fix qwen_rope

examples/qwen_image/README.md

@@ -236,7 +236,6 @@ The script includes the following parameters:
   * `--model_paths`: Model paths to load. In JSON format.
   * `--model_id_with_origin_paths`: Model ID with original paths, e.g., Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors. Separate with commas.
   * `--tokenizer_path`: Tokenizer path. Leave empty to auto-download.
-  * `--edit_model`: Whether to use Qwen-Image-Edit. If True, the model will be used for image editing.
   * `--processor_path`: Path to the processor of Qwen-Image-Edit. Leave empty to auto-download.
 * Training
   * `--learning_rate`: Learning rate.

examples/qwen_image/README_zh.md

@@ -236,7 +236,6 @@ Qwen-Image 系列模型训练通过统一的 [`./model_training/train.py`](./mod
   * `--model_paths`: 要加载的模型路径。JSON 格式。
   * `--model_id_with_origin_paths`: 带原始路径的模型 ID，例如 Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors。用逗号分隔。
   * `--tokenizer_path`: tokenizer 路径，留空将会自动下载。
-  * `--edit_model`：是否使用 Qwen-Image-Edit。若为 True，则将使用该模型进行图像编辑。  
   * `--processor_path`：Qwen-Image-Edit 的 processor 路径。留空则自动下载。
 * 训练
   * `--learning_rate`: 学习率。

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

@@ -1,5 +1,4 @@
 accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml examples/qwen_image/model_training/train.py \
-  --edit_model \
   --dataset_base_path data/example_image_dataset \
   --dataset_metadata_path data/example_image_dataset/metadata_edit.csv \
   --max_pixels 1048576 \

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

@@ -1,5 +1,4 @@
 accelerate launch examples/qwen_image/model_training/train.py \
-  --edit_model \
   --dataset_base_path data/example_image_dataset \
   --dataset_metadata_path data/example_image_dataset/metadata_edit.csv \
   --max_pixels 1048576 \

examples/qwen_image/model_training/train.py

@@ -11,7 +11,7 @@ class QwenImageTrainingModule(DiffusionTrainingModule):
     def __init__(
         self,
         model_paths=None, model_id_with_origin_paths=None,
-        tokenizer_path=None, processor_path=None, edit_model=False,
+        tokenizer_path=None, processor_path=None,
         trainable_models=None,
         lora_base_model=None, lora_target_modules="", lora_rank=32, lora_checkpoint=None,
         use_gradient_checkpointing=True,
@@ -28,12 +28,8 @@ class QwenImageTrainingModule(DiffusionTrainingModule):
             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 edit_model:
-            tokenizer_config = None
-            processor_config = ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/") if processor_path is None else ModelConfig(processor_path)
-        else:
-            tokenizer_config = ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/") if tokenizer_path is None else ModelConfig(tokenizer_path)
-            processor_config = None
+        tokenizer_config = ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/") if tokenizer_path is None else ModelConfig(tokenizer_path)
+        processor_config = ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/") if processor_path is None else ModelConfig(processor_path)
         self.pipe = QwenImagePipeline.from_pretrained(torch_dtype=torch.bfloat16, device="cpu", model_configs=model_configs, tokenizer_config=tokenizer_config, processor_config=processor_config)
         
         # Reset training scheduler (do it in each training step)
@@ -120,7 +116,6 @@ if __name__ == "__main__":
         model_id_with_origin_paths=args.model_id_with_origin_paths,
         tokenizer_path=args.tokenizer_path,
         processor_path=args.processor_path,
-        edit_model=args.edit_model,
         trainable_models=args.trainable_models,
         lora_base_model=args.lora_base_model,
         lora_target_modules=args.lora_target_modules,