| { | |
| "__version": 2, | |
| "training_method": "LORA", | |
| "model_type": "STABLE_CASCADE_1", | |
| "debug_mode": false, | |
| "debug_dir": "debug", | |
| "workspace_dir": "workspace/run", | |
| "cache_dir": "workspace-cache/run", | |
| "tensorboard": true, | |
| "tensorboard_expose": false, | |
| "continue_last_backup": false, | |
| "include_train_config": "NONE", | |
| "base_model_name": "stabilityai/stable-cascade-prior", | |
| "weight_dtype": "BFLOAT_16", | |
| "output_dtype": "BFLOAT_16", | |
| "output_model_format": "SAFETENSORS", | |
| "output_model_destination": "./workspace/run/save/ak31-1716-50.safetensors", | |
| "gradient_checkpointing": true, | |
| "concept_file_name": "training_concepts/concepts.json", | |
| "concepts": null, | |
| "circular_mask_generation": false, | |
| "random_rotate_and_crop": false, | |
| "aspect_ratio_bucketing": true, | |
| "latent_caching": true, | |
| "clear_cache_before_training": true, | |
| "learning_rate_scheduler": "CONSTANT", | |
| "learning_rate": 1.0, | |
| "learning_rate_warmup_steps": 200, | |
| "learning_rate_cycles": 1, | |
| "epochs": 50, | |
| "batch_size": 1, | |
| "gradient_accumulation_steps": 1, | |
| "ema": "OFF", | |
| "ema_decay": 0.999, | |
| "ema_update_step_interval": 5, | |
| "train_device": "cuda", | |
| "temp_device": "cpu", | |
| "train_dtype": "FLOAT_16", | |
| "fallback_train_dtype": "BFLOAT_16", | |
| "only_cache": false, | |
| "resolution": "1024", | |
| "attention_mechanism": "XFORMERS", | |
| "align_prop": false, | |
| "align_prop_probability": 0.1, | |
| "align_prop_loss": "AESTHETIC", | |
| "align_prop_weight": 0.01, | |
| "align_prop_steps": 20, | |
| "align_prop_truncate_steps": 0.5, | |
| "align_prop_cfg_scale": 7.0, | |
| "mse_strength": 1.0, | |
| "mae_strength": 0.0, | |
| "vb_loss_strength": 1.0, | |
| "min_snr_gamma": 3.0, | |
| "loss_scaler": "NONE", | |
| "learning_rate_scaler": "NONE", | |
| "offset_noise_weight": 0.06, | |
| "perturbation_noise_weight": 0.0, | |
| "rescale_noise_scheduler_to_zero_terminal_snr": false, | |
| "force_v_prediction": false, | |
| "force_epsilon_prediction": false, | |
| "min_noising_strength": 0.0, | |
| "max_noising_strength": 1.0, | |
| "noising_weight": 0.0, | |
| "noising_bias": 0.5, | |
| "unet": { | |
| "__version": 0, | |
| "model_name": "", | |
| "train": true, | |
| "stop_training_after": 0, | |
| "stop_training_after_unit": "NEVER", | |
| "learning_rate": null, | |
| "weight_dtype": "NONE" | |
| }, | |
| "prior": { | |
| "__version": 0, | |
| "model_name": "", | |
| "train": true, | |
| "stop_training_after": 0, | |
| "stop_training_after_unit": "NEVER", | |
| "learning_rate": null, | |
| "weight_dtype": "NONE" | |
| }, | |
| "text_encoder": { | |
| "__version": 0, | |
| "model_name": "", | |
| "train": true, | |
| "stop_training_after": 50, | |
| "stop_training_after_unit": "EPOCH", | |
| "learning_rate": null, | |
| "weight_dtype": "NONE" | |
| }, | |
| "text_encoder_layer_skip": 0, | |
| "text_encoder_2": { | |
| "__version": 0, | |
| "model_name": "", | |
| "train": true, | |
| "stop_training_after": 30, | |
| "stop_training_after_unit": "EPOCH", | |
| "learning_rate": null, | |
| "weight_dtype": "NONE" | |
| }, | |
| "text_encoder_2_layer_skip": 0, | |
| "vae": { | |
| "__version": 0, | |
| "model_name": "", | |
| "train": true, | |
| "stop_training_after": null, | |
| "stop_training_after_unit": "NEVER", | |
| "learning_rate": null, | |
| "weight_dtype": "FLOAT_32" | |
| }, | |
| "effnet_encoder": { | |
| "__version": 0, | |
| "model_name": "./models/effnet_encoder.safetensors", | |
| "train": true, | |
| "stop_training_after": null, | |
| "stop_training_after_unit": "NEVER", | |
| "learning_rate": null, | |
| "weight_dtype": "FLOAT_16" | |
| }, | |
| "decoder": { | |
| "__version": 0, | |
| "model_name": "stabilityai/stable-cascade", | |
| "train": true, | |
| "stop_training_after": null, | |
| "stop_training_after_unit": "NEVER", | |
| "learning_rate": null, | |
| "weight_dtype": "FLOAT_16" | |
| }, | |
| "decoder_text_encoder": { | |
| "__version": 0, | |
| "model_name": "", | |
| "train": true, | |
| "stop_training_after": null, | |
| "stop_training_after_unit": "NEVER", | |
| "learning_rate": null, | |
| "weight_dtype": "NONE" | |
| }, | |
| "decoder_vqgan": { | |
| "__version": 0, | |
| "model_name": "", | |
| "train": true, | |
| "stop_training_after": null, | |
| "stop_training_after_unit": "NEVER", | |
| "learning_rate": null, | |
| "weight_dtype": "NONE" | |
| }, | |
| "masked_training": false, | |
| "unmasked_probability": 0.1, | |
| "unmasked_weight": 0.1, | |
