The output is not closely what is expected - what am I doing wrong?
Running on Google's Colab... Here is the output I am getting for sample queries:

maybe tell it more detail or other words ?
I think I've got the same issue




what's missing here xD
even tried the image from the demo...




Me too, It seems that the demo don't understand the content before
Maybe use the image name, "change the motorcycle on the image/3914e55f.jpg"
Hi @hezzze and @emarutian For replacement and removement, you need to load the ImageEditing. For Visual Question Answering, you need to load the VisualQuestionAnswering. For changing the style, you need to load InstructPix2Pix. Please make sure that you have loaded the visual foundation models you want to use. Thanks~
That's right. That was it. Thank you