Upload folder using huggingface_hub

checkpoint-10000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db880a0400f97bfa87b149cc9676402713b3adf3a79270d0c679edb331169f6
+size 2614904964

checkpoint-10000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98bef1d891075adf439835c4c0967c657e8bcb2ec4cac7bd06920c3c075558f3
+size 14344

checkpoint-10000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d49367aa0f19981d0484e3ef5c1b009e6bdd8e5c0d8ef08f2f8d235b9f843816
+size 988

checkpoint-10000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d31ad9a5150e341b638f838a47b3cb3db0d48efa493bcc8d1f8bf787b2c8cee3
+size 1000

checkpoint-10000/unet/config.json

@@ -0,0 +1,69 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.34.0.dev0",
+  "_name_or_path": "bkv2t-fttest/checkpoint-9000",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    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"
+  ],
+  "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": 1,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": null,
+  "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": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": true
+}

checkpoint-10000/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde3a4acfb2038126b170cd8fb234dad7c6cb14036b08a90d9c4bd106936b33a
+size 1307346120

checkpoint-10000/unet_ema/config.json

@@ -0,0 +1,76 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.34.0.dev0",
+  "_name_or_path": "nota-ai/bk-sdm-v2-tiny",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    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,
+  "decay": 0.9999,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "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,
+  "inv_gamma": 1.0,
+  "layers_per_block": 1,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": null,
+  "min_decay": 0.0,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "optimization_step": 10000,
+  "out_channels": 4,
+  "power": 0.6666666666666666,
+  "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": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "update_after_step": 0,
+  "use_ema_warmup": false,
+  "use_linear_projection": true
+}

checkpoint-10000/unet_ema/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2881f25410445850a142a8a57820cb218215d1fbf28fe292cd4b2bc8598512ff
+size 1307346120

logs/text2image-fine-tune/1749855193.0743153/events.out.tfevents.1749855193.9b33668f112d.6080.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7e3e5331ad97bacf8f38dc8296710c42e0aafa01a5724838345efcceebba0b1
+size 2715

logs/text2image-fine-tune/1749855193.0759602/hparams.yml

@@ -0,0 +1,56 @@
+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: true
+checkpointing_steps: 1000
+checkpoints_total_limit: 1
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: ./img-dataset
+dream_detail_preservation: 1.0
+dream_training: false
+enable_xformers_memory_efficient_attention: false
+foreach_ema: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+image_interpolation_mode: lanczos
+input_perturbation: 0
+learning_rate: 1.0e-05
+local_rank: -1
+logging_dir: logs
+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: 22
+offload_ema: false
+output_dir: bkv2t-fttest
+prediction_type: null
+pretrained_model_name_or_path: nota-ai/bk-sdm-v2-tiny
+push_to_hub: false
+random_flip: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: checkpoint-9000
+revision: null
+scale_lr: false
+seed: 42
+snr_gamma: 5.0
+tracker_project_name: text2image-fine-tune
+train_batch_size: 16
+train_data_dir: null
+use_8bit_adam: false
+use_ema: true
+validation_epochs: 5
+variant: null

logs/text2image-fine-tune/events.out.tfevents.1749855193.9b33668f112d.6080.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b6a0db6da7bfc2daa658b681d647c0ee2858af7319c4c1a3dca6335533dfa6
+size 49137