Upload folder using huggingface_hub

checkpoint-250/ema_unet.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:179fc02418019fffa3e6ebd34aa1d0684ff37efc9b2942d42a9070d0fd764f8b
+size 1307450832

checkpoint-250/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ca0b726c2161bd7dbd85b5b9a96908c8cc6641a2889031e4ccae858a940f99b
+size 665134170

checkpoint-250/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbfe8bb6f07c1327c13db2f26fbe0a3f97eeba98bd716577a2bd06bc23a12f67
+size 14408

checkpoint-250/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccec82ecb1db9fee8431a9924525ac42c65eba373a478c5528e653b68744a6a9
+size 988

checkpoint-250/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:671d7cdad6271b0e08d32ec8a2aef8dfcbceb770590b34b1f7cb1d58335266bb
+size 1000

checkpoint-250/unet.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5921dd9dc5b29de744fd62f604bd2a3d51cc28fb49f0bf8ef0e446796be6a00
+size 1307426536

config.json

@@ -0,0 +1,69 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.33.1",
+  "_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,
+  "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
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d5ae04c3c76b378c269b816dd17edb75f0dfed2b91ef1b08c331c23f6579e5
+size 1307346120

logs/text2image-fine-tune/1745049067.6277308/events.out.tfevents.1745049067.737ec2541a83.6090.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05311231f958d69ea50a367b40d49f8acbd7f3bd273e6be2dbb225d25ce70e70
+size 2485

logs/text2image-fine-tune/1745049067.6294327/hparams.yml

@@ -0,0 +1,49 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.001
+allow_tf32: false
+cache_dir: null
+cast_teacher_unet: false
+center_crop: false
+checkpointing_steps: 250
+checkpoints_total_limit: 20
+dataloader_num_workers: 1
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+huber_c: 0.001
+learning_rate: 5.0e-06
+local_rank: -1
+logging_dir: logs
+lora_rank: 64
+loss_type: huber
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: 4000000
+max_train_steps: 250
+mixed_precision: fp16
+num_ddim_timesteps: 40
+num_train_epochs: 1
+output_dir: bkv2trfdp-test
+pretrained_teacher_model: nota-ai/bk-sdm-v2-tiny
+pretrained_vae_model_name_or_path: null
+proportion_empty_prompts: 0
+push_to_hub: false
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: null
+teacher_revision: null
+tracker_project_name: text2image-fine-tune
+train_batch_size: 16
+use_8bit_adam: true
+validation_steps: 10000
+w_max: 15.0
+w_min: 5.0

logs/text2image-fine-tune/events.out.tfevents.1745049067.737ec2541a83.6090.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:641cf132982a56d15bb7354df565b7b16e8114762a7144662e74439d5102fbc7
+size 20834