Upload folder using huggingface_hub

controlnet/config.json

@@ -0,0 +1,47 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.15.0",
+  "_name_or_path": "thibaud/controlnet-sd21-depth-diffusers",
+  "act_fn": "silu",
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 1024,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_time_scale_shift": "default",
+  "upcast_attention": true,
+  "use_linear_projection": true
+}

controlnet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:601f2cab03cac15d2a7f63f2c92a3f1fe3f1659016a89d028bf908c33ea2c454
+size 728594745

feature_extractor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

log_loss.csv

@@ -0,0 +1 @@
+epoch,step,global_step,loss_total,loss_sd,loss_kd_output,loss_kd_feat,lr,lamb_sd,lamb_kd_output,lamb_kd_feat

logs/text2image-fine-tune/1723365390.529287/events.out.tfevents.1723365390.c3f27f3fcda3.14704.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14c0c0cadef788c82522b7e995241513c6352bd6320f4dd18ee868401ad2b98f
+size 2463

logs/text2image-fine-tune/1723365390.5334532/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: fp16
+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/train
+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/1723366020.4606588/events.out.tfevents.1723366020.c3f27f3fcda3.17346.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0d2623bf2d945832aa053dfe8babf60b4d9cf3ab854ff3f796683debe90d9ed
+size 2463

logs/text2image-fine-tune/1723366020.465218/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: fp16
+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/train
+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.1723365381.c3f27f3fcda3.14704.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73394283442b68c035f71fa250471bbd2ac5752b7a90f583129e68e4ebda81ed
+size 88

logs/text2image-fine-tune/events.out.tfevents.1723366011.c3f27f3fcda3.17346.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38896dc2d8882a9f419f685f8e32aea70bf3d9cd2026404bba90801b645508ef
+size 88

model_index.json

@@ -0,0 +1,37 @@
+{
+  "_class_name": "StableDiffusionControlNetPipeline",
+  "_diffusers_version": "0.15.0",
+  "controlnet": [
+    "diffusers",
+    "ControlNetModel"
+  ],
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "requires_safety_checker": false,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.15.0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float16",
+  "transformers_version": "4.27.4",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ee67f13de719e6c72334b4a066852d43dde1b050b11b78983f12f5f8d5553d8
+size 680898977

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,58 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.15.0",
+  "act_fn": "silu",
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "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,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": 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_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_type": "positional",
+  "timestep_post_act": null,
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": true
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140a4d0f0758ee78b3b8de58eb522299462840c0c05b5ada968f844652347b1b
+size 1307450869

vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.15.0",
+  "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 768,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:354e94ceb8cebe720c40510b94599b388a8eda407e7694a4db1ed8dc4f678538
+size 167404145