Open JihadAKl opened 1 year ago
Can you try it again? It seems the output mask_image
of MaskFormer is None unfortunately at https://github.com/microsoft/visual-chatgpt/blob/main/visual_chatgpt.py#L180. What is the object you want to remove? maybe this MaskFormer cannot find the object in this image. More details?
Hi @JihadAKl , could you share your input image 'image/228cf7ef.png' and your dialogue, so we can debug that.
I am using this image and the prompt is remove everything except the couch from the image
I use this prompt: Change the color of the couch to white i get this:
so, the couch is masked. I am getting another couch tho.
This is a foundation model issue, since the ImageEditing model failed to remove everything except the sofa.
The log is:
Processed ImageEditing, Input Image: image/7908da62.png, Replace everything except the