End of training

README.md

@@ -1,8 +1,8 @@
 
 ---
 license: creativeml-openrail-m
-base_model: stabilityai/stable-diffusion-2
-instance_prompt: a photo of xyz woman
+base_model: runwayml/stable-diffusion-v1-5
+instance_prompt: a picture of oghj woman
 tags:
 - stable-diffusion
 - stable-diffusion-diffusers
@@ -14,9 +14,9 @@ inference: true
     
 # DreamBooth - moteloumka/model
 
-This is a dreambooth model derived from stabilityai/stable-diffusion-2. The weights were trained on a photo of xyz woman using [DreamBooth](https://dreambooth.github.io/).
+This is a dreambooth model derived from runwayml/stable-diffusion-v1-5. The weights were trained on a picture of oghj woman using [DreamBooth](https://dreambooth.github.io/).
 You can find some example images in the following. 
 
 
 
-DreamBooth for the text encoder was enabled: True.
+DreamBooth for the text encoder was enabled: False.

checkpoint-1000/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9db57d7b4c105b160776ebd7003b6dae3b1b7317bd694c575702cb614038a5c
-size 2421617512
+oid sha256:e1ef578c13bd2536ccd5c1423a39a147b223a244d2c7ae48b65876662ea38e62
+size 1725110394

checkpoint-1000/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:614e160a1c12ddf43a044a91c915847658ee111e1c6a19de7e358d887f9613e6
-size 14408
+oid sha256:327e512a38c60a12f8ba1d3915bc9e397ae13c6f390db7f4470c148e7931b123
+size 14344

checkpoint-1000/unet/config.json

@@ -1,17 +1,12 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.26.0.dev0",
-  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "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-1000/unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83a069f2460294823098a9b42e3af772761625d465845dd87abbdc11c6cf71dd
-size 3463726504
+oid sha256:a47c26391517730024585a660b3958f252465bf182c6815eead504151560ae5b
+size 3438167536

checkpoint-1500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf52cad6dd8d385c54dcb519a8671a7f20c0f4996f9222931ef21005d95713f3
+size 1725110394

checkpoint-1500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c239e8aca517c964d6d32f7e71252280f861bba65d3fa9db0e1d2a086eb393
+size 14344

checkpoint-1500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f8108c9f3ee073c12b3784e0f4fdb33e21478fc1e37ff98e67bf025cabaa140
+size 1000

checkpoint-1500/unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.26.0.dev0",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "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": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "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": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "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": false
+}

checkpoint-1500/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:856a2b3b134a70c437e5b58d05c41b4639327ae8324d7188c662a2fec742168e
+size 3438167536

checkpoint-500/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa4012350a17735b45d75c9c691beb8d02c003d953946e6eade0e1b79c9637e8
-size 2421617512
+oid sha256:c00ae596f5993297dc559733a691689f854e52bb68d84a5c3f6d15f80c8de3da
+size 1725110394

checkpoint-500/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4ffe91528141f9cc3a2c33c8e05571fb7a48c195f1bab7440161c9f5dbb66a
-size 14408
+oid sha256:da106af12d8b74a5e6c575cfce8b3606e12557a55d3d35192d83370a5d92c092
+size 14344

checkpoint-500/unet/config.json

@@ -1,17 +1,12 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.26.0.dev0",
-  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "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 sha256:0c429d324c5712643fba42fcaddfdda35e0c83c3497c1ac01f671c20a60dc6c6
-size 3463726504
+oid sha256:e6525f2b5a2d6f0c81cda52973a9f6aeb9f61cebc8abf76d0706a7ae8d1b5ea5
+size 3438167536

logs/dreambooth/1704957461.4648933/events.out.tfevents.1704957461.nqnovjm5g0.229.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ecee2d56fa6561681cb506d3349e8720c0d77f0c4becd2f52ca659bf086c7d
+size 2899

logs/dreambooth/1704957461.4675572/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: /notebooks/diffusers/examples/dreambooth/gen_woman
+class_labels_conditioning: null
+class_prompt: picture of a woman
+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: /notebooks/diffusers/examples/dreambooth/sonja
+instance_prompt: a picture of oghj woman
+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: 1500
+mixed_precision: null
+num_class_images: 450
+num_train_epochs: 7
+num_validation_images: 4
+offset_noise: false
+output_dir: /notebooks/model
+pre_compute_text_embeddings: false
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+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: false
+use_8bit_adam: true
+validation_prompt: null
+validation_scheduler: DPMSolverMultistepScheduler
+validation_steps: 100
+variant: null
+with_prior_preservation: true

logs/dreambooth/events.out.tfevents.1704957461.nqnovjm5g0.229.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d669e1cfd6a28f308cfddbcbbea74ba2d2eda14eb1752225670edadad2e08223
+size 251526

model_index.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "StableDiffusionPipeline",
   "_diffusers_version": "0.26.0.dev0",
-  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "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",

safety_checker/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/safety_checker",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/safety_checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
   ],

scheduler/scheduler_config.json

@@ -1,20 +1,15 @@
 {
-  "_class_name": "DDIMScheduler",
+  "_class_name": "PNDMScheduler",
   "_diffusers_version": "0.26.0.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": "runwayml/stable-diffusion-v1-5",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -7,18 +7,18 @@
   "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,
+  "projection_dim": 768,
   "torch_dtype": "float32",
   "transformers_version": "4.36.2",
   "vocab_size": 49408

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b16377b86fbf6be57291e4f28ada1e65403741c0cea96c88ee05f3bc7c279df3
-size 1361596304
+oid sha256:778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3
+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,
@@ -32,7 +24,7 @@
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "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": "0.26.0.dev0",
-  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "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 sha256:83a069f2460294823098a9b42e3af772761625d465845dd87abbdc11c6cf71dd
-size 3463726504
+oid sha256:856a2b3b134a70c437e5b58d05c41b4639327ae8324d7188c662a2fec742168e
+size 3438167536

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.26.0.dev0",
-  "_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2/snapshots/1e128c8891e52218b74cde8f26dbfc701cb99d79/vae",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/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": 768,
+  "sample_size": 512,
   "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 sha256:2aa1f43011b553a4cba7f37456465cdbd48aab7b54b9348b890e8058ea7683ec
+oid sha256:b4d2b5932bb4151e54e694fd31ccf51fca908223c9485bd56cd0e1d83ad94c49
 size 334643268