End of training

README.md

@@ -37,7 +37,7 @@ image.save("my_image.png")
 
 These are the key hyperparameters used during training:
 
-* Epochs: 1
+* Epochs: 17
 * Learning rate: 2e-06
 * Batch size: 2
 * Gradient accumulation steps: 1

checkpoint-7000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1098894dee08e6edf5469d9cd2ba489b753ddf097e002ae124962a3edb781e24
+size 1725109957

checkpoint-7000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53a2ff0bd429c0b69e9b8b53c8e8ac4cf45d5cdb772c857d1c9ebd33ddf1daa1
+size 14663

checkpoint-7000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d22aed3a858ee389297b2101bb2ed7ee9e37744f1a1f75273dbdf045d65b041a
+size 557

checkpoint-7000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea83ff14f5e8f1da2235cf21ca8b3fdc5fd812f31508a5c7359633540e54ac7
+size 563

checkpoint-7000/unet/config.json

@@ -0,0 +1,67 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.22.0.dev0",
+  "_name_or_path": "ekshat/stable-diffusion-anime-style",
+  "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",
+  "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-7000/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b83475abbf46a313166aefe2be9a287ebcd592bdc33962563fddb63d517a3874
+size 3438167536

results/text2image-fine-tune/1696224359.5462363/events.out.tfevents.1696224359.e9ff7e0f3622.6376.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:453a00720b21a25c128775d8ac110cac1d5f08da566ae601b95504eb17ab1ba0
+size 2294

results/text2image-fine-tune/1696224359.5480986/hparams.yml

@@ -0,0 +1,50 @@
+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: 7000
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: lambdalabs/naruto-blip-captions
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+input_perturbation: 0
+learning_rate: 2.0e-06
+local_rank: -1
+logging_dir: ./results
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 10000
+mixed_precision: fp16
+noise_offset: 0
+non_ema_revision: null
+num_train_epochs: 17
+output_dir: /content/Stable_Diffussion_Anime_Style
+prediction_type: null
+pretrained_model_name_or_path: ekshat/stable-diffusion-anime-style
+push_to_hub: true
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+snr_gamma: null
+tracker_project_name: text2image-fine-tune
+train_batch_size: 2
+train_data_dir: null
+use_8bit_adam: true
+use_ema: false
+validation_epochs: 5

results/text2image-fine-tune/events.out.tfevents.1696224022.e9ff7e0f3622.4903.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bef2cec016af17543e03c627e62d4306b266388313ebe3f155415916f12f632
-size 331912
+oid sha256:944736cf73a7661ee8b5217031b0b84a610b5ce902a3ab684e85108561144163
+size 335669

results/text2image-fine-tune/events.out.tfevents.1696224359.e9ff7e0f3622.6376.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20ece6a436996fa9779245783ce8d35f8f36e2823eaa884ab02352d3b5f7832f
+size 1870939

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4783ec1f4d181128db8464bb29630ed574db748c3dc24adc8fff7f0c1f05649f
+oid sha256:2b5422b668b7f1e75a63e2c9b01cb2f90ac7ff2afbd30920b1f1923d1a8e87af
 size 3438167536