Fix vae path validation

Author: bmaltais

.gitignore

@@ -50,4 +50,5 @@ dataset/**
 !dataset/**/.gitkeep
 models
 data
-config.toml
+config.toml
+sd-scripts

README.md

@@ -382,11 +382,13 @@ The documentation in this section will be moved to a separate document later.
 
 ## Change History
 
-### 2024/03/20 (v23.0.15)
+### 2024/03/21 (v23.0.15)
 
 - Add support for toml dataset configuration fole to all trainers
 - Add new setup menu option to install Triton 2.1.0 for Windows
 - Add support for LyCORIS BOFT and DoRA and QLyCORIS options for LoHA, LoKr and LoCon
+- Fix issue with vae path validation
+- Other fixes
 
 ### 2024/03/19 (v23.0.14)
 

kohya_gui/class_advanced_training.py

@@ -39,8 +39,7 @@ def __init__(
             headless (bool): Run in headless mode without GUI.
             finetuning (bool): Enable model fine-tuning.
             training_type (str): The type of training to be performed.
-            default_vae_dir (str): Default directory for VAE models.
-            default_output_dir (str): Default directory for output files.
+            config (dict): Configuration options for the training process.
         """
         self.headless = headless
         self.finetuning = finetuning
@@ -369,10 +368,6 @@ def list_state_dirs(path):
                 outputs=self.resume,
                 show_progress=False,
             )
-            # self.max_train_epochs = gr.Textbox(
-            #     label='Max train epoch',
-            #     placeholder='(Optional) Override number of epoch',
-            # )
             self.max_data_loader_n_workers = gr.Textbox(
                 label="Max num workers for DataLoader",
                 placeholder="(Optional) Override number of epoch. Default: 8",

kohya_gui/common_gui.py

@@ -1775,6 +1775,13 @@ def validate_path(
         if key in ["output_dir", "logging_dir"]:
             if not validate_path(value, key, create_if_missing=True):
                 return False
+        elif key in ["vae"]:
+            # Check if it matches the Hugging Face model pattern
+            if re.match(r"^[\w-]+\/[\w-]+$", value):
+                log.info("Checking vae... huggingface.co model, skipping validation")
+            else:
+                if not validate_path(value, key):
+                    return False
         else:
             if key not in ["pretrained_model_name_or_path"]:
                 if not validate_path(value, key):

test/config/dreambooth-AdamW8bit.json

@@ -1,11 +1,6 @@
 {
-  "LoRA_type": "Standard",
-  "LyCORIS_preset": "full",
   "adaptive_noise_scale": 0,
   "additional_parameters": "",
-  "block_alphas": "",
-  "block_dims": "",
-  "block_lr_zero_threshold": "",
   "bucket_no_upscale": true,
   "bucket_reso_steps": 64,
   "cache_latents": true,
@@ -15,58 +10,45 @@
   "caption_extension": "",
   "clip_skip": 2,
   "color_aug": false,
-  "constrain": 0.0,
-  "conv_alpha": 1,
-  "conv_block_alphas": "",
-  "conv_block_dims": "",
-  "conv_dim": 1,
-  "debiased_estimation_loss": false,
-  "decompose_both": false,
-  "dim_from_weights": false,
-  "down_lr_weight": "",
+  "dataset_config": "",
   "enable_bucket": true,
   "epoch": 1,
-  "factor": -1,
   "flip_aug": false,
-  "fp8_base": false,
   "full_bf16": false,
   "full_fp16": false,
   "gpu_ids": "",
   "gradient_accumulation_steps": 1,
   "gradient_checkpointing": false,
   "keep_tokens": "0",
   "learning_rate": 5e-05,
+  "learning_rate_te": 1e-05,
+  "learning_rate_te1": 1e-05,
+  "learning_rate_te2": 1e-05,
   "log_tracker_config": "",
   "log_tracker_name": "",
   "logging_dir": "./test/logs",
-  "lora_network_weights": "",
   "lr_scheduler": "constant",
   "lr_scheduler_args": "",
   "lr_scheduler_num_cycles": "",
   "lr_scheduler_power": "",
   "lr_warmup": 0,
   "max_bucket_reso": 2048,
   "max_data_loader_n_workers": "0",
-  "max_grad_norm": 1,
   "max_resolution": "512,512",
   "max_timestep": 1000,
   "max_token_length": "75",
   "max_train_epochs": "",
   "max_train_steps": "",
   "mem_eff_attn": false,
-  "mid_lr_weight": "",
   "min_bucket_reso": 256,
   "min_snr_gamma": 0,
   "min_timestep": 0,
   "mixed_precision": "bf16",
   "model_list": "runwayml/stable-diffusion-v1-5",
-  "module_dropout": 0,
   "multi_gpu": false,
   "multires_noise_discount": 0,
   "multires_noise_iterations": 0,
-  "network_alpha": 1,
-  "network_dim": 8,
-  "network_dropout": 0,
+  "no_token_padding": false,
   "noise_offset": 0.05,
   "noise_offset_type": "Original",
   "num_cpu_threads_per_process": 2,
@@ -80,10 +62,7 @@
   "pretrained_model_name_or_path": "runwayml/stable-diffusion-v1-5",
   "prior_loss_weight": 1.0,
   "random_crop": false,
-  "rank_dropout": 0,
-  "rank_dropout_scale": false,
   "reg_data_dir": "",
-  "rescaled": false,
   "resume": "",
   "sample_every_n_epochs": 0,
   "sample_every_n_steps": 25,
@@ -97,30 +76,17 @@
   "save_precision": "fp16",
   "save_state": false,
   "scale_v_pred_loss_like_noise_pred": false,
-  "scale_weight_norms": 0,
   "sdxl": false,
-  "sdxl_cache_text_encoder_outputs": false,
-  "sdxl_no_half_vae": true,
   "seed": "1234",
   "shuffle_caption": false,
   "stop_text_encoder_training": 0,
-  "text_encoder_lr": 0.0,
   "train_batch_size": 4,
   "train_data_dir": "./test/img",
-  "train_norm": false,
-  "train_on_input": true,
-  "training_comment": "",
-  "unet_lr": 0.0,
-  "unit": 1,
-  "up_lr_weight": "",
-  "use_cp": false,
-  "use_scalar": false,
-  "use_tucker": false,
   "use_wandb": false,
   "v2": false,
   "v_parameterization": false,
   "v_pred_like_loss": 0,
-  "vae": "",
+  "vae": "stabilityai/vae",
   "vae_batch_size": 0,
   "wandb_api_key": "",
   "wandb_run_name": "",