i use 2 images as input, and get this error:
Traceback (most recent call last):
File "/mnt/afs/OmniGen/demo.py", line 45, in
gen(prompt, input_images, saved_path)
File "/mnt/afs/OmniGen/demo.py", line 21, in gen
images = pipe(
File "/mnt/afs/conda/envs/controlplus/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/mnt/afs/OmniGen/OmniGen/pipeline.py", line 221, in call
input_data = self.processor(prompt, input_images, height=height, width=width, use_img_cfg=use_img_guidance, separate_cfg_input=separate_cfg_infer, use_input_image_size_as_output=use_input_image_size_as_output)
File "/mnt/afs/OmniGen/OmniGen/processor.py", line 130, in call
mllm_input = self.process_multi_modal_prompt(cur_instruction, cur_input_images)
File "/mnt/afs/OmniGen/OmniGen/processor.py", line 76, in process_multi_modal_prompt
assert len(unique_image_ids) == len(input_images), f"total images must be the same as the number of image tags, got {len(unique_image_ids)} image tags and {len(input_images)} images"
AssertionError: total images must be the same as the number of image tags, got 1 image tags and 2 images