +22,12 @@
   "class_embeddings_concat": false,
   "conv_in_kernel": 3,
   "conv_out_kernel": 3,
-  "cross_attention_dim": 768,
+  "cross_attention_dim": 2048,
   "cross_attention_norm": null,
   "down_block_types": [
+    "DownBlock2D",
     "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "DownBlock2D"
+    "CrossAttnDownBlock2D"
   ],
   "downsample_padding": 1,
   "dropout": 0.0,
@@ -45,24 +47,27 @@
   "num_class_embeds": null,
   "only_cross_attention": false,
   "out_channels": 4,
-  "projection_class_embeddings_input_dim": null,
+  "projection_class_embeddings_input_dim": 2816,
   "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,
+  "sample_size": 128,
   "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,
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
   "up_block_types": [
-    "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D"
+    "UpBlock2D"
   ],
-  "upcast_attention": false,
-  "use_linear_projection": false
+  "upcast_attention": null,
+  "use_linear_projection": true
 }

unet/diffusion_pytorch_model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:551cc57557101aa2fa272d1e7ccf769df8ef32381e24f279e111f74f94ca2aae
+size 9988185240

unet/diffusion_pytorch_model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bbfe671d5bc7b9d9307757545a059d66171d3354a4ec981e44264bd3f5bae8d
+size 281938304

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.33.0.dev0",
-  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
+  "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -24,8 +24,8 @@
   "mid_block_add_attention": true,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 512,
-  "scaling_factor": 0.18215,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
   "shift_factor": null,
   "up_block_types": [
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
-size 167335342
+oid sha256:1598f3d24932bcfe6634e8b618ea1e30ab1d57f5aad13a6d2de446d2199f2341
+size 334643268