End of training

README.md

@@ -10,6 +10,11 @@ tags:
 - diffusers-training
 - stable-diffusion
 - stable-diffusion-diffusers
+- text-to-image
+- dreambooth
+- diffusers-training
+- stable-diffusion
+- stable-diffusion-diffusers
 ---
 
 <!-- This model card has been generated automatically according to the information the training script had access to. You

checkpoint-500/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d64888b9c24ca395b2962f16d488a84f53d6c877f08185de91372a40d4556207
-size 6927867604
+oid sha256:cbc336965e96f43077586b92c851925c9dd9ce103f9dfbe63a593ae1c0a5bc7c
+size 1999458902

checkpoint-500/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75a7fea21a2f7c24ed938969e15015819d6665c5238825f42dc85797152ea22b
-size 14408
+oid sha256:c090abde591b2d8f58e9f012138a768f867c6e31cf7fe159a4f0d882481c3936
+size 14472

checkpoint-500/scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65115106fbd9463fa6c7133b543dece71c31fcba363ff15b8c73f8c7eb0739c5
+oid sha256:298e7e75502de41a98ece7ac5311b3b598cf308af851c910dc4da2b9a52082ad
 size 1000

checkpoint-500/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "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": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "vocab_size": 49408
+}

checkpoint-500/text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f701015536a0210e2734b390e70868e8a5e611c12254930fb53239f196401210
+size 492265168

checkpoint-500/unet/config.json

@@ -1,17 +1,12 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.33.0.dev0",
-  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
   "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_head_dim": 8,
   "attention_type": "default",
   "block_out_channels": [
     320,
@@ -24,7 +19,7 @@
   "class_embeddings_concat": false,
   "conv_in_kernel": 3,
   "conv_out_kernel": 3,
-  "cross_attention_dim": 1024,
+  "cross_attention_dim": 768,
   "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
@@ -55,7 +50,7 @@
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
   "reverse_transformer_layers_per_block": null,
-  "sample_size": 96,
+  "sample_size": 64,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,
   "time_embedding_dim": null,
@@ -69,5 +64,5 @@
     "CrossAttnUpBlock2D"
   ],
   "upcast_attention": false,
-  "use_linear_projection": true
+  "use_linear_projection": false
 }

checkpoint-500/unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76a7714faf4003e5028071bf38c1c32107df8acc005e1dd8a5451950485a759f
-size 3463726504
+oid sha256:2e2372e9e43520ea25fd6698b3e9616b29476ed1d5479cc06a9bc861149e0e63
+size 3438167536

logs/dreambooth/1739794284.604542/events.out.tfevents.1739794284.baker.cs.ubc.ca.769702.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8401cc92160c3a504cf1d1a78ff00abcdd63ae1924d3e024fc564af5199956df
+size 2864

logs/dreambooth/1739794284.6056771/hparams.yml

@@ -0,0 +1,60 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_data_dir: ./dog_class_prior
+class_labels_conditioning: null
+class_prompt: a photo of dog
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+instance_data_dir: dog
+instance_prompt: a photo of sks dog
+learning_rate: 2.0e-06
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_steps: 800
+mixed_precision: null
+num_class_images: 200
+num_train_epochs: 4
+num_validation_images: 4
+offset_noise: false
+output_dir: ./model_checkpoints
+pre_compute_text_embeddings: false
+pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
+prior_generation_precision: null
+prior_loss_weight: 1.0
+push_to_hub: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: null
+set_grads_to_none: false
+skip_save_text_encoder: false
+snr_gamma: null
+text_encoder_use_attention_mask: false
+tokenizer_max_length: null
+tokenizer_name: null
+train_batch_size: 1
+train_text_encoder: true
+use_8bit_adam: true
+validation_prompt: null
+validation_scheduler: DPMSolverMultistepScheduler
+validation_steps: 100
+variant: null
+with_prior_preservation: true

logs/dreambooth/events.out.tfevents.1739794284.baker.cs.ubc.ca.769702.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c274e184bb0848f5e8c3877975295899b5a38d5cfc0ec910c03e7fd0be52a02
+size 67034

