diff --git a/README.md b/README.md
index 1acdff9..3b5facb 100644
--- a/README.md
+++ b/README.md
@@ -95,6 +95,7 @@ image.save("image.jpg")
 |-|-|-|-|-|-|-|
 |[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image)|[code](./examples/qwen_image/model_inference/Qwen-Image.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image.py)|
 |[Qwen/Qwen-Image-Edit](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit)|[code](./examples/qwen_image/model_inference/Qwen-Image-Edit.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Edit.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Edit.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Edit.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit.py)|
+|[Qwen/Qwen-Image-Edit-2509](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2509)|[code](./examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py)|
 |[DiffSynth-Studio/Qwen-Image-EliGen-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-V2)|[code](./examples/qwen_image/model_inference/Qwen-Image-EliGen-V2.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-V2.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-EliGen.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)|[code](./examples/qwen_image/model_inference/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Distill-Full.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Distill-Full.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./examples/qwen_image/model_inference/Qwen-Image-Distill-LoRA.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Distill-LoRA.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Distill-LoRA.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Distill-LoRA.py)|
diff --git a/README_zh.md b/README_zh.md
index bba1659..2b40b50 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -97,6 +97,7 @@ image.save("image.jpg")
 |-|-|-|-|-|-|-|
 |[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image)|[code](./examples/qwen_image/model_inference/Qwen-Image.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image.py)|
 |[Qwen/Qwen-Image-Edit](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit)|[code](./examples/qwen_image/model_inference/Qwen-Image-Edit.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Edit.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Edit.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Edit.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit.py)|
+|[Qwen/Qwen-Image-Edit-2509](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2509)|[code](./examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py)|
 |[DiffSynth-Studio/Qwen-Image-EliGen-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-V2)|[code](./examples/qwen_image/model_inference/Qwen-Image-EliGen-V2.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-V2.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-EliGen.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)|[code](./examples/qwen_image/model_inference/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Distill-Full.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Distill-Full.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./examples/qwen_image/model_inference/Qwen-Image-Distill-LoRA.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Distill-LoRA.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Distill-LoRA.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Distill-LoRA.py)|
diff --git a/diffsynth/pipelines/qwen_image.py b/diffsynth/pipelines/qwen_image.py
index 032b7a3..e949b56 100644
--- a/diffsynth/pipelines/qwen_image.py
+++ b/diffsynth/pipelines/qwen_image.py
@@ -524,37 +524,63 @@ class QwenImageUnit_PromptEmbedder(PipelineUnit):
         selected = hidden_states[bool_mask]
         split_result = torch.split(selected, valid_lengths.tolist(), dim=0)
         return split_result
+    
+    def calculate_dimensions(self, target_area, ratio):
+        import math
+        width = math.sqrt(target_area * ratio)
+        height = width / ratio
+        width = round(width / 32) * 32
+        height = round(height / 32) * 32
+        return width, height
+    
+    def resize_image(self, image, target_area=384*384):
+        width, height = self.calculate_dimensions(target_area, image.size[0] / image.size[1])
+        return image.resize((width, height))
+    
+    def encode_prompt(self, pipe: QwenImagePipeline, prompt):
+        template = "<|im_start|>system\nDescribe the image by detailing the color, shape, size, texture, quantity, text, spatial relationships of the objects and background:<|im_end|>\n<|im_start|>user\n{}<|im_end|>\n<|im_start|>assistant\n"
+        drop_idx = 34
+        txt = [template.format(e) for e in prompt]
+        model_inputs = pipe.tokenizer(txt, max_length=4096+drop_idx, padding=True, truncation=True, return_tensors="pt").to(pipe.device)
+        if model_inputs.input_ids.shape[1] >= 1024:
+            print(f"Warning!!! QwenImage model was trained on prompts up to 512 tokens. Current prompt requires {model_inputs['input_ids'].shape[1] - drop_idx} tokens, which may lead to unpredictable behavior.")
