Upload folder using huggingface_hub

controlnet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1420180f584edeb3aa28c9dab7d4bef4317b71bfbe7e3c8cd5d977708fe7f507
-size 1445157120
+oid sha256:8199ce735834688ef40e758d7e7086b69361da4bb41dbcbbdd90b0172fcae69a
+size 722598648

feature_extractor/preprocessor_config.json

@@ -1,21 +1,4 @@
 {
-  "_valid_processor_keys": [
-    "images",
-    "do_resize",
-    "size",
-    "resample",
-    "do_center_crop",
-    "crop_size",
-    "do_rescale",
-    "rescale_factor",
-    "do_normalize",
-    "image_mean",
-    "image_std",
-    "do_convert_rgb",
-    "return_tensors",
-    "data_format",
-    "input_data_format"
-  ],
   "crop_size": {
     "height": 224,
     "width": 224
@@ -25,6 +8,7 @@
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
   "image_mean": [
     0.48145466,
     0.4578275,

logs/text2image-fine-tune/1717821007.8383396/events.out.tfevents.1717821007.0f914b078d44.4636.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:319a1493b00763d4a312319e60271fc5191530e75b74d632d823ec2b49f98d2f
+size 2436

logs/text2image-fine-tune/1717821007.8419707/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: 5
+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/toy_bk_small
+pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
+random_flip: true
+report_to: all
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 1234
+train_batch_size: 2
+train_data_dir: ./data/laion_aes/preprocessed_11k
+unet_config_name: bk_small
+unet_config_path: ./src/unet_config
+use_8bit_adam: false
+use_copy_weight_from_teacher: true
+use_ema: true
+valid_prompt: a golden vase with different flowers
+valid_steps: 5

logs/text2image-fine-tune/events.out.tfevents.1717820999.0f914b078d44.4636.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f4bea260be0f9aa57f01594a4a8c829bd39279bba9dbf02c5c260cc5ea07935
+size 88

model_index.json

@@ -1,7 +1,11 @@
 {
-  "_class_name": "StableDiffusionPipeline",
+  "_class_name": "StableDiffusionControlNetPipeline",
   "_diffusers_version": "0.28.2",
-  "_name_or_path": "kmpartner/bk-test",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "controlnet": [
+    "diffusers",
+    "ControlNetModel"
+  ],
   "feature_extractor": [
     "transformers",
     "CLIPImageProcessor"
@@ -33,6 +37,6 @@
   ],
   "vae": [
     "diffusers",
-    "AutoencoderTiny"
+    "AutoencoderKL"
   ]
 }

safety_checker/config.json

@@ -1,6 +1,6 @@
 {
-  "_commit_hash": "858c800d0667613dc2f87f859e4843a95f8120cc",
-  "_name_or_path": "/root/.cache/huggingface/hub/models--kmpartner--bk-test/snapshots/858c800d0667613dc2f87f859e4843a95f8120cc/safety_checker",
+  "_commit_hash": "133a221b8aa7292a167afc5127cb63fb5005638b",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/safety_checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
   ],
@@ -86,7 +86,7 @@
     "vocab_size": 49408
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.41.2",
+  "transformers_version": null,
   "vision_config": {
     "_name_or_path": "",
     "add_cross_attention": false,

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "kmpartner/bk-test",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -18,8 +18,8 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 1,
-  "projection_dim": 768,
-  "torch_dtype": "float32",
+  "projection_dim": 512,
+  "torch_dtype": "float16",
   "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 sha256:71c10601ece1342fede0300fb88db71c09ece8be491b71875d18b9799a5e6c15
-size 492265880
+oid sha256:77795e2023adcf39bc29a884661950380bd093cf0750a966d473d1718dc9ef4e
+size 246144864

tokenizer/tokenizer_config.json

@@ -1,23 +1,5 @@
 {
   "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "49406": {
-      "content": "<|startoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "49407": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
   "bos_token": {
     "__type": "AddedToken",
     "content": "<|startoftext|>",
@@ -26,7 +8,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
   "eos_token": {
     "__type": "AddedToken",
@@ -39,7 +20,7 @@
   "errors": "replace",
   "model_max_length": 77,
   "pad_token": "<|endoftext|>",
-  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--kmpartner--bk-test/snapshots/858c800d0667613dc2f87f859e4843a95f8120cc/tokenizer/special_tokens_map.json",
+  "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",
   "unk_token": {
     "__type": "AddedToken",

unet/config.json

@@ -10,6 +10,7 @@
   "block_out_channels": [
     320,
     640,
+    1280,
     1280
   ],
   "center_input_sample": false,
@@ -22,7 +23,8 @@
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D"
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
   ],
   "downsample_padding": 1,
   "dropout": 0.0,
@@ -55,6 +57,7 @@
   "timestep_post_act": null,
   "transformer_layers_per_block": 1,
   "up_block_types": [
+    "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e7506c2f819d897010902927b8f204679374d7610e0cb45cbc37489fb007ee9
-size 1293583616
+oid sha256:a9e9d51e8c2e414f5e4ef31164276798dcad2761559e290ed2c80d9900fe7c77
+size 1929435608

vae/config.json

@@ -1,45 +1,34 @@
 {
-  "_class_name": "AutoencoderTiny",
+  "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.28.2",
-  "_name_or_path": "madebyollin/taesd",
-  "act_fn": "relu",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "act_fn": "silu",
   "block_out_channels": [
-    64,
-    64,
-    64,
-    64
+    128,
+    256,
+    512,
+    512
   ],
-  "decoder_block_out_channels": [
-    64,
-    64,
-    64,
-    64
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
   ],
-  "encoder_block_out_channels": [
-    64,
-    64,
-    64,
-    64
-  ],
-  "force_upcast": false,
+  "force_upcast": true,
   "in_channels": 3,
   "latent_channels": 4,
-  "latent_magnitude": 3,
-  "latent_shift": 0.5,
-  "num_decoder_blocks": [
-    3,
-    3,
-    3,
-    1
-  ],
-  "num_encoder_blocks": [
-    1,
-    3,
-    3,
-    3
-  ],
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
   "out_channels": 3,
-  "scaling_factor": 1.0,
-  "upsample_fn": "nearest",
-  "upsampling_scaling_factor": 2
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
 }

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7956d561b1efbd861ad9b03fd8f01510f9e87eddc07bdfd20837009433f6ee5
-size 9793292
+oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
+size 167335342