| job: "extension" | |
| config: | |
| name: "my_first_lora_v1" | |
| process: | |
| - type: "diffusion_trainer" | |
| training_folder: "/app/ai-toolkit/output" | |
| sqlite_db_path: "./aitk_db.db" | |
| device: "cuda" | |
| trigger_word: "TRIGGER_WORD_HERE" | |
| 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: 250 | |
| max_step_saves_to_keep: 4 | |
| save_format: "diffusers" | |
| push_to_hub: false | |
| datasets: | |
| - folder_path: "/path/to/images/folder" | |
| 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: | |
| - 512 | |
| - 768 | |
| - 1024 | |
| controls: [] | |
| shrink_video_to_frames: true | |
| num_frames: 1 | |
| flip_x: false | |
| flip_y: false | |
| num_repeats: 1 | |
| control_path_1: null | |
| control_path_2: null | |
| control_path_3: null | |
| train: | |
| batch_size: 1 | |
| bypass_guidance_embedding: false | |
| steps: 3000 | |
| gradient_accumulation: 1 | |
| train_unet: true | |
| train_text_encoder: false | |
| gradient_checkpointing: true | |
| 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: false | |
| lr: 0.0001 | |
| ema_config: | |
| use_ema: false | |
| ema_decay: 0.99 | |
| skip_first_sample: false | |
| 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" | |
| logging: | |
| log_every: 1 | |
| use_ui_logger: true | |
| model: | |
| name_or_path: "black-forest-labs/FLUX.2-klein-base-9B" | |
| quantize: true | |
| qtype: "qfloat8" | |
| quantize_te: true | |
| qtype_te: "qfloat8" | |
| arch: "flux2_klein_9b" | |
| low_vram: true | |
| model_kwargs: | |
| match_target_res: false | |
| layer_offloading: false | |
| layer_offloading_text_encoder_percent: 1 | |
| layer_offloading_transformer_percent: 1 | |
| sample: | |
| sampler: "flowmatch" | |
| sample_every: 250 | |
| width: 1024 | |
| height: 1024 | |
| samples: | |
| - prompt: "woman with red hair, playing chess at the park, bomb going off in the background" | |
| - prompt: "a woman holding a coffee cup, in a beanie, sitting at a cafe" | |
| - prompt: "a horse is a DJ at a night club, fish eye lens, smoke machine, lazer lights, holding a martini" | |
| neg: "" | |
| seed: 42 | |
| walk_seed: true | |
| guidance_scale: 4 | |
| sample_steps: 25 | |
| num_frames: 1 | |
| fps: 1 | |
| meta: | |
| name: "[name]" | |
| version: "1.0" |