| { | |
| "job": "extension", | |
| "config": { | |
| "name": "eLiza", | |
| "process": [ | |
| { | |
| "type": "diffusion_trainer", | |
| "training_folder": "/app/ai-toolkit/output", | |
| "sqlite_db_path": "/app/ai-toolkit/aitk_db.db", | |
| "device": "cuda", | |
| "trigger_word": null, | |
| "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": "/app/ai-toolkit/datasets/esminaia", | |
| "control_path": null, | |
| "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, | |
| "do_i2v": true, | |
| "flip_x": false, | |
| "flip_y": false | |
| } | |
| ], | |
| "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": true, | |
| "lr": 0.0001, | |
| "ema_config": { | |
| "use_ema": false, | |
| "ema_decay": 0.99 | |
| }, | |
| "skip_first_sample": false, | |
| "force_first_sample": false, | |
| "disable_sampling": true, | |
| "dtype": "bf16", | |
| "diff_output_preservation": false, | |
| "diff_output_preservation_multiplier": 1, | |
| "diff_output_preservation_class": "person", | |
| "switch_boundary_every": 1 | |
| }, | |
| "model": { | |
| "name_or_path": "ai-toolkit/Wan2.2-I2V-A14B-Diffusers-bf16", | |
| "quantize": true, | |
| "qtype": "uint4|ostris/accuracy_recovery_adapters/wan22_14b_i2v_torchao_uint4.safetensors", | |
| "quantize_te": true, | |
| "qtype_te": "qfloat8", | |
| "arch": "wan22_14b_i2v", | |
| "low_vram": false, | |
| "model_kwargs": { | |
| "train_high_noise": true, | |
| "train_low_noise": true | |
| } | |
| }, | |
| "sample": { | |
| "sampler": "flowmatch", | |
| "sample_every": 250, | |
| "width": 1024, | |
| "height": 1024, | |
| "samples": [], | |
| "neg": "", | |
| "seed": 42, | |
| "walk_seed": true, | |
| "guidance_scale": 4, | |
| "sample_steps": 25, | |
| "num_frames": 1, | |
| "fps": 1 | |
| } | |
| } | |
| ] | |
| }, | |
| "meta": { | |
| "name": "[name]", | |
| "version": "1.0" | |
| } | |
| } |