End of training

README.md

@@ -1,7 +1,7 @@
 
 ---
 license: creativeml-openrail-m
-base_model: CompVis/stable-diffusion-v1-4
+base_model: stabilityai/stable-diffusion-2
 instance_prompt: a photo of sks dog
 tags:
 - stable-diffusion
@@ -14,7 +14,7 @@ inference: true
  
 # DreamBooth - oliverN/path-to-save-model
 
-This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/).
+This is a dreambooth model derived from stabilityai/stable-diffusion-2. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/).
 You can find some example images in the following. 
 
 

checkpoint-500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bad01461c1b84636b21480a4b67b31c9eb6062ea7470f1c8e377e9c7fb58df91
+size 1737911025

checkpoint-500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3eef1bbc4562b367d938f60bd61cd607cfe0dfa3684c939ca6a8feb8ec6709c
+size 14567

checkpoint-500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa4c7be44c959599b8b43bb9bc3371e9e4e5bbc5758b3ab5afcccfda3e72e67
+size 559

checkpoint-500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98fce84a297634754cde5ed846e847d31898924cb043a40f488bb85612efa6b7
+size 559

checkpoint-500/unet/config.json

@@ -0,0 +1,71 @@
+{
+ "_class_name": "UNet2DConditionModel",
+ "_diffusers_version": "0.21.0.dev0",
+ "_name_or_path": "stabilityai/stable-diffusion-2",
+ "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,
+ "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",
+ "sample_size": 96,
+ "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-500/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7580572485ecbaee7fbe7c69f62f69be17f4c533b93aad9a7ca5e308abe1bdb4
+size 3463726504

logs/dreambooth/1693473798.9984226/events.out.tfevents.1693473798.RND-02.324323.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d08ed00c65749725a8c9fb34e5e1139a35459ca9f56b448b67b6f1ef2bb59b92
+size 2867

logs/dreambooth/1693473798.9990923/hparams.yml

@@ -0,0 +1,58 @@
+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: path-to-class-images
+class_labels_conditioning: null
+class_prompt: a photo of dog
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 2
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+instance_data_dir: dog
+instance_prompt: a photo of sks dog
+learning_rate: 5.0e-06
+local_rank: 0
+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: 8
+num_validation_images: 4
+offset_noise: false
+output_dir: path-to-save-model
+pre_compute_text_embeddings: false
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2
+prior_generation_precision: null
+prior_loss_weight: 1.0
+push_to_hub: true
+report_to: tensorboard
+resolution: 768
+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
+text_encoder_use_attention_mask: false
+tokenizer_max_length: null
+tokenizer_name: null
+train_batch_size: 1
+train_text_encoder: false
+use_8bit_adam: true
+validation_prompt: null
+validation_scheduler: DPMSolverMultistepScheduler
+validation_steps: 100
+with_prior_preservation: true

logs/dreambooth/1693474035.716167/events.out.tfevents.1693474035.RND-02.324510.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee239fc19f7505c47d3193f5b8eba901a51f9fc4e0481fbfe08f4226e0637884
+size 2867

logs/dreambooth/1693474035.716927/hparams.yml

@@ -0,0 +1,58 @@
+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: path-to-class-images
+class_labels_conditioning: null
+class_prompt: a photo of dog
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 2
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+instance_data_dir: dog
+instance_prompt: a photo of sks dog
+learning_rate: 5.0e-06
+local_rank: 0
+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: 8
+num_validation_images: 4
+offset_noise: false
+output_dir: path-to-save-model
+pre_compute_text_embeddings: false
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2
+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
+text_encoder_use_attention_mask: false
+tokenizer_max_length: null
+tokenizer_name: null
+train_batch_size: 1
+train_text_encoder: false
+use_8bit_adam: true
+validation_prompt: null
+validation_scheduler: DPMSolverMultistepScheduler
+validation_steps: 100
+with_prior_preservation: true

logs/dreambooth/events.out.tfevents.1693473798.RND-02.324323.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a1eb2a0ba59c080ac0f2f546d6478190951905fdd2176b7c237655c429de4ca
+size 88

logs/dreambooth/events.out.tfevents.1693474035.RND-02.324510.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8efa8ffb2bf6b557661a6424e4828ce09751d24378b44daa8bdd3b399c28ebeb
+size 133974