+        hidden_states = pipe.text_encoder(input_ids=model_inputs.input_ids, attention_mask=model_inputs.attention_mask, output_hidden_states=True,)[-1]
+        split_hidden_states = self.extract_masked_hidden(hidden_states, model_inputs.attention_mask)
+        split_hidden_states = [e[drop_idx:] for e in split_hidden_states]
+        return split_hidden_states
+        
+    def encode_prompt_edit(self, pipe: QwenImagePipeline, prompt, edit_image):
+        template =  "<|im_start|>system\nDescribe the key features of the input image (color, shape, size, texture, objects, background), then explain how the user's text instruction should alter or modify the image. Generate a new image that meets the user's requirements while maintaining consistency with the original input where appropriate.<|im_end|>\n<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>{}<|im_end|>\n<|im_start|>assistant\n"
+        drop_idx = 64
+        txt = [template.format(e) for e in prompt]
+        model_inputs = pipe.processor(text=txt, images=edit_image, padding=True, return_tensors="pt").to(pipe.device)
+        hidden_states = pipe.text_encoder(input_ids=model_inputs.input_ids, attention_mask=model_inputs.attention_mask, pixel_values=model_inputs.pixel_values, image_grid_thw=model_inputs.image_grid_thw, output_hidden_states=True,)[-1]
+        split_hidden_states = self.extract_masked_hidden(hidden_states, model_inputs.attention_mask)
+        split_hidden_states = [e[drop_idx:] for e in split_hidden_states]
+        return split_hidden_states
+    
+    def encode_prompt_edit_multi(self, pipe: QwenImagePipeline, prompt, edit_image):
+        template =  "<|im_start|>system\nDescribe the key features of the input image (color, shape, size, texture, objects, background), then explain how the user's text instruction should alter or modify the image. Generate a new image that meets the user's requirements while maintaining consistency with the original input where appropriate.<|im_end|>\n<|im_start|>user\n{}<|im_end|>\n<|im_start|>assistant\n"
+        drop_idx = 64
+        img_prompt_template = "Picture {}: <|vision_start|><|image_pad|><|vision_end|>"
+        base_img_prompt = "".join([img_prompt_template.format(i + 1) for i in range(len(edit_image))])
+        txt = [template.format(base_img_prompt + e) for e in prompt]
+        edit_image = [self.resize_image(image) for image in edit_image]
+        model_inputs = pipe.processor(text=txt, images=edit_image, padding=True, return_tensors="pt").to(pipe.device)
+        hidden_states = pipe.text_encoder(input_ids=model_inputs.input_ids, attention_mask=model_inputs.attention_mask, pixel_values=model_inputs.pixel_values, image_grid_thw=model_inputs.image_grid_thw, output_hidden_states=True,)[-1]
+        split_hidden_states = self.extract_masked_hidden(hidden_states, model_inputs.attention_mask)
+        split_hidden_states = [e[drop_idx:] for e in split_hidden_states]
+        return split_hidden_states
 
     def process(self, pipe: QwenImagePipeline, prompt, edit_image=None) -> dict:
         if pipe.text_encoder is not None:
             prompt = [prompt]
-            # If edit_image is None, use the default template for Qwen-Image, otherwise use the template for Qwen-Image-Edit
             if edit_image is None:
-                template = "<|im_start|>system\nDescribe the image by detailing the color, shape, size, texture, quantity, text, spatial relationships of the objects and background:<|im_end|>\n<|im_start|>user\n{}<|im_end|>\n<|im_start|>assistant\n"
-                drop_idx = 34
+                split_hidden_states = self.encode_prompt(pipe, prompt)
+            elif isinstance(edit_image, Image.Image):
+                split_hidden_states = self.encode_prompt_edit(pipe, prompt, edit_image)
             else:
-                template =  "<|im_start|>system\nDescribe the key features of the input image (color, shape, size, texture, objects, background), then explain how the user's text instruction should alter or modify the image. Generate a new image that meets the user's requirements while maintaining consistency with the original input where appropriate.<|im_end|>\n<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>{}<|im_end|>\n<|im_start|>assistant\n"
-                drop_idx = 64
-            txt = [template.format(e) for e in prompt]
-
-            # Qwen-Image-Edit model
-            if pipe.processor is not None:
-                model_inputs = pipe.processor(text=txt, images=edit_image, padding=True, return_tensors="pt").to(pipe.device)
-            # Qwen-Image model
-            elif pipe.tokenizer is not None:
-                model_inputs = pipe.tokenizer(txt, max_length=4096+drop_idx, padding=True, truncation=True, return_tensors="pt").to(pipe.device)
-                if model_inputs.input_ids.shape[1] >= 1024:
-                    print(f"Warning!!! QwenImage model was trained on prompts up to 512 tokens. Current prompt requires {model_inputs['input_ids'].shape[1] - drop_idx} tokens, which may lead to unpredictable behavior.")
