update

checkpoint-500/optimizer.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3e7497c67898dca80cc2acbd43ac726fb9fb9d67810a908a751b5ae882fc1b50
-size 47392445

checkpoint-500/pytorch_lora_weights.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:359ae367f84b4dc4f59c5baa9cafee3774117cd1443b28b300846000349e6353
-size 23401064

checkpoint-500/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a3f196a54202bb4ba1220e8c59f42f9cda0702d68ea83147d814c2fb2f36b8f2
-size 557

checkpoint-500/scheduler.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:62783ff6f0ae2c2ccc177b097e430c03940c5e70c38a191df273c5cf7ab1227c
-size 563

checkpoint-1000/scheduler.bin → logs/text2image-fine-tune-sdxl/1694021617.6494288/events.out.tfevents.1694021617.twinkle1.794128.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:963c3085720a3a3ca1d178559a0f2dc5d5b36fa395a4663f0194bfac4a754038
-size 563
+oid sha256:7b782dd43d192bc2b310904a36d9b30c0023fd43900f16f5ae532454aff7e71c
+size 2403

logs/{text2image-fine-tune/1694016628.386469 → text2image-fine-tune-sdxl/1694021617.651228}/hparams.yml

@@ -5,47 +5,48 @@ adam_weight_decay: 0.01
 allow_tf32: false
 cache_dir: null
 caption_column: text
-center_crop: false
-checkpointing_steps: 500
+center_crop: true
+checkpointing_steps: 1000
 checkpoints_total_limit: null
 dataloader_num_workers: 0
 dataset_config_name: null
 dataset_name: JAWCF/maps
-enable_xformers_memory_efficient_attention: false
-gradient_accumulation_steps: 1
-gradient_checkpointing: false
+enable_xformers_memory_efficient_attention: true
+force_snr_gamma: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
 hub_model_id: null
 hub_token: null
 image_column: image
-learning_rate: 0.0001
+learning_rate: 1.0e-06
 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: 88
+max_train_steps: 3000
 mixed_precision: fp16
 noise_offset: 0
-num_train_epochs: 2
+num_train_epochs: 273
 num_validation_images: 4
-output_dir: sdxl-maps
+output_dir: maps-xl
 prediction_type: null
 pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
 pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
+proportion_empty_prompts: 0.2
 push_to_hub: false
 random_flip: true
-rank: 4
 report_to: tensorboard
-resolution: 1024
+resolution: 512
 resume_from_checkpoint: null
 revision: null
 scale_lr: false
-seed: 42
+seed: null
 snr_gamma: null
 train_batch_size: 1
 train_data_dir: null
-train_text_encoder: false
-use_8bit_adam: false
+use_8bit_adam: true
+use_ema: false
 validation_epochs: 1
 validation_prompt: null

checkpoint-500/random_states_0.pkl → logs/text2image-fine-tune-sdxl/events.out.tfevents.1694021617.twinkle1.794128.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f2bfff117f6074e4eb51eb6fd03c26fb5dead6a6052cd468bc56da4cc96a2e4
-size 14663
+oid sha256:45cee1b83d8665760b1064fbc320335eef81f02c99aa559138604aba65323819
+size 146961

logs/text2image-fine-tune/1694016628.3844774/events.out.tfevents.1694016628.twinkle1.765799.1

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ef6db7372ba09f2ddf869a4160d08611715cf27b629804052e5a55bde8cdef85
-size 2365

logs/text2image-fine-tune/1694019947.4911246/events.out.tfevents.1694019947.twinkle1.781724.1

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:41af42758fab67a82ffd65267d30fae1e8664977451e7e5b76048b95eb138fd0
-size 2365

logs/text2image-fine-tune/1694019947.4924138/hparams.yml

@@ -1,51 +0,0 @@
-adam_beta1: 0.9
-adam_beta2: 0.999
-adam_epsilon: 1.0e-08
-adam_weight_decay: 0.01
-allow_tf32: false
-cache_dir: null
-caption_column: text
-center_crop: false
-checkpointing_steps: 500
-checkpoints_total_limit: null
-dataloader_num_workers: 0
-dataset_config_name: null
-dataset_name: JAWCF/maps
-enable_xformers_memory_efficient_attention: false
-gradient_accumulation_steps: 1
-gradient_checkpointing: false
-hub_model_id: null
-hub_token: null
-image_column: image
-learning_rate: 0.0001
-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: 1320
-mixed_precision: fp16
-noise_offset: 0
-num_train_epochs: 30
-num_validation_images: 4
-output_dir: sdxl-maps
-prediction_type: null
-pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
-pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
-push_to_hub: false
-random_flip: true
-rank: 4
-report_to: tensorboard
-resolution: 1024
-resume_from_checkpoint: null
-revision: null
-scale_lr: false
-seed: 42
-snr_gamma: null
-train_batch_size: 1
-train_data_dir: null
-train_text_encoder: false
-use_8bit_adam: false
-validation_epochs: 1
-validation_prompt: null

logs/text2image-fine-tune/events.out.tfevents.1694016628.twinkle1.765799.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:88167d9ca1f86c66d14d5c5e45d9932e15496d37132c503a6e3adcf34d8aee5b
-size 4312

logs/text2image-fine-tune/events.out.tfevents.1694019947.twinkle1.781724.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7b8f7475120f2ae9c1491b67ab47ec319f46e1c58741719ba815d00e745c07f8
-size 64641

model_index.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "StableDiffusionXLPipeline",
+  "_diffusers_version": "0.21.0.dev0",
+  "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
+  "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"
+  ]
+}

pytorch_lora_weights.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2c1e559a4f52e0513d0e73fde88397280d69c03588fa0671de694943ad553428
-size 23401064

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.21.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "interpolation_type": "linear",
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "trained_betas": null,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/wucf/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/f898a3e026e802f68796b95e9702464bac78d76f/text_encoder",
+  "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": "float16",
+  "transformers_version": "4.33.0",
+  "vocab_size": 49408
+}

checkpoint-1000/optimizer.bin → text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d535d837672c7ef94ddab64bdad01628a00d95428df06dd0020855f5a4ffb86
-size 47392445
+oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+size 246144152

text_encoder_2/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/wucf/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/f898a3e026e802f68796b95e9702464bac78d76f/text_encoder_2",
+  "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": "float16",
+  "transformers_version": "4.33.0",
+  "vocab_size": 49408
+}

checkpoint-1000/random_states_0.pkl → text_encoder_2/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:192f79e73e3b59beb5b5695bc0a83081bf5cbb9f3e42eda7b23c62f73945d1e8
-size 14663
+oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
+size 1389382176

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 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,72 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.21.0.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": 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": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "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/scaler.pt → unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68cff80b680ddf6e7abbef98b5f336b97f9b5963e2209307f639383870e8cc71
-size 557
+oid sha256:c95444d15efd6410c6b5ff45db1d224f9d75d29476db9f0859bf47f5f2fa63ab
+size 10270077736

vae/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.21.0.dev0",
+  "_name_or_path": "madebyollin/sdxl-vae-fp16-fix",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": false,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.13025,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

checkpoint-1000/pytorch_lora_weights.safetensors → vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1a2c84c3cae8724cc199319bc8ced37ab0f144775f5c6dfd754c3fff263ebf9
-size 23401064
+oid sha256:6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48
+size 167335342