config/examples/train_lora_qwen_image_edit_2509_32gb.yaml

---
job: extension
config:
  # this name will be the folder and filename name
  name: "my_first_qwen_image_edit_2509_lora_v1"
  process:
    - type: 'diffusion_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
      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"
          # can do up to 3 control image folders, file names must match target file names, but aspect/size can be different
          control_path:
            - "/path/to/control/images/folder1"
            - "/path/to/control/images/folder2"
            - "/path/to/control/images/folder3"
          caption_ext: "txt"
          # default_caption: "a person" # if caching text embeddings, if you don't have captions, this will get cached
          caption_dropout_rate: 0.05  # will drop out the caption 5% of time
          resolution: [ 512, 768, 1024 ]  # qwen image enjoys multiple resolutions
          # a trigger word that can be cached with the text embeddings 
          # trigger_word: "optional trigger word"
      train:
        batch_size: 1
        # caching text embeddings is required for 32GB
        cache_text_embeddings: true
        # unload_text_encoder: true
        
        steps: 3000  # total number of steps to train 500 - 4000 is a good range
        gradient_accumulation: 1
        timestep_type: "weighted"
        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-Edit-2509"
        arch: "qwen_image_edit_plus"
        quantize: true
        # to use the ARA use the | pipe to point to hf path, or a local path if you have one.
        # 3bit is required for 32GB
        qtype: "uint3|ostris/accuracy_recovery_adapters/qwen_image_edit_2509_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
        # you can provide up to 3 control images here
        samples:
          - prompt: "Do whatever with Image1 and Image2"
            ctrl_img_1: "/path/to/image1.png"
            ctrl_img_2: "/path/to/image2.png"
            # ctrl_img_3: "/path/to/image3.png"
          - prompt: "Do whatever with Image1 and Image2"
            ctrl_img_1: "/path/to/image1.png"
            ctrl_img_2: "/path/to/image2.png"
            # ctrl_img_3: "/path/to/image3.png"
          - prompt: "Do whatever with Image1 and Image2"
            ctrl_img_1: "/path/to/image1.png"
            ctrl_img_2: "/path/to/image2.png"
            # ctrl_img_3: "/path/to/image3.png"
          - prompt: "Do whatever with Image1 and Image2"
            ctrl_img_1: "/path/to/image1.png"
            ctrl_img_2: "/path/to/image2.png"
            # ctrl_img_3: "/path/to/image3.png"
          - prompt: "Do whatever with Image1 and Image2"
            ctrl_img_1: "/path/to/image1.png"
            ctrl_img_2: "/path/to/image2.png"
            # ctrl_img_3: "/path/to/image3.png"
        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'