-            else:
-                assert False, "QwenImagePipeline requires either tokenizer or processor to be loaded."
-
-            if 'pixel_values' in model_inputs:
-                hidden_states = pipe.text_encoder(input_ids=model_inputs.input_ids, attention_mask=model_inputs.attention_mask, pixel_values=model_inputs.pixel_values, image_grid_thw=model_inputs.image_grid_thw, output_hidden_states=True,)[-1]
-            else:
-                hidden_states = pipe.text_encoder(input_ids=model_inputs.input_ids, attention_mask=model_inputs.attention_mask, output_hidden_states=True,)[-1]
-
-            split_hidden_states = self.extract_masked_hidden(hidden_states, model_inputs.attention_mask)
-            split_hidden_states = [e[drop_idx:] for e in split_hidden_states]
+                split_hidden_states = self.encode_prompt_edit_multi(pipe, prompt, edit_image)
             attn_mask_list = [torch.ones(e.size(0), dtype=torch.long, device=e.device) for e in split_hidden_states]
             max_seq_len = max([e.size(0) for e in split_hidden_states])
             prompt_embeds = torch.stack([torch.cat([u, u.new_zeros(max_seq_len - u.size(0), u.size(1))]) for u in split_hidden_states])
@@ -712,12 +738,23 @@ class QwenImageUnit_EditImageEmbedder(PipelineUnit):
     def process(self, pipe: QwenImagePipeline, edit_image, tiled, tile_size, tile_stride, edit_image_auto_resize=False):
         if edit_image is None:
             return {}
-        resized_edit_image = self.edit_image_auto_resize(edit_image) if edit_image_auto_resize else edit_image
         pipe.load_models_to_device(['vae'])
-        edit_image = pipe.preprocess_image(resized_edit_image).to(device=pipe.device, dtype=pipe.torch_dtype)
-        edit_latents = pipe.vae.encode(edit_image, tiled=tiled, tile_size=tile_size, tile_stride=tile_stride)
+        if isinstance(edit_image, Image.Image):
+            resized_edit_image = self.edit_image_auto_resize(edit_image) if edit_image_auto_resize else edit_image
+            edit_image = pipe.preprocess_image(resized_edit_image).to(device=pipe.device, dtype=pipe.torch_dtype)
+            edit_latents = pipe.vae.encode(edit_image, tiled=tiled, tile_size=tile_size, tile_stride=tile_stride)
+        else:
+            resized_edit_image, edit_latents = [], []
+            for image in edit_image:
+                if edit_image_auto_resize:
+                    image = self.edit_image_auto_resize(image)
+                resized_edit_image.append(image)
+                image = pipe.preprocess_image(image).to(device=pipe.device, dtype=pipe.torch_dtype)
+                latents = pipe.vae.encode(image, tiled=tiled, tile_size=tile_size, tile_stride=tile_stride)
+                edit_latents.append(latents)
         return {"edit_latents": edit_latents, "edit_image": resized_edit_image}
 
+
 class QwenImageUnit_ContextImageEmbedder(PipelineUnit):
     def __init__(self):
         super().__init__(
@@ -770,9 +807,10 @@ def model_fn_qwen_image(
         context_image = rearrange(context_latents, "B C (H P) (W Q) -> B (H W) (C P Q)", H=context_latents.shape[2]//2, W=context_latents.shape[3]//2, P=2, Q=2)
         image = torch.cat([image, context_image], dim=1)
     if edit_latents is not None:
-        img_shapes += [(edit_latents.shape[0], edit_latents.shape[2]//2, edit_latents.shape[3]//2)]
-        edit_image = rearrange(edit_latents, "B C (H P) (W Q) -> B (H W) (C P Q)", H=edit_latents.shape[2]//2, W=edit_latents.shape[3]//2, P=2, Q=2)
-        image = torch.cat([image, edit_image], dim=1)
+        edit_latents_list = edit_latents if isinstance(edit_latents, list) else [edit_latents]
+        img_shapes += [(e.shape[0], e.shape[2]//2, e.shape[3]//2) for e in edit_latents_list]
+        edit_image = [rearrange(e, "B C (H P) (W Q) -> B (H W) (C P Q)", H=e.shape[2]//2, W=e.shape[3]//2, P=2, Q=2) for e in edit_latents_list]
+        image = torch.cat([image] + edit_image, dim=1)
 
     image = dit.img_in(image)
     conditioning = dit.time_text_embed(timestep, image.dtype)
diff --git a/examples/qwen_image/README.md b/examples/qwen_image/README.md
