End of training

README.md

@@ -0,0 +1,22 @@
+
+---
+license: creativeml-openrail-m
+base_model: stabilityai/stable-diffusion-2
+instance_prompt: a photo of sks dog
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+- dreambooth
+inference: true
+---
+ 
+# DreamBooth - Yacong/my_dreambooth_out_dir
+
+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. 
+
+
+
+DreamBooth for the text encoder was enabled: False.

checkpoint-500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb5d1e1f3af8622e11c1c9685d46f4e2e4d944d0c7898543eb0727840baf06c7
+size 6927867155

checkpoint-500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b25a7789c9adea600e60e4ee2f97625da3dec117dc3d7740f6901cf3175bc751
+size 14727

checkpoint-500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6be622d51c3bcf8a1991c02b9778f31d7e3a79a8b22e03e81a36e25205ef4c5b
+size 563

checkpoint-500/unet/config.json

@@ -0,0 +1,70 @@
+{
+ "_class_name": "UNet2DConditionModel",
+ "_diffusers_version": "0.20.0.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
+ ],
+ "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.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab299ef8023cd1306e95cf216cdc8e6d03045d76bb88913078ec7fc4b0301e3
+size 3463934693

feature_extractor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+ "crop_size": {
+ "height": 224,
+ "width": 224
+ },
+ "do_center_crop": true,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_rescale": true,
+ "do_resize": true,
+ "feature_extractor_type": "CLIPFeatureExtractor",
+ "image_mean": [
+ 0.48145466,
+ 0.4578275,
+ 0.40821073
+ ],
+ "image_processor_type": "CLIPImageProcessor",
+ "image_std": [
+ 0.26862954,
+ 0.26130258,
+ 0.27577711
+ ],
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "size": {
+ "shortest_edge": 224
+ }
+}

logs/dreambooth/1691334595.4086812/events.out.tfevents.1691334595.DESKTOP-QNVT4IJ.256737.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b92b7c7b5b58a680c923dfa246e84bab4d4b4db1759e77b88d60b1827da8412
+size 2790

logs/dreambooth/1691334595.4266348/hparams.yml

@@ -0,0 +1,57 @@
+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: class_dir
+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: false
+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: -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: ./my_dreambooth_out_dir
+pre_compute_text_embeddings: false
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
+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: false
+validation_prompt: null
+validation_steps: 100
+with_prior_preservation: true

logs/dreambooth/1691334869.7514734/events.out.tfevents.1691334869.DESKTOP-QNVT4IJ.268392.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa31a478625ca9e5e1a17e9fb2d13a5e4ecb9ff409fd189abd65bd8769319acf
+size 2790

logs/dreambooth/1691334869.7705326/hparams.yml

@@ -0,0 +1,57 @@
+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: class_dir
+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: false
+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: -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: ./my_dreambooth_out_dir
+pre_compute_text_embeddings: false
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
+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: false
+validation_prompt: null
+validation_steps: 100
+with_prior_preservation: true

logs/dreambooth/1691335085.2478547/events.out.tfevents.1691335085.DESKTOP-QNVT4IJ.269085.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c9f3487f224a38753c6fd0babc78898188e43fb3baf80018a5515494a4e63c
+size 2780

logs/dreambooth/1691335085.267748/hparams.yml

@@ -0,0 +1,57 @@
+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: class_dir
+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: false
+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: -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: ./my_dreambooth_out_dir
+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: false
+validation_prompt: null
+validation_steps: 100
+with_prior_preservation: true

logs/dreambooth/events.out.tfevents.1691334595.DESKTOP-QNVT4IJ.256737.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf4ffa810712e7f75a49ef6715df285d4f10fad4cc9aa1511027fb6c18dc6899
+size 88

logs/dreambooth/events.out.tfevents.1691334869.DESKTOP-QNVT4IJ.268392.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f7607b4e25eee4c5591d5662eea44d8046c040f1a4633193cd6d479d4c5c2a
+size 88

logs/dreambooth/events.out.tfevents.1691335085.DESKTOP-QNVT4IJ.269085.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:324bda0e49b0a5765451073f593d3ee380fd0131bfec7c8075e76d6751dc6916
+size 67034

model_index.json

@@ -0,0 +1,34 @@
+{
+ "_class_name": "StableDiffusionPipeline",
+ "_diffusers_version": "0.20.0.dev0",
+ "_name_or_path": "stabilityai/stable-diffusion-2",
+ "feature_extractor": [
+ "transformers",
+ "CLIPImageProcessor"
+ ],
+ "requires_safety_checker": false,
+ "safety_checker": [
+ null,
+ null
+ ],
+ "scheduler": [
+ "diffusers",
+ "DDIMScheduler"
+ ],
+ "text_encoder": [
+ "transformers",
+ "CLIPTextModel"
+ ],
+ "tokenizer": [
+ "transformers",
+ "CLIPTokenizer"
+ ],
+ "unet": [
+ "diffusers",
+ "UNet2DConditionModel"
+ ],
+ "vae": [
+ "diffusers",
+ "AutoencoderKL"
+ ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,20 @@
+{
+ "_class_name": "DDIMScheduler",
+ "_diffusers_version": "0.20.0.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,
+ "set_alpha_to_one": false,
+ "skip_prk_steps": true,
+ "steps_offset": 1,
+ "thresholding": false,
+ "timestep_spacing": "leading",
+ "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+ "_name_or_path": "stabilityai/stable-diffusion-2",
+ "architectures": [
+ "CLIPTextModel"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 0,
+ "dropout": 0.0,
+ "eos_token_id": 2,
+ "hidden_act": "gelu",
+ "hidden_size": 1024,
+ "initializer_factor": 1.0,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "layer_norm_eps": 1e-05,
+ "max_position_embeddings": 77,
+ "model_type": "clip_text_model",
+ "num_attention_heads": 16,
+ "num_hidden_layers": 23,
+ "pad_token_id": 1,
+ "projection_dim": 512,
+ "torch_dtype": "float32",
+ "transformers_version": "4.31.0",
+ "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011e594b95e5c3fa2d317d6e8958102cd3f0283dccc10ecf0b705ce57cd6ecb0
+size 1361678941

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": "!",
+ "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
+ }
+}

unet/config.json

@@ -0,0 +1,70 @@
+{
+ "_class_name": "UNet2DConditionModel",
+ "_diffusers_version": "0.20.0.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
+ ],
+ "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
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34e3af666988805be30cbdee930ad360c6cb8d9d8564b3299ee6252def5e152e
+size 3463934693

vae/config.json

@@ -0,0 +1,32 @@
+{
+ "_class_name": "AutoencoderKL",
+ "_diffusers_version": "0.20.0.dev0",
+ "_name_or_path": "/home/exp/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2/snapshots/1e128c8891e52218b74cde8f26dbfc701cb99d79/vae",
+ "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,
+ "layers_per_block": 2,
+ "norm_num_groups": 32,
+ "out_channels": 3,
+ "sample_size": 768,
+ "scaling_factor": 0.18215,
+ "up_block_types": [
+ "UpDecoderBlock2D",
+ "UpDecoderBlock2D",
+ "UpDecoderBlock2D",
+ "UpDecoderBlock2D"
+ ]
+}

vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b01618945554d9840701d3453d4a9fe3db0db090164a5ed6305641306285b6f
+size 334712113