model_index.json

@@ -1,19 +1,19 @@
 {
  "_class_name": "StableDiffusionPipeline",
  "_diffusers_version": "0.21.0.dev0",
- "_name_or_path": "CompVis/stable-diffusion-v1-4",
+ "_name_or_path": "stabilityai/stable-diffusion-2",
  "feature_extractor": [
  "transformers",
  "CLIPImageProcessor"
  ],
- "requires_safety_checker": true,
+ "requires_safety_checker": false,
  "safety_checker": [
- "stable_diffusion",
- "StableDiffusionSafetyChecker"
+ null,
+ null
  ],
  "scheduler": [
  "diffusers",
- "PNDMScheduler"
+ "DDIMScheduler"
  ],
  "text_encoder": [
  "transformers",

scheduler/scheduler_config.json

@@ -1,15 +1,20 @@
 {
- "_class_name": "PNDMScheduler",
+ "_class_name": "DDIMScheduler",
  "_diffusers_version": "0.21.0.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": "epsilon",
+ "prediction_type": "v_prediction",
+ "rescale_betas_zero_snr": false,
+ "sample_max_value": 1.0,
  "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": "CompVis/stable-diffusion-v1-4",
+ "_name_or_path": "stabilityai/stable-diffusion-2",
  "architectures": [
  "CLIPTextModel"
  ],
@@ -7,16 +7,16 @@
  "bos_token_id": 0,
  "dropout": 0.0,
  "eos_token_id": 2,
- "hidden_act": "quick_gelu",
- "hidden_size": 768,
+ "hidden_act": "gelu",
+ "hidden_size": 1024,
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
- "intermediate_size": 3072,
+ "intermediate_size": 4096,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 77,
  "model_type": "clip_text_model",
- "num_attention_heads": 12,
- "num_hidden_layers": 12,
+ "num_attention_heads": 16,
+ "num_hidden_layers": 23,
  "pad_token_id": 1,
  "projection_dim": 512,
  "torch_dtype": "float16",

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
-size 246144152
+oid sha256:bc1827c465450322616f06dea41596eac7d493f4e95904dcb51f0fc745c4e13f
+size 680820392

tokenizer/special_tokens_map.json

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

unet/config.json

@@ -1,12 +1,17 @@
 {
  "_class_name": "UNet2DConditionModel",
  "_diffusers_version": "0.21.0.dev0",
- "_name_or_path": "CompVis/stable-diffusion-v1-4",
+ "_name_or_path": "stabilityai/stable-diffusion-2",
  "act_fn": "silu",
  "addition_embed_type": null,
  "addition_embed_type_num_heads": 64,
  "addition_time_embed_dim": null,
- "attention_head_dim": 8,
+ "attention_head_dim": [
+ 5,
+ 10,
+ 20,
+ 20
+ ],
  "attention_type": "default",
  "block_out_channels": [
  320,
@@ -19,7 +24,7 @@
  "class_embeddings_concat": false,
  "conv_in_kernel": 3,
  "conv_out_kernel": 3,
- "cross_attention_dim": 768,
+ "cross_attention_dim": 1024,
  "cross_attention_norm": null,
  "down_block_types": [
  "CrossAttnDownBlock2D",
@@ -48,7 +53,7 @@
  "resnet_out_scale_factor": 1.0,
  "resnet_skip_time_act": false,
  "resnet_time_scale_shift": "default",
- "sample_size": 64,
+ "sample_size": 96,
  "time_cond_proj_dim": null,
  "time_embedding_act_fn": null,
  "time_embedding_dim": null,
@@ -62,5 +67,5 @@
  "CrossAttnUpBlock2D"
  ],
  "upcast_attention": false,
- "use_linear_projection": false
+ "use_linear_projection": true
 }

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:666d1c028481171e3ce70a966603fc01fd79fb24c64f50e17feafdb0bd85233c
-size 3438167536
+oid sha256:c28e5714abcc08ac4012afc4244e014373f7264311c49bd6ce3c07c298e47f67
+size 3463726504

vae/config.json

@@ -1,7 +1,7 @@
 {
  "_class_name": "AutoencoderKL",
  "_diffusers_version": "0.21.0.dev0",
- "_name_or_path": "CompVis/stable-diffusion-v1-4/vae",
+ "_name_or_path": "/home/dev_ml2/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2/snapshots/1e128c8891e52218b74cde8f26dbfc701cb99d79/vae",
  "act_fn": "silu",
  "block_out_channels": [
  128,
@@ -21,7 +21,7 @@
  "layers_per_block": 2,
  "norm_num_groups": 32,
  "out_channels": 3,
- "sample_size": 512,
+ "sample_size": 768,
  "scaling_factor": 0.18215,
  "up_block_types": [
  "UpDecoderBlock2D",

vae/diffusion_pytorch_model.safetensors

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