Key Code：
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)
Comment：
It looks like 'List' is not match the argument 'edit_image' of pipe.
Error Details：
Traceback (most recent call last):
File "/data/source/opensource/video_ai/qwen-image-edit-test.py", line 40, in
image_3 = pipe(prompt, edit_image=edit_image, seed=1, num_inference_steps=40, height=1328, width=1024, edit_image_auto_resize=True)
File "/data/source/opensource/video_ai/.venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
return func(*args, **kwargs)
File "/data/source/opensource/video_ai/.venv/lib/python3.10/site-packages/diffsynth/pipelines/qwen_image.py", line 422, in call
inputs_shared, inputs_posi, inputs_nega = self.unit_runner(unit, self, inputs_shared, inputs_posi, inputs_nega)
File "/data/source/opensource/video_ai/.venv/lib/python3.10/site-packages/diffsynth/utils/init.py", line 273, in call
processor_outputs = unit.process(pipe, **processor_inputs)
File "/data/source/opensource/video_ai/.venv/lib/python3.10/site-packages/diffsynth/pipelines/qwen_image.py", line 714, in process
resized_edit_image = self.edit_image_auto_resize(edit_image) if edit_image_auto_resize else edit_image
File "/data/source/opensource/video_ai/.venv/lib/python3.10/site-packages/diffsynth/pipelines/qwen_image.py", line 707, in edit_image_auto_resize
calculated_width, calculated_height = self.calculate_dimensions(1024 * 1024, edit_image.size[0] / edit_image.size[1])
AttributeError: 'list' object has no attribute 'size'
@charleybin Please use git clone to update the code.
@charleybin Please use git clone to update the code.
I also face the same question, but I git clone the code just now and the question remained. Could you please tell me why? Thanks.
modelscope
