so how to input multi-images? (Just python code without ComfyUI)

#69
by HughZyy - opened

image1 = Image.open("./1.png").convert("RGB").resize((512, 512))
image2 = Image.open("./2.png").convert("RGB").resize((512, 512))
inputs = {
"image": [image1, image2],
"prompt": prompt,
"generator": torch.manual_seed(0),
"true_cfg_scale": 4.0,
"negative_prompt": "",
"num_inference_steps": 8,
}

I tried to pass multiple images as a list into the pipeline, but unfortunately, it does not work. The error is as follows:

"/home/zyy/miniconda3/envs/py311/lib/python3.11/site-packages/transformers/models/qwen2_5_vl/modeling_qwen2_5_vl.py", line 1220, in get_placeholder_mask raise ValueError( ValueError: Image features and image tokens do not match: tokens: 324, features: 648

image_paths = ["./1.png", "./2.png"]
prompt = "Wushu stance"

for image_path in image_paths:

image = Image.open(image_path).convert("RGB").resize((512, 512))


inputs = {
    "image": image,
    "prompt": prompt,
    "generator": torch.manual_seed(0),
    "true_cfg_scale": 4.0,
    "negative_prompt": "",
    "num_inference_steps": 8,
}

Sign up or log in to comment