index d01da52..4190ade 100644
--- a/examples/qwen_image/README.md
+++ b/examples/qwen_image/README.md
@@ -47,6 +47,7 @@ image.save("image.jpg")
 |-|-|-|-|-|-|-|
 |[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image)|[code](./model_inference/Qwen-Image.py)|[code](./model_inference_low_vram/Qwen-Image.py)|[code](./model_training/full/Qwen-Image.sh)|[code](./model_training/validate_full/Qwen-Image.py)|[code](./model_training/lora/Qwen-Image.sh)|[code](./model_training/validate_lora/Qwen-Image.py)|
 |[Qwen/Qwen-Image-Edit](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit)|[code](./model_inference/Qwen-Image-Edit.py)|[code](./model_inference_low_vram/Qwen-Image-Edit.py)|[code](./model_training/full/Qwen-Image-Edit.sh)|[code](./model_training/validate_full/Qwen-Image-Edit.py)|[code](./model_training/lora/Qwen-Image-Edit.sh)|[code](./model_training/validate_lora/Qwen-Image-Edit.py)|
+|[Qwen/Qwen-Image-Edit-2509](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2509)|[code](./model_inference/Qwen-Image-Edit-2509.py)|[code](./model_inference_low_vram/Qwen-Image-Edit-2509.py)|[code](./model_training/full/Qwen-Image-Edit-2509.sh)|[code](./model_training/validate_full/Qwen-Image-Edit-2509.py)|[code](./model_training/lora/Qwen-Image-Edit-2509.sh)|[code](./model_training/validate_lora/Qwen-Image-Edit-2509.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)|[code](./model_inference/Qwen-Image-Distill-Full.py)|[code](./model_inference_low_vram/Qwen-Image-Distill-Full.py)|[code](./model_training/full/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_lora/Qwen-Image-Distill-Full.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./model_inference/Qwen-Image-Distill-LoRA.py)|[code](./model_inference_low_vram/Qwen-Image-Distill-LoRA.py)|-|-|[code](./model_training/lora/Qwen-Image-Distill-LoRA.sh)|[code](./model_training/validate_lora/Qwen-Image-Distill-LoRA.py)|
 |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](./model_inference/Qwen-Image-EliGen.py)|[code](./model_inference_low_vram/Qwen-Image-EliGen.py)|-|-|[code](./model_training/lora/Qwen-Image-EliGen.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen.py)|
diff --git a/examples/qwen_image/README_zh.md b/examples/qwen_image/README_zh.md
index a7f75e4..fa7a3d4 100644
--- a/examples/qwen_image/README_zh.md
+++ b/examples/qwen_image/README_zh.md
@@ -47,6 +47,7 @@ image.save("image.jpg")
 |-|-|-|-|-|-|-|
 |[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image)|[code](./model_inference/Qwen-Image.py)|[code](./model_inference_low_vram/Qwen-Image.py)|[code](./model_training/full/Qwen-Image.sh)|[code](./model_training/validate_full/Qwen-Image.py)|[code](./model_training/lora/Qwen-Image.sh)|[code](./model_training/validate_lora/Qwen-Image.py)|
 |[Qwen/Qwen-Image-Edit](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit)|[code](./model_inference/Qwen-Image-Edit.py)|[code](./model_inference_low_vram/Qwen-Image-Edit.py)|[code](./model_training/full/Qwen-Image-Edit.sh)|[code](./model_training/validate_full/Qwen-Image-Edit.py)|[code](./model_training/lora/Qwen-Image-Edit.sh)|[code](./model_training/validate_lora/Qwen-Image-Edit.py)|
+|[Qwen/Qwen-Image-Edit-2509](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2509)|[code](./model_inference/Qwen-Image-Edit-2509.py)|[code](./model_inference_low_vram/Qwen-Image-Edit-2509.py)|[code](./model_training/full/Qwen-Image-Edit-2509.sh)|[code](./model_training/validate_full/Qwen-Image-Edit-2509.py)|[code](./model_training/lora/Qwen-Image-Edit-2509.sh)|[code](./model_training/validate_lora/Qwen-Image-Edit-2509.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)|[code](./model_inference/Qwen-Image-Distill-Full.py)|[code](./model_inference_low_vram/Qwen-Image-Distill-Full.py)|[code](./model_training/full/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_lora/Qwen-Image-Distill-Full.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./model_inference/Qwen-Image-Distill-LoRA.py)|[code](./model_inference_low_vram/Qwen-Image-Distill-LoRA.py)|-|-|[code](./model_training/lora/Qwen-Image-Distill-LoRA.sh)|[code](./model_training/validate_lora/Qwen-Image-Distill-LoRA.py)|