model_index.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "StableDiffusionPipeline",
   "_diffusers_version": "0.33.0.dev0",
-  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
   "feature_extractor": [
     "transformers",
     "CLIPImageProcessor"
@@ -10,14 +10,14 @@
     null,
     null
   ],
-  "requires_safety_checker": false,
+  "requires_safety_checker": true,
   "safety_checker": [
-    null,
-    null
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
   ],
   "scheduler": [
     "diffusers",
-    "DDIMScheduler"
+    "PNDMScheduler"
   ],
   "text_encoder": [
     "transformers",

scheduler/scheduler_config.json

@@ -1,20 +1,15 @@
 {
-  "_class_name": "DDIMScheduler",
+  "_class_name": "PNDMScheduler",
   "_diffusers_version": "0.33.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
-  "clip_sample_range": 1.0,
-  "dynamic_thresholding_ratio": 0.995,
   "num_train_timesteps": 1000,
-  "prediction_type": "v_prediction",
-  "rescale_betas_zero_snr": false,
-  "sample_max_value": 1.0,
+  "prediction_type": "epsilon",
   "set_alpha_to_one": false,
   "skip_prk_steps": true,
   "steps_offset": 1,
-  "thresholding": false,
   "timestep_spacing": "leading",
   "trained_betas": null
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -7,16 +7,16 @@
   "bos_token_id": 0,
   "dropout": 0.0,
   "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_size": 1024,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
   "initializer_factor": 1.0,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 77,
   "model_type": "clip_text_model",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 23,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "projection_dim": 512,
   "torch_dtype": "float32",

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67e013543d4fac905c882e2993d86a2d454ee69dc9e8f37c0c23d33a48959d15
-size 1361596304
+oid sha256:709ec1b3a4481cfb5393ca7679c988511faf53b1fc2bc99ef336a4cb2aeae481
+size 492265168

tokenizer/special_tokens_map.json

@@ -13,7 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "!",
+  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer/tokenizer_config.json

@@ -1,14 +1,6 @@
 {
   "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,
@@ -33,7 +25,7 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 77,
-  "pad_token": "!",
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "CLIPTokenizer",
   "unk_token": "<|endoftext|>"
 }

unet/config.json

@@ -1,17 +1,12 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.33.0.dev0",
-  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
   "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_head_dim": 8,
   "attention_type": "default",
   "block_out_channels": [
     320,
@@ -24,7 +19,7 @@
   "class_embeddings_concat": false,
   "conv_in_kernel": 3,
   "conv_out_kernel": 3,
-  "cross_attention_dim": 1024,
+  "cross_attention_dim": 768,
   "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
@@ -55,7 +50,7 @@
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
   "reverse_transformer_layers_per_block": null,
-  "sample_size": 96,
+  "sample_size": 64,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,
   "time_embedding_dim": null,
@@ -69,5 +64,5 @@
     "CrossAttnUpBlock2D"
   ],
   "upcast_attention": false,
-  "use_linear_projection": true
+  "use_linear_projection": false
 }

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60e52d56caa99c2eb7a72794051dbfc00970c55632e0b21eb3b0cdaa107a01f1
-size 3463726504
+oid sha256:9715039e384093cdee3926e0b02465a60b2f98acab19bb433d8a874d2453db5a
+size 3438167536

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.33.0.dev0",
-  "_name_or_path": "/scratch/dajisafe/Track_Diffusion/Dreambooth/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2/snapshots/1e128c8891e52218b74cde8f26dbfc701cb99d79/vae",
+  "_name_or_path": "/scratch/dajisafe/Track_Diffusion/Dreambooth/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -24,7 +24,7 @@
   "mid_block_add_attention": true,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 768,
+  "sample_size": 512,
   "scaling_factor": 0.18215,
   "shift_factor": null,
   "up_block_types": [

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aa1f43011b553a4cba7f37456465cdbd48aab7b54b9348b890e8058ea7683ec
+oid sha256:b4d2b5932bb4151e54e694fd31ccf51fca908223c9485bd56cd0e1d83ad94c49
 size 334643268