Upload folder using huggingface_hub

ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1-20241228-170700.log

@@ -0,0 +1,37 @@
+12/28/2024 05:07:00 PM  Disabling AMP, not recommended.
+12/28/2024 05:07:00 PM  Seed: 756498848
+12/28/2024 05:07:00 PM  unet attention_head_dim: 8
+12/28/2024 05:07:00 PM Inferred yaml: v1-inference.yaml, attn: sd1, prediction_type: epsilon
+12/28/2024 05:07:01 PM  * Using default (DDPM) noise scheduler for training: ddpm
+12/28/2024 05:07:01 PM * Using SDP attention *
+12/28/2024 05:07:01 PM * DLMA resolution 512, buckets: [[512, 512], [576, 448], [448, 576], [640, 384], [384, 640], [768, 320], [320, 768], [896, 256], [256, 896], [1024, 256], [256, 1024]]
+12/28/2024 05:07:01 PM  Preloading images...
+12/28/2024 05:07:06 PM  * Loaded 40 validation images for validation set 'val' from ../data/val
+12/28/2024 05:07:06 PM  * DLMA initialized with 40 images.
+12/28/2024 05:07:06 PM  ** Dataset 'val': 40 batches, num_images: 40, batch_size: 1
+12/28/2024 05:07:06 PM  * Aspect ratio bucket ('default_batch', 768, 320) has only 1 images. At batch size 1 this makes for an effective multiplier of 2.0, which may cause problems. Consider adding 1 or more images with aspect ratio 12:5, or reducing your batch_size.
+12/28/2024 05:07:06 PM  - Plugin plugins.interruptible.InterruptiblePlugin loaded to <class 'plugins.interruptible.InterruptiblePlugin'>
+12/28/2024 05:07:06 PM  * DLMA initialized with 1913 images.
+12/28/2024 05:07:06 PM  ** Dataset 'train': 1913 batches, num_images: 1913, batch_size: 1
+12/28/2024 05:07:06 PM  * unet optimizer: AdamW (686 parameters) *
+12/28/2024 05:07:06 PM     lr: 3e-07, betas: [0.9, 0.99], epsilon: 1e-08, weight_decay: 0.01 *
+12/28/2024 05:07:06 PM  Grad scaler enabled: False (amp mode)
+12/28/2024 05:07:06 PM  Pretraining GPU Memory: 5102 / 24564 MB
+12/28/2024 05:07:06 PM  saving ckpts every 1000000000.0 minutes
+12/28/2024 05:07:06 PM  saving ckpts every 4 epochs
+12/28/2024 05:07:06 PM  unet device: cuda:0, precision: torch.float32, training: True
+12/28/2024 05:07:06 PM  text_encoder device: cuda:0, precision: torch.float32, training: False
+12/28/2024 05:07:06 PM  vae device: cuda:0, precision: torch.float32, training: False
+12/28/2024 05:07:06 PM  scheduler: <class 'diffusers.schedulers.scheduling_ddpm.DDPMScheduler'>
+12/28/2024 05:07:06 PM  Project name: ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1
+12/28/2024 05:07:06 PM  grad_accum: 1
+12/28/2024 05:07:06 PM  batch_size: 1
+12/28/2024 05:07:06 PM  epoch_len: 1913
+12/28/2024 05:45:02 PM  * Saving diffusers model to ../logs/ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1-20241228-170700/ckpts/ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1-ep04-gs07652
+12/28/2024 05:45:04 PM  Saving optimizer state to ../logs/ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1-20241228-170700/ckpts/ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1-ep04-gs07652
+12/28/2024 05:45:08 PM Training complete
+12/28/2024 05:45:08 PM Total training time took 38.03 minutes, total steps: 7652
+12/28/2024 05:45:08 PM Average epoch time: 9.46 minutes
+12/28/2024 05:45:08 PM  ***************************
+12/28/2024 05:45:08 PM  **** Finished training ****
+12/28/2024 05:45:08 PM  ***************************

ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1-20241228-170700_main.json

@@ -0,0 +1,149 @@
+{
+  "config": "ff7r.json",
+  "batch_size": 1,
+  "ckpt_every_n_minutes": 1000000000.0,
+  "clip_grad_norm": 1000000000.0,
+  "clip_skip": 0,
+  "contrastive_learning_batch_ids": [],
+  "contrastive_learning_max_negative_loss": 1.0,
+  "contrastive_learning_negative_loss_scale": 0.1,
+  "everything_contrastive_learning_p": 0.0,
+  "contrastive_learning_delta_loss_method": true,
+  "max_backward_accum": 5,
+  "init_grad_scale": 11500,
+  "auto_decay_steps_multiplier": 1.001,
+  "cond_dropout": 0.02,
+  "data_root": "../data/train",
+  "disable_amp": true,
+  "disable_textenc_training": true,
+  "disable_unet_training": false,
+  "disable_xformers": false,
+  "flip_p": 1.0,
+  "gpuid": 0,
+  "gradient_checkpointing": true,
+  "grad_accum": 1,
+  "logdir": "../logs",
+  "log_step": 25,
+  "lowvram": false,
+  "max_epochs": 4,
+  "notebook": false,
+  "optimizer_config": "optimizer-unet-3e7lin-nowarmup-adamw.json",
+  "plugins": [
+    "plugins.interruptible.InterruptiblePlugin"
+  ],
+  "project_name": "ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1",
+  "resolution": 512,
+  "resume_ckpt": "../logs/ff7r_4e-5cosine_everything-cont-20-20241228-105146/ckpts/ff7r_4e-5cosine_everything-cont-20-ep50-gs16100",
+  "run_name": null,
+  "sample_prompts": "sample_prompts.json",
+  "sample_steps": 666,
+  "save_ckpt_dir": null,
+  "save_ckpts_from_n_epochs": 0,
+  "save_every_n_epochs": 4,
+  "save_optimizer": true,
+  "scale_lr": false,
+  "seed": 756498848,
+  "shuffle_tags": false,
+  "validation_config": "validation.json",
+  "wandb": false,
+  "write_schedule": false,
+  "rated_dataset": false,
+  "rated_dataset_target_dropout_percent": 50,
+  "zero_frequency_noise_ratio": 0.0,
+  "enable_zero_terminal_snr": false,
+  "load_settings_every_epoch": false,
+  "min_snr_gamma": 1.5,
+  "loss_type": "mse_huber",
+  "ema_decay_rate": null,
+  "ema_strength_target": null,
+  "ema_update_interval": null,
+  "ema_device": null,
+  "ema_sample_nonema_model": false,
+  "ema_sample_ema_model": false,
+  "ema_resume_model": null,
+  "no_save_ckpt": true,
+  "no_prepend_last": true,
+  "amp": false,
+  "attn_type": "sdp",
+  "embedding_perturbation": 1.0,
+  "latents_perturbation": 0.0,
+  "log_huber": false,
+  "save_full_precision": false,
+  "timestep_start": 0,
+  "timestep_end": 1000,
+  "train_sampler": "ddpm",
+  "keep_tags": 0,
+  "pyramid_noise_discount": null,
+  "lr": null,
+  "lr_decay_steps": 7659,
+  "lr_scheduler": "constant",
+  "lr_warmup_steps": 153,
+  "no_initial_validation": false,
+  "mix_zero_terminal_snr": null,
+  "match_zero_terminal_snr": null,
+  "debug_invert_min_snr_gamma": false,
+  "batch_share_noise": false,
+  "batch_share_timesteps": false,
+  "teacher": null,
+  "teacher_is_sdxl": false,
+  "teacher_loss_scale": 1,
+  "contrastive_learning_use_l1_loss": false,
+  "contrastive_learning_no_average_negatives": false,
+  "contrastive_learning_save_on_cpu": false,
+  "contrastive_learning_delta_timestep_start": 150,
+  "contrastive_learning_dropout_p": 0,
+  "batch_id_dropout_p": 0,
+  "cond_dropout_noise_p": 0,
+  "jacobian_descent": false,
+  "use_masks": false,
+  "lora": false,
+  "lora_resume": null,
+  "lora_rank": 16,
+  "lora_alpha": 8,
+  "aspects": [
+    [
+      512,
+      512
+    ],
+    [
+      576,
+      448
+    ],
+    [
+      448,
+      576
+    ],
+    [
+      640,
+      384
+    ],
+    [
+      384,
+      640
+    ],
+    [
+      768,
+      320
+    ],
+    [
+      320,
+      768
+    ],
+    [
+      896,
+      256
+    ],
+    [
+      256,
+      896
+    ],
+    [
+      1024,
+      256
+    ],
+    [
+      256,
+      1024
+    ]
+  ]
+}

ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1-20241228-170700_opt.json

@@ -0,0 +1,32 @@
+{
+  "base": {
+    "optimizer": "adamw",
+    "lr": 3e-07,
+    "lr_scheduler": "linear",
+    "lr_decay_steps": 7659,
+    "lr_warmup_steps": 1,
+    "betas": [
+      0.9,
+      0.99
+    ],
+    "epsilon": 1e-08,
+    "weight_decay": 0.01
+  },
+  "text_encoder_overrides": {
+    "optimizer": "adamw",
+    "lr": 1e-06,
+    "lr_scheduler": "linear",
+    "lr_decay_steps": 7659,
+    "lr_warmup_steps": 1,
+    "betas": [
+      0.9,
+      0.99
+    ],
+    "epsilon": 1e-08,
+    "weight_decay": 0.01
+  },
+  "text_encoder_freezing": {
+    "unfreeze_last_n_layers": 2
+  },
+  "apply_grad_scaler_step_tweaks": false
+}

model_index.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.31.0",
+  "_name_or_path": "../logs/ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1-20241228-170700/ckpts/ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1-ep04-gs07652",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "image_encoder": [
+    null,
+    null
+  ],
+  "requires_safety_checker": null,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.31.0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "../logs/ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1-20241228-170700/ckpts/ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1-ep04-gs07652/text_encoder",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+size 246144152

tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "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": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>",
+  "use_fast": false
+}

unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.31.0",
+  "_name_or_path": "../logs/ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1-20241228-170700/ckpts/ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1-ep04-gs07652/unet",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "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": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "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": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a30d8eaa78c527fc9a84265856a8d50a3c6a0b6de670b22b647d2b2d3eb51b6c
+size 1719125304

vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.31.0",
+  "_name_or_path": "../logs/ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1-20241228-170700/ckpts/ff7r_4e-5cosine_everything-cont-20-ep50-3e-7_bs1-ep04-gs07652/vae",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "shift_factor": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
+size 167335342