| "normalize_masked_area_loss": false, | |
| "embeddings": [ | |
| { | |
| "__version": 0, | |
| "model_name": "", | |
| "train": true, | |
| "stop_training_after": null, | |
| "stop_training_after_unit": "NEVER", | |
| "token_count": 1, | |
| "initial_embedding_text": "*", | |
| "weight_dtype": "FLOAT_32" | |
| } | |
| ], | |
| "embedding_weight_dtype": "FLOAT_32", | |
| "lora_model_name": "", | |
| "lora_rank": 64, | |
| "lora_alpha": 1.0, | |
| "lora_weight_dtype": "FLOAT_32", | |
| "optimizer": { | |
| "__version": 0, | |
| "optimizer": "PRODIGY", | |
| "adam_w_mode": false, | |
| "alpha": null, | |
| "amsgrad": false, | |
| "beta1": 0.9, | |
| "beta2": 0.999, | |
| "beta3": null, | |
| "bias_correction": false, | |
| "block_wise": false, | |
| "capturable": false, | |
| "centered": false, | |
| "clip_threshold": null, | |
| "d0": 1e-06, | |
| "d_coef": 1.0, | |
| "dampening": null, | |
| "decay_rate": null, | |
| "decouple": true, | |
| "differentiable": false, | |
| "eps": 1e-08, | |
| "eps2": null, | |
| "foreach": false, | |
| "fsdp_in_use": false, | |
| "fused": false, | |
| "growth_rate": "inf", | |
| "initial_accumulator_value": null, | |
| "is_paged": false, | |
| "log_every": null, | |
| "lr_decay": null, | |
| "max_unorm": null, | |
| "maximize": false, | |
| "min_8bit_size": null, | |
| "momentum": null, | |
| "nesterov": false, | |
| "no_prox": false, | |
| "optim_bits": null, | |
| "percentile_clipping": null, | |
| "relative_step": false, | |
| "safeguard_warmup": true, | |
| "scale_parameter": false, | |
| "use_bias_correction": true, | |
| "use_triton": false, | |
| "warmup_init": false, | |
| "weight_decay": 0.0 | |
| }, | |
| "optimizer_defaults": { | |
| "ADAFACTOR": { | |
| "__version": 0, | |
| "optimizer": "ADAFACTOR", | |
| "adam_w_mode": false, | |
| "alpha": null, | |
| "amsgrad": false, | |
| "beta1": null, | |
| "beta2": null, | |
| "beta3": null, | |
| "bias_correction": false, | |
| "block_wise": false, | |
| "capturable": false, | |
| "centered": false, | |
| "clip_threshold": 1.0, | |
| "d0": null, | |
| "d_coef": null, | |
| "dampening": null, | |
| "decay_rate": -0.8, | |
| "decouple": false, | |
| "differentiable": false, | |
| "eps": 1e-30, | |
| "eps2": 0.001, | |
| "foreach": false, | |
| "fsdp_in_use": false, | |
| "fused": false, | |
| "growth_rate": null, | |
| "initial_accumulator_value": null, | |
| "is_paged": false, | |
| "log_every": null, | |
| "lr_decay": null, | |
| "max_unorm": null, | |
| "maximize": false, | |
| "min_8bit_size": null, | |
| "momentum": null, | |
| "nesterov": false, | |
| "no_prox": false, | |
| "optim_bits": null, | |
| "percentile_clipping": null, | |
| "relative_step": false, | |
| "safeguard_warmup": false, | |
| "scale_parameter": false, | |
| "use_bias_correction": false, | |
| "use_triton": false, | |
| "warmup_init": false, | |
| "weight_decay": 0.0 | |
| }, | |
| "PRODIGY": { | |
| "__version": 0, | |
| "optimizer": "PRODIGY", | |
| "adam_w_mode": false, | |
| "alpha": null, | |
| "amsgrad": false, | |
| "beta1": 0.9, | |
| "beta2": 0.999, | |
| "beta3": null, | |
| "bias_correction": false, | |
| "block_wise": false, | |
| "capturable": false, | |
| "centered": false, | |
| "clip_threshold": null, | |
| "d0": 1e-06, | |
| "d_coef": 1.0, | |
| "dampening": null, | |
| "decay_rate": null, | |
| "decouple": true, | |
| "differentiable": false, | |
| "eps": 1e-08, | |
| "eps2": null, | |
| "foreach": false, | |
| "fsdp_in_use": false, | |
| "fused": false, | |
| "growth_rate": "inf", | |
| "initial_accumulator_value": null, | |
| "is_paged": false, | |
| "log_every": null, | |
| "lr_decay": null, | |
| "max_unorm": null, | |
| "maximize": false, | |
| "min_8bit_size": null, | |
| "momentum": null, | |
| "nesterov": false, | |
| "no_prox": false, | |
| "optim_bits": null, | |
| "percentile_clipping": null, | |
| "relative_step": false, | |
| "safeguard_warmup": true, | |
| "scale_parameter": false, | |
| "use_bias_correction": true, | |
| "use_triton": false, | |
| "warmup_init": false, | |
| "weight_decay": 0.0 | |
| } | |
| }, | |
| "sample_definition_file_name": "training_samples/samples.json", | |
| "samples": null, | |
| "sample_after": 10, | |
| "sample_after_unit": "MINUTE", | |
| "sample_image_format": "JPG", | |
| "samples_to_tensorboard": true, | |
| "non_ema_sampling": true, | |
| "backup_after": 30, | |
| "backup_after_unit": "MINUTE", | |
| "rolling_backup": false, | |
| "rolling_backup_count": 3, | |
| "backup_before_save": true, | |
| "save_after": 4, | |
| "save_after_unit": "EPOCH" | |
| } |