| job: extension | |
| config: | |
| # this name will be the folder and filename name 训练结果的目录名和文件名 | |
| name: "sincitymov" | |
| process: | |
| - type: 'sd_trainer' | |
| # root folder to save training sessions/samples/weights | |
| training_folder: "output" | |
| # uncomment to see performance stats in the terminal every N steps | |
| performance_log_every: 1000 | |
| device: cuda:0 | |
| # if a trigger word is specified, it will be added to captions of training data if it does not already exist | |
| # alternatively, in your captions you can add [trigger] and it will be replaced with the trigger word | |
| # 触发词，不设置触发词也可以 | |
| trigger_word: "sincitymov" | |
| network: | |
| type: "lora" | |
| linear: 16 | |
| linear_alpha: 16 | |
| save: | |
| dtype: float16 # precision to save | |
| save_every: 200 # save every this many steps 多少步保存一个模型 | |
| max_step_saves_to_keep: 40 # how many intermittent saves to keep 最多保留多少个模型，可以设置大一点，反正每个文件也就168M | |
| datasets: | |
| - folder_path: "C:/sincitymov" # 数据集所在目录 | |
| caption_ext: "txt" | |
| caption_dropout_rate: 0.05 # will drop out the caption 5% of time | |
| shuffle_tokens: false # shuffle caption order, split by commas | |
| cache_latents_to_disk: true # leave this true unless you know what you're doing | |
| resolution: [ 512, 768, 1024 ] # flux enjoys multiple resolutions | |
| train: | |
| batch_size: 1 | |
| steps: 4000 # total number of steps to train 500 - 4000 is a good range 成与不成通常在1500步以内 | |
| gradient_accumulation_steps: 1 | |
| train_unet: true | |
| train_text_encoder: false # probably won't work with flux | |
| content_or_style: balanced # content, style, balanced | |
| gradient_checkpointing: true # need the on unless you have a ton of vram | |
| noise_scheduler: "flowmatch" # for training only | |
| optimizer: "adamw8bit" | |
| lr: 6e-4 # 学习率，默认是1e-4，就是0.0001如果训练下来发现没学到特征就加大，很快就过拟合了就缩小 | |
| # uncomment this to skip the pre training sample | |
| skip_first_sample: true | |
| # ema will smooth out learning, but could slow it down. Recommended to leave on. | |
| ema_config: | |
| use_ema: true | |
| ema_decay: 0.99 | |
| # will probably need this if gpu supports it for flux, other dtypes may not work correctly | |
| dtype: bf16 | |
| model: | |
| # huggingface model name or path | |
| name_or_path: "black-forest-labs/FLUX.1-dev" | |
| is_flux: true | |
| quantize: true # run 8bit mixed precision | |
| low_vram: true # uncomment this if the GPU is connected to your monitors. It will use less vram to quantize, but is slower. 量化处理模型的时候减少显存占用 | |
| sample: | |
| sampler: "flowmatch" # must match train.noise_scheduler | |
| sample_every: 200 # sample every this many steps 多少步输出一批测试图片，最好和保存模型的步数一致，否则没办法把测试图片和模型直接对应起来 | |
| width: 1024 | |
| height: 1024 | |
| prompts: | |
| # you can add [trigger] to the prompts here and it will be replaced with the trigger word 生成测试图片的提示词 | |
| # - "[trigger] holding a sign that says 'I LOVE PROMPTS!'"\ | |
| - "a woman holding a coffee cup, in a beanie, sitting at a cafe, [trigger]" | |
| - "[trigger], A monochromatic portrait of a woman with striking green eyes and bold red lipstick. She is positioned in a dramatic pose, holding a pistol in her right hand." | |
| - "a bear building a log cabin in the snow covered mountains, [trigger]" | |
| - "photo of a man, white background, medium shot, modeling clothing, studio lighting, white backdrop, [trigger]" | |
| - "a man holding a sign that says, 'this is a sign', [trigger]" | |
| - "a bulldog, in a post apocalyptic world, with a shotgun, in a leather jacket, in a desert, with a motorcycle" | |
| neg: "" # not used on flux 不需要设置负面提示词 | |
| seed: 42 | |
| walk_seed: true | |
| guidance_scale: 4 | |
| sample_steps: 20 | |
| # you can add any additional meta info here. [name] is replaced with config name at top | |
| meta: | |
| name: "[sincitymov]" | |
| version: '1.0' | |