| |
| seed_everything: 0 |
| torch_hub_dir: ~/.cache/torch/hub |
| huggingface_cache_dir: null |
| trainer: |
| accelerator: auto |
| strategy: ddp_find_unused_parameters_true |
| devices: auto |
| num_nodes: 1 |
| precision: bf16-mixed |
| logger: |
| class_path: lightning.pytorch.loggers.WandbLogger |
| init_args: |
| name: sft_pix512_gan_v8 |
| save_dir: . |
| version: null |
| offline: false |
| dir: null |
| id: null |
| anonymous: null |
| project: universal_flow_JiT_t2i |
| log_model: false |
| experiment: null |
| prefix: '' |
| checkpoint_name: null |
| add_file_policy: mutable |
| entity: null |
| notes: null |
| tags: null |
| config: null |
| config_exclude_keys: null |
| config_include_keys: null |
| allow_val_change: null |
| group: null |
| job_type: null |
| mode: null |
| force: null |
| reinit: null |
| resume: null |
| resume_from: null |
| fork_from: null |
| save_code: null |
| tensorboard: null |
| sync_tensorboard: null |
| monitor_gym: null |
| settings: null |
| callbacks: |
| - class_path: src.callbacks.model_checkpoint.CheckpointHook |
| init_args: |
| dirpath: null |
| filename: null |
| monitor: null |
| verbose: false |
| save_last: true |
| save_top_k: -1 |
| save_on_exception: false |
| save_weights_only: false |
| mode: min |
| auto_insert_metric_name: true |
| every_n_train_steps: 5000 |
| train_time_interval: null |
| every_n_epochs: null |
| save_on_train_epoch_end: null |
| enable_version_counter: true |
| - class_path: src.callbacks.save_images.SaveImagesHook |
| init_args: |
| save_dir: val |
| save_compressed: false |
| fast_dev_run: false |
| max_epochs: null |
| min_epochs: null |
| max_steps: 200000 |
| min_steps: null |
| max_time: null |
| limit_train_batches: null |
| limit_val_batches: null |
| limit_test_batches: null |
| limit_predict_batches: null |
| overfit_batches: 0.0 |
| val_check_interval: 10000 |
| check_val_every_n_epoch: null |
| num_sanity_val_steps: 2 |
| log_every_n_steps: 50 |
| enable_checkpointing: null |
| enable_progress_bar: null |
| enable_model_summary: null |
| accumulate_grad_batches: 1 |
| gradient_clip_val: null |
| gradient_clip_algorithm: null |
| deterministic: null |
| benchmark: null |
| inference_mode: true |
| use_distributed_sampler: false |
| profiler: null |
| detect_anomaly: false |
| barebones: false |
| plugins: |
| - class_path: src.plugins.bd_env.BDEnvironment |
| sync_batchnorm: false |
| reload_dataloaders_every_n_epochs: 0 |
| default_root_dir: ./universal_pix_t2i_workdirs |
| enable_autolog_hparams: true |
| model_registry: null |
| model: |
| vae: |
| class_path: src.models.autoencoder.pixel.PixelAE |
| init_args: |
| scale: 1.0 |
| shift: 0.0 |
| conditioner: |
| class_path: src.models.conditioner.qwen3_text_encoder.Qwen3TextEncoder |
| init_args: |
| weight_path: Qwen/Qwen3-1.7B |
| embed_dim: 2048 |
| max_length: 128 |
| denoiser: |
| class_path: src.models.transformer.JiT_T2I.JiT_T2I |
| init_args: |
| input_size: 512 |
| in_channels: 3 |
| num_groups: 24 |
| hidden_size: 1536 |
| num_blocks: 16 |
| num_text_blocks: 4 |
| patch_size: 16 |
| txt_embed_dim: 2048 |
| txt_max_length: 128 |
| bottleneck_dim: 256 |
| weight_path: null |
| load_ema: false |
| diffusion_trainer: |
| class_path: src.diffusion.flow_matching.training_repa_JiT_LPIPS_DINO_NoiseGating_DMD2_GAN.REPADMD2GANTrainer |
| init_args: |
| scheduler: |
| class_path: src.diffusion.flow_matching.scheduling.LinearScheduler |
| loss_weight_fn: src.diffusion.flow_matching.training_repa_JiT_LPIPS_DINO_NoiseGating.constant |
| feat_loss_weight: 0.5 |
| lognorm_t: true |
| timeshift: 1.0 |
| encoder: |
| class_path: src.models.encoder.DINOv2 |
| init_args: |
