---
job: extension
config:
  # this name will be the folder and filename name
  name: "my_first_qwen_image_lora_v1"
  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
      # Trigger words will not work when caching text embeddings
#      trigger_word: "p3r5on"
      network:
        type: "lora"
        linear: 16
        linear_alpha: 16
      save:
        dtype: float16 # precision to save
        save_every: 250 # save every this many steps
        max_step_saves_to_keep: 4 # how many intermittent saves to keep
      datasets:
        # datasets are a folder of images. captions need to be txt files with the same name as the image
        # for instance image2.jpg and image2.txt. Only jpg, jpeg, and png are supported currently
        # images will automatically be resized and bucketed into the resolution specified
        # on windows, escape back slashes with another backslash so
        # "C:\\path\\to\\images\\folder"
        - folder_path: "/path/to/images/folder"
          caption_ext: "txt"
          # default_caption: "a person" # if caching text embeddings, if you dont have captions, this will get cached
          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 have a large dataset
          # if you OOM, 1024 may be too much, but should work
          resolution: [ 512, 768, 1024 ]  # qwen image enjoys multiple resolutions
      train:
        batch_size: 1
        # caching text embeddings is required for 24GB
        cache_text_embeddings: true
        
        steps: 2000  # total number of steps to train 500 - 4000 is a good range
        gradient_accumulation: 1
        train_unet: true
        train_text_encoder: false  # probably won't work with qwen image
        gradient_checkpointing: true  # need the on unless you have a ton of vram
        noise_scheduler: "flowmatch" # for training only
        optimizer: "adamw8bit"
        lr: 1e-4
        # uncomment this to skip the pre training sample
#        skip_first_sample: true
        # uncomment to completely disable sampling
#        disable_sampling: true
        dtype: bf16
      model:
        # huggingface model name or path
        name_or_path: "Qwen/Qwen-Image"
        arch: "qwen_image"
        quantize: true
        # qtype_te: "qfloat8" Default float8 qquantization
        # to use the ARA use the | pipe to point to hf path, or a local path if you have one.
        # 3bit is required for 24GB
        qtype: "uint3|ostris/accuracy_recovery_adapters/qwen_image_torchao_uint3.safetensors"
        quantize_te: true
        qtype_te: "qfloat8"
        low_vram: true
      sample:
        sampler: "flowmatch" # must match train.noise_scheduler
        sample_every: 250 # sample every this many steps
        width: 1024
        height: 1024
        prompts:
          # you can add [trigger] to the prompts here and it will be replaced with the trigger word
          # - "[trigger] holding a sign that says 'I LOVE PROMPTS!'"\ 
          - "woman with red hair, playing chess at the park, bomb going off in the background"
          - "a woman holding a coffee cup, in a beanie, sitting at a cafe"
          - "a horse is a DJ at a night club, fish eye lens, smoke machine, lazer lights, holding a martini"
          - "a man showing off his cool new t shirt at the beach, a shark is jumping out of the water in the background"
          - "a bear building a log cabin in the snow covered mountains"
          - "woman playing the guitar, on stage, singing a song, laser lights, punk rocker"
          - "hipster man with a beard, building a chair, in a wood shop"
          - "photo of a man, white background, medium shot, modeling clothing, studio lighting, white backdrop"
          - "a man holding a sign that says, 'this is a sign'"
          - "a bulldog, in a post apocalyptic world, with a shotgun, in a leather jacket, in a desert, with a motorcycle"
        neg: ""
        seed: 42
        walk_seed: true
        guidance_scale: 3
        sample_steps: 25
# you can add any additional meta info here. [name] is replaced with config name at top
meta:
  name: "[name]"
  version: '1.0'