| job: extension |
| config: |
| name: szn_zimage_turbo_lora |
| process: |
| - type: diffusion_trainer |
| training_folder: /out |
| sqlite_db_path: ./aitk_db.db |
| device: cuda |
| performance_log_every: 10 |
| network: |
| type: lora |
| linear: 32 |
| linear_alpha: 32 |
| conv: 16 |
| conv_alpha: 16 |
| lokr_full_rank: true |
| lokr_factor: -1 |
| network_kwargs: |
| ignore_if_contains: [] |
| save: |
| dtype: bf16 |
| save_every: 500 |
| max_step_saves_to_keep: 10 |
| save_format: diffusers |
| push_to_hub: false |
| datasets: |
| - folder_path: /Femboy dataset |
| mask_path: null |
| mask_min_value: 0.1 |
| default_caption: '' |
| caption_ext: txt |
| caption_dropout_rate: 0.05 |
| cache_latents_to_disk: false |
| is_reg: false |
| network_weight: 1 |
| resolution: |
| - 1024 |
| controls: [] |
| shrink_video_to_frames: true |
| num_frames: 1 |
| do_i2v: true |
| flip_x: false |
| flip_y: false |
| train: |
| batch_size: 1 |
| bypass_guidance_embedding: false |
| steps: 5000 |
| gradient_accumulation: 1 |
| train_unet: true |
| train_text_encoder: false |
| gradient_checkpointing: false |
| noise_scheduler: flowmatch |
| optimizer: adamw8bit |
| timestep_type: weighted |
| content_or_style: balanced |
| optimizer_params: |
| weight_decay: 0.0001 |
| unload_text_encoder: false |
| cache_text_embeddings: true |
| lr: 0.0001 |
| ema_config: |
| use_ema: false |
| ema_decay: 0.99 |
| skip_first_sample: true |
| force_first_sample: false |
| disable_sampling: false |
| dtype: bf16 |
| diff_output_preservation: false |
| diff_output_preservation_multiplier: 1 |
| diff_output_preservation_class: person |
| switch_boundary_every: 1 |
| loss_type: mse |
| do_differential_guidance: true |
| differential_guidance_scale: 3 |
| model: |
| name_or_path: Tongyi-MAI/Z-Image-Turbo |
| quantize: false |
| qtype: qfloat8 |
| quantize_te: false |
| qtype_te: qfloat8 |
| arch: zimage:turbo |
| low_vram: false |
| model_kwargs: {} |
| layer_offloading: false |
| layer_offloading_text_encoder_percent: 1 |
| layer_offloading_transformer_percent: 1 |
| assistant_lora_path: ostris/zimage_turbo_training_adapter/zimage_turbo_training_adapter_v2.safetensors |
| sample: |
| sampler: flowmatch |
| sample_every: 500 |
| width: 896 |
| height: 1152 |
| samples: |
| - prompt: Photo of a ohwx woman taking a selfie in front of a large mirror, |
| wearing a tight, form-fitting beige dress with thin straps and a deep V-neckline. |
| She has a fair complexion, short curly hair, and is wearing a pearl necklace. |
| She is standing in a modern, minimalist living room with a wooden floor, |
| a gray sofa, and a potted plant in the background. The lighting is soft |
| and natural, creating a warm and inviting atmosphere. The ohwx woman is |
| holding a black iPhone in her right hand, taking the picture. The image |
| is high quality and has a professional, polished look. |
| - prompt: a ohwx woman holding a coffee cup, in a beanie, sitting at a cafe |
| neg: '' |
| seed: 42 |
| walk_seed: true |
| guidance_scale: 1 |
| sample_steps: 8 |
| num_frames: 1 |
| fps: 1 |
| meta: |
| name: szn_zimage_turbo_lora |
| version: '1.0' |
|
|
