Upload folder using huggingface_hub

controlnet/config.json

@@ -20,7 +20,7 @@
     256
   ],
   "controlnet_conditioning_channel_order": "rgb",
-  "cross_attention_dim": 768,
+  "cross_attention_dim": 1024,
   "down_block_types": [
     "DownBlock2D",
     "CrossAttnDownBlock2D",

controlnet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d005da74cf9e639b3b9d6a49ff845690fd2081fead531c714c98d2694e490c96
-size 728496840
+oid sha256:0686b783664e862fb77836c7a6cf5d116dca2aa9d40341e68a90128177245430
+size 1456953560

logs/text2image-fine-tune/1717903784.86201/events.out.tfevents.1717903784.3a3e3b616396.2113.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f8cfa3986afcf097e6b2644a7db6d8f9957da41cb1774b7a9331730d73d19e
+size 2457

logs/text2image-fine-tune/1717903784.8642344/hparams.yml

@@ -0,0 +1,47 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: true
+checkpointing_steps: 5000
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+lambda_kd_feat: 1.0
+lambda_kd_output: 1.0
+lambda_sd: 1.0
+learning_rate: 5.0e-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: 400000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 4939
+num_valid_images: 2
+output_dir: ./results/v2-base_kd_bk_tiny
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1-base
+random_flip: true
+report_to: all
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 1234
+train_batch_size: 32
+train_data_dir: ./data/laion_aes/preprocessed_11k
+unet_config_name: bk_tiny
+unet_config_path: ./src/unet_config_v2-base
+use_8bit_adam: false
+use_copy_weight_from_teacher: true
+use_ema: true
+valid_prompt: a golden vase with different flowers
+valid_steps: 500

logs/text2image-fine-tune/1717903925.3434956/events.out.tfevents.1717903925.3a3e3b616396.3501.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02e23a7c5660311efb1d4a72ab4129c6e946d478660020b301651b29015f8e04
+size 2409

logs/text2image-fine-tune/1717903925.3458326/hparams.yml

@@ -0,0 +1,47 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: true
+checkpointing_steps: 5000
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+lambda_kd_feat: 1.0
+lambda_kd_output: 1.0
+lambda_sd: 1.0
+learning_rate: 5.0e-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: 0
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 0
+num_valid_images: 2
+output_dir: ./results/v2-base_kd_bk_tiny
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1-base
+random_flip: true
+report_to: all
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 1234
+train_batch_size: 32
+train_data_dir: ./data/laion_aes/preprocessed_11k
+unet_config_name: bk_tiny
+unet_config_path: ./src/unet_config_v2-base
+use_8bit_adam: false
+use_copy_weight_from_teacher: true
+use_ema: true
+valid_prompt: a golden vase with different flowers
+valid_steps: 500

logs/text2image-fine-tune/events.out.tfevents.1717903778.3a3e3b616396.2113.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe47a550748b5bca29fae86582b59a28b7224ad77874115c8c680f265a2b8a6
+size 88

logs/text2image-fine-tune/events.out.tfevents.1717903908.3a3e3b616396.3501.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a6f78f4d4a32a59c49b1e64948d1d5e6e4225c22cdd82eda7313ca7ffa5f9a
+size 88

text_encoder/config.json

@@ -19,7 +19,7 @@
   "num_hidden_layers": 23,
   "pad_token_id": 1,
   "projection_dim": 512,
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.27.4",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:681c555376658c81dc273f2d737a2aeb23ddb6d1d8e5b3a7064636d359a22668
-size 680821096
+oid sha256:1e4aa519f64dc6386f88221a66c106a09fa027b47a20cc0e126687695f2a6669
+size 1361597016

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
-size 167335342
+oid sha256:2aa1f43011b553a4cba7f37456465cdbd48aab7b54b9348b890e8058ea7683ec
+size 334643268