| weight_path: ~/.cache/torch/hub/checkpoints/dinov2_vitb14_pretrain.pth |
| base_patch_size: 16 |
| align_layer: 8 |
| proj_denoiser_dim: 1536 |
| proj_hidden_dim: 1536 |
| proj_encoder_dim: 768 |
| P_mean: -0.8 |
| P_std: 0.8 |
| t_eps: 0.05 |
| num_classes: 1000 |
| lpips_weight: 0.1 |
| dino_weight: 0.01 |
| percept_t_threshold: 0.3 |
| noise_scale: 1.0 |
| patch_size: 16 |
| percept_ratio: 1.0 |
| percept_adaptive_step: 0 |
| use_gan_loss: true |
| gan_loss_weight: 0.003 |
| d_fm_loss_weight: 1.0 |
| gan_loss_weight_final: 0.003 |
| decay_start_step: 0 |
| decay_end_step: 0 |
| lr_final_multiplier: 1.0 |
| decay_schedule: constant |
| diffusion_gan: true |
| diffusion_gan_max_timestep: 0.4 |
| gan_start_step: 0 |
| gan_timestep_min: 0.6 |
| gan_timestep_max: 1.0 |
| null_condition_p: 0.1 |
| diffusion_sampler: |
| class_path: src.diffusion.flow_matching.adam_sampling.AdamLMSamplerJiT |
| init_args: |
| order: 2 |
| timeshift: 3.0 |
| guidance_interval_min: 0.0 |
| guidance_interval_max: 1.0 |
| lms_transform_fn: src.diffusion.flow_matching.adam_sampling.nop |
| last_step: null |
| step_fn: src.diffusion.flow_matching.adam_sampling.ode_step_fn |
| scheduler: |
| class_path: src.diffusion.flow_matching.scheduling.LinearScheduler |
| guidance_fn: src.diffusion.base.guidance.simple_guidance_fn |
| num_steps: 25 |
| guidance: 4.0 |
| ema_tracker: |
| class_path: src.callbacks.simple_ema.SimpleEMA |
| init_args: |
| decay: 0.9999 |
| every_n_steps: 1 |
| optimizer: |
| class_path: torch.optim.AdamW |
| init_args: |
| lr: 1.0e-05 |
| betas: |
| - 0.9 |
| - 0.999 |
| eps: 1.0e-08 |
| weight_decay: 0.0 |
| amsgrad: false |
| maximize: false |
| foreach: null |
| capturable: false |
| differentiable: false |
| fused: null |
| lr_scheduler: null |
| eval_original_model: false |
| discriminator: |
| class_path: src.models.discriminator.DenoiserBackboneDiscriminator |
| init_args: |
| backbone: |
| class_path: src.models.transformer.JiT_T2I.JiT_T2I |
| init_args: |
| input_size: 512 |
| in_channels: 3 |
| num_groups: 24 |
| hidden_size: 1536 |
| num_blocks: 16 |
| num_text_blocks: 4 |
| patch_size: 16 |
| txt_embed_dim: 2048 |
| txt_max_length: 128 |
| bottleneck_dim: 256 |
| weight_path: null |
| load_ema: false |
| hidden_size: 1536 |
| head_hidden_size: 1536 |
| head_depth: 2 |
| train_backbone: true |
| backbone_lr_scale: 1.0 |
| d_optimizer: |
| class_path: torch.optim.AdamW |
| init_args: |
| lr: 1.0e-05 |
| betas: |
| - 0.0 |
| - 0.99 |
| eps: 1.0e-08 |
| weight_decay: 0.0 |
| amsgrad: false |
| maximize: false |
| foreach: null |
| capturable: false |
| differentiable: false |
| fused: null |
| d_steps_per_g: 1 |
| g_grad_clip: 1.0 |
| d_grad_clip: 1.0 |
| data: |
| train_dataset: |
| class_path: src.data.dataset.image_txt.ImageText |
| init_args: |
| root: /media/home/lx/sharp/blip/extracted |
| resolution: 512 |
| cache_path: null |
| require_text: true |
| eval_dataset: |
| class_path: src.data.dataset.txt_dir_eval.TxtDirEvalDataset |
| init_args: |
| txt_dir: /media/home/lx/sharp/blip/extracted_new/sa_000201 |
| latent_shape: |
| - 3 |
| - 512 |
| - 512 |
| limit: 50 |
| seed_offset: 0 |
| pred_dataset: |
| class_path: src.data.dataset.txt_dir_eval.TxtDirEvalDataset |
| init_args: |
| txt_dir: /media/home/lx/sharp/blip/extracted_new/sa_000201 |
| latent_shape: |
| - 3 |
| - 512 |
| - 512 |
| limit: 50 |
| seed_offset: 0 |
| train_batch_size: 8 |
| train_num_workers: 8 |
| train_prefetch_factor: 8 |
| eval_batch_size: 32 |
| eval_num_workers: 4 |
| pred_batch_size: 8 |
| pred_num_workers: 1 |
| tags: |
| exp: sft_pix512_gan_v8 |
| ckpt_path: /media/home/lx/PixelGen-fuxian/ck/PixelGen_XXL_T2I.ckpt |
| weights_only: null |
|
|
