DiffSynth-Studio/examples/qwen_image/model_training/train.py

import torch, os, json
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from diffsynth.trainers.utils import DiffusionTrainingModule, ImageDataset, ModelLogger, launch_training_task, qwen_image_parser
from diffsynth.models.lora import QwenImageLoRAConverter
os.environ["TOKENIZERS_PARALLELISM"] = "false"



class QwenImageTrainingModule(DiffusionTrainingModule):
    def __init__(
        self,
        model_paths=None, model_id_with_origin_paths=None,
        tokenizer_path=None,
        trainable_models=None,
        lora_base_model=None, lora_target_modules="", lora_rank=32,
        use_gradient_checkpointing=True,
        use_gradient_checkpointing_offload=False,
        extra_inputs=None,
    ):
        super().__init__()
        # Load models
        model_configs = []
        if model_paths is not None:
            model_paths = json.loads(model_paths)
            model_configs += [ModelConfig(path=path) for path in model_paths]
        if model_id_with_origin_paths is not None:
            model_id_with_origin_paths = model_id_with_origin_paths.split(",")
            model_configs += [ModelConfig(model_id=i.split(":")[0], origin_file_pattern=i.split(":")[1]) for i in model_id_with_origin_paths]
        if tokenizer_path is not None:
            self.pipe = QwenImagePipeline.from_pretrained(torch_dtype=torch.bfloat16, device="cpu", model_configs=model_configs, tokenizer_config=ModelConfig(tokenizer_path))
        else:
            self.pipe = QwenImagePipeline.from_pretrained(torch_dtype=torch.bfloat16, device="cpu", model_configs=model_configs)

        # Reset training scheduler (do it in each training step)
        self.pipe.scheduler.set_timesteps(1000, training=True)
        
        # Freeze untrainable models
        self.pipe.freeze_except([] if trainable_models is None else trainable_models.split(","))
        
        # Add LoRA to the base models
        if lora_base_model is not None:
            model = self.add_lora_to_model(
                getattr(self.pipe, lora_base_model),
                target_modules=lora_target_modules.split(","),
                lora_rank=lora_rank
            )
            setattr(self.pipe, lora_base_model, model)
            
        # Store other configs
        self.use_gradient_checkpointing = use_gradient_checkpointing
        self.use_gradient_checkpointing_offload = use_gradient_checkpointing_offload
        self.extra_inputs = extra_inputs.split(",") if extra_inputs is not None else []

    
    def forward_preprocess(self, data):
        # CFG-sensitive parameters
        inputs_posi = {"prompt": data["prompt"]}
        inputs_nega = {"negative_prompt": ""}
        
        # CFG-unsensitive parameters
        inputs_shared = {
            # Assume you are using this pipeline for inference,
            # please fill in the input parameters.
            "input_image": data["image"],
            "height": data["image"].size[1],
            "width": data["image"].size[0],
            # Please do not modify the following parameters
            # unless you clearly know what this will cause.
            "cfg_scale": 1,
            "rand_device": self.pipe.device,
            "use_gradient_checkpointing": self.use_gradient_checkpointing,
            "use_gradient_checkpointing_offload": self.use_gradient_checkpointing_offload,
        }
        
        # Extra inputs
        for extra_input in self.extra_inputs:
            inputs_shared[extra_input] = data[extra_input]
        
        # Pipeline units will automatically process the input parameters.
        for unit in self.pipe.units:
            inputs_shared, inputs_posi, inputs_nega = self.pipe.unit_runner(unit, self.pipe, inputs_shared, inputs_posi, inputs_nega)
        return {**inputs_shared, **inputs_posi}
    
    
    def forward(self, data, inputs=None):
        if inputs is None: inputs = self.forward_preprocess(data)
        models = {name: getattr(self.pipe, name) for name in self.pipe.in_iteration_models}
        loss = self.pipe.training_loss(**models, **inputs)
        return loss



if __name__ == "__main__":
    parser = qwen_image_parser()
    args = parser.parse_args()
    dataset = ImageDataset(args=args)
    model = QwenImageTrainingModule(
        model_paths=args.model_paths,
        model_id_with_origin_paths=args.model_id_with_origin_paths,
        tokenizer_path=args.tokenizer_path,
        trainable_models=args.trainable_models,
        lora_base_model=args.lora_base_model,
        lora_target_modules=args.lora_target_modules,
        lora_rank=args.lora_rank,
        use_gradient_checkpointing=args.use_gradient_checkpointing,
        use_gradient_checkpointing_offload=args.use_gradient_checkpointing_offload,
        extra_inputs=args.extra_inputs,
    )
    model_logger = ModelLogger(
        args.output_path,
        remove_prefix_in_ckpt=args.remove_prefix_in_ckpt,
        state_dict_converter=QwenImageLoRAConverter.align_to_opensource_format if args.align_to_opensource_format else lambda x:x,
    )
    optimizer = torch.optim.AdamW(model.trainable_modules(), lr=args.learning_rate)
    scheduler = torch.optim.lr_scheduler.ConstantLR(optimizer)
    launch_training_task(
        dataset, model, model_logger, optimizer, scheduler,
        num_epochs=args.num_epochs,
        gradient_accumulation_steps=args.gradient_accumulation_steps,
        save_steps=args.save_steps,
        find_unused_parameters=args.find_unused_parameters,
        num_workers=args.dataset_num_workers,
    )