 |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](./model_inference/Qwen-Image-EliGen.py)|[code](./model_inference_low_vram/Qwen-Image-EliGen.py)|-|-|[code](./model_training/lora/Qwen-Image-EliGen.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen.py)|
diff --git a/examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py b/examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py
new file mode 100644
index 0000000..45489cd
--- /dev/null
+++ b/examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py
@@ -0,0 +1,25 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+from PIL import Image
+import torch
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image-Edit-2509", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+    ],
+    processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"),
+)
+
+image_1 = pipe(prompt="一位少女", seed=0, num_inference_steps=40, height=1328, width=1024)
+image_1.save("image1.jpg")
+
+image_2 = pipe(prompt="一位老人", seed=0, num_inference_steps=40, height=1328, width=1024)
+image_2.save("image2.jpg")
+
+prompt = "生成这两个人的合影"
+edit_image = [Image.open("image1.jpg"), Image.open("image2.jpg")]
+image_3 = pipe(prompt, edit_image=edit_image, seed=1, num_inference_steps=40, height=1328, width=1024, edit_image_auto_resize=True)
+image_3.save("image3.jpg")
diff --git a/examples/qwen_image/model_inference/Qwen-Image-Edit-Lowres-Fix.py b/examples/qwen_image/model_inference/Qwen-Image-Edit-Lowres-Fix.py
index bbe3b7e..c18eaa8 100644
--- a/examples/qwen_image/model_inference/Qwen-Image-Edit-Lowres-Fix.py
+++ b/examples/qwen_image/model_inference/Qwen-Image-Edit-Lowres-Fix.py
@@ -10,7 +10,6 @@ pipe = QwenImagePipeline.from_pretrained(
         ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
         ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
     ],
-    tokenizer_config=None,
     processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"),
 )
 snapshot_download("DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix", local_dir="models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix", allow_file_pattern="model.safetensors")
diff --git a/examples/qwen_image/model_inference/Qwen-Image-Edit.py b/examples/qwen_image/model_inference/Qwen-Image-Edit.py
index 39d39a6..8a47756 100644
--- a/examples/qwen_image/model_inference/Qwen-Image-Edit.py
+++ b/examples/qwen_image/model_inference/Qwen-Image-Edit.py
@@ -9,7 +9,6 @@ pipe = QwenImagePipeline.from_pretrained(
         ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
         ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
     ],
-    tokenizer_config=None,
     processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"),
 )
 prompt = "精致肖像，水下少女，蓝裙飘逸，发丝轻扬，光影透澈，气泡环绕，面容恬静，细节精致，梦幻唯美。"
diff --git a/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py b/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py
new file mode 100644
index 0000000..833cba5
--- /dev/null
+++ b/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py
@@ -0,0 +1,26 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+from PIL import Image
+import torch
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image-Edit-2509", 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),
+    ],
+    processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"),
+)
+pipe.enable_vram_management()
+
+image_1 = pipe(prompt="一位少女", seed=0, num_inference_steps=40, height=1328, width=1024)
+image_1.save("image1.jpg")
+
+image_2 = pipe(prompt="一位老人", seed=0, num_inference_steps=40, height=1328, width=1024)
+image_2.save("image2.jpg")
+
+prompt = "生成这两个人的合影"
+edit_image = [Image.open("image1.jpg"), Image.open("image2.jpg")]
+image_3 = pipe(prompt, edit_image=edit_image, seed=1, num_inference_steps=40, height=1328, width=1024, edit_image_auto_resize=True)
+image_3.save("image3.jpg")
diff --git a/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py b/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py
index 55c771f..5573fb5 100644
