qwen-image

examples/qwen_image/model_training/full/Qwen-Image.sh

@@ -0,0 +1,12 @@
+accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml examples/qwen_image/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Qwen-Image_full" \
+  --trainable_models "dit" \
+  --use_gradient_checkpointing

examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml

@@ -0,0 +1,22 @@
+compute_environment: LOCAL_MACHINE
+debug: false
+deepspeed_config:
+  gradient_accumulation_steps: 1
+  offload_optimizer_device: 'cpu'
+  offload_param_device: 'cpu'
+  zero3_init_flag: false
+  zero_stage: 2
+distributed_type: DEEPSPEED
+downcast_bf16: 'no'
+enable_cpu_affinity: false
+machine_rank: 0
+main_training_function: main
+mixed_precision: bf16
+num_machines: 1
+num_processes: 8
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false

examples/qwen_image/model_training/lora/Qwen-Image.sh

@@ -0,0 +1,15 @@
+accelerate launch examples/qwen_image/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Qwen-Image_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "to_q,to_k,to_v,add_q_proj,add_k_proj,add_v_proj,to_out.0,to_add_out,img_mlp.net.2,img_mod.1,txt_mlp.net.2,txt_mod.1" \
+  --lora_rank 32 \
+  --align_to_opensource_format \
+  --use_gradient_checkpointing

examples/qwen_image/model_training/train.py

@@ -0,0 +1,118 @@
+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
+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,
+    )
+    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,
+    )

examples/qwen_image/model_training/validate_full/Qwen-Image.py

@@ -0,0 +1,20 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+from diffsynth import load_state_dict
+import torch
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+state_dict = load_state_dict("models/train/Qwen-Image_full/epoch-1.safetensors")
+pipe.dit.load_state_dict(state_dict)
+prompt = "a dog"
+image = pipe(prompt, seed=0)
+image.save("image.jpg")

examples/qwen_image/model_training/validate_lora/Qwen-Image.py

@@ -0,0 +1,18 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+import torch
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+pipe.load_lora(pipe.dit, "models/train/Qwen-Image_lora/epoch-4.safetensors")
+prompt = "a dog"
+image = pipe(prompt, seed=0)
+image.save("image.jpg")