End of training

.gitattributes

@@ -33,3 +33,83 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+validation_images/step_100_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_100_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_100_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_100_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_10_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_10_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_10_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_10_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_110_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_110_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_110_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_110_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_120_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_120_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_120_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_120_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_130_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_130_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_130_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_130_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_140_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_140_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_140_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_140_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_150_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_150_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_150_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_150_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_160_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_160_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_160_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_160_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_170_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_170_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_170_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_170_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_180_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_180_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_180_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_180_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_190_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_190_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_190_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_190_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_200_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_200_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_200_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_200_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_20_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_20_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_20_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_20_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_30_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_30_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_30_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_30_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_40_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_40_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_40_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_40_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_50_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_50_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_50_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_50_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_60_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_60_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_60_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_60_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_70_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_70_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_70_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_70_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_80_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_80_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_80_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_80_val_img_3.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_90_val_img_0.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_90_val_img_1.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_90_val_img_2.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_90_val_img_3.png filter=lfs diff=lfs merge=lfs -text

model_index.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "StableDiffusionXLInstructPix2PixPipeline",
+  "_diffusers_version": "0.33.1",
+  "_name_or_path": "/home/ach17654gk/download/model/sdxl/snapshots/462165984030d82259a11f4367a4eed129e94a7b",
+  "force_zeros_for_empty_prompt": true,
+  "scheduler": [
+    "diffusers",
+    "EulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.33.1",
+  "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",
+  "timestep_type": "discrete",
+  "trained_betas": null,
+  "use_beta_sigmas": false,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/ach17654gk/download/model/sdxl/snapshots/462165984030d82259a11f4367a4eed129e94a7b",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c3d6454dd2d23414b56aa1b5858a72487a656937847b6fea8d0606d7a42cdbc
+size 492265168

text_encoder_2/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/ach17654gk/download/model/sdxl/snapshots/462165984030d82259a11f4367a4eed129e94a7b",
+  "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": "float32",
+  "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 sha256:3a6032f63d37ae02bbc74ccd6a27440578cd71701f96532229d0154f55a8d3ff
+size 2778702264

tokenizer/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": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "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": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

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

@@ -0,0 +1,73 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.33.1",
+  "_name_or_path": "/home/ach17654gk/download/model/sdxl/snapshots/462165984030d82259a11f4367a4eed129e94a7b",
+  "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
+}

unet/diffusion_pytorch_model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00228f76d3df535e8a69259f37188ee046534c85bfa237ccc7094f2cde9e1fe7
+size 9988185240

unet/diffusion_pytorch_model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:444c8f523575097783a255acf9b6ca9fff7971c6cef1fd78508ef6d41ea22536
+size 281938304

vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.33.1",
+  "_name_or_path": "/home/ach17654gk/download/model/sdxl/snapshots/462165984030d82259a11f4367a4eed129e94a7b",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
+  "shift_factor": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1598f3d24932bcfe6634e8b618ea1e30ab1d57f5aad13a6d2de446d2199f2341
+size 334643268