--- a/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py
+++ b/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py
@@ -10,7 +10,6 @@ pipe = QwenImagePipeline.from_pretrained(
         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=None,
     processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"),
 )
 pipe.enable_vram_management()
diff --git a/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit.py b/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit.py
index 5cc79fd..b3b9a5a 100644
--- a/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit.py
+++ b/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit.py
@@ -9,7 +9,6 @@ pipe = QwenImagePipeline.from_pretrained(
         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=None,
     processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"),
 )
 pipe.enable_vram_management()
diff --git a/examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh b/examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh
new file mode 100644
index 0000000..a41f2da
--- /dev/null
+++ b/examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh
@@ -0,0 +1,15 @@
+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_edit.csv \
+  --data_file_keys "image,edit_image" \
+  --extra_inputs "edit_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "Qwen/Qwen-Image-Edit-2509: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-Edit-2509_full" \
+  --trainable_models "dit" \
+  --use_gradient_checkpointing \
+  --find_unused_parameters
diff --git a/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh b/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh
new file mode 100644
index 0000000..3bbf742
--- /dev/null
+++ b/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh
@@ -0,0 +1,18 @@
+accelerate launch examples/qwen_image/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_edit.csv \
+  --data_file_keys "image,edit_image" \
+  --extra_inputs "edit_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "Qwen/Qwen-Image-Edit-2509: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-Edit-2509_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 \
+  --use_gradient_checkpointing \
+  --dataset_num_workers 8 \
+  --find_unused_parameters
diff --git a/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py b/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py
new file mode 100644
index 0000000..ff1fdbf
--- /dev/null
+++ b/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py
@@ -0,0 +1,23 @@
+import torch
+from PIL import Image
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+from diffsynth import load_state_dict
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image-Edit-2509", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+    ],
+    tokenizer_config=None,
+    processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"),
+)
+state_dict = load_state_dict("models/train/Qwen-Image-Edit-2509_full/epoch-1.safetensors")
+pipe.dit.load_state_dict(state_dict)
+
+prompt = "将裙子改为粉色"
+image = Image.open("data/example_image_dataset/edit/image1.jpg").resize((1024, 1024))
+image = pipe(prompt, edit_image=image, seed=0, num_inference_steps=40, height=1024, width=1024)
+image.save(f"image.jpg")
diff --git a/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py b/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py
new file mode 100644
index 0000000..4eaf428
--- /dev/null
+++ b/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py
@@ -0,0 +1,21 @@
+import torch
+from PIL import Image
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image-Edit-2509", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+    ],
+    tokenizer_config=None,
+    processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"),
+)
+pipe.load_lora(pipe.dit, "models/train/Qwen-Image-Edit-2509_lora/epoch-4.safetensors")
+
+prompt = "将裙子改为粉色"
+image = Image.open("data/example_image_dataset/edit/image1.jpg").resize((1024, 1024))
+image = pipe(prompt, edit_image=image, seed=0, num_inference_steps=40, height=1024, width=1024)
+image.save(f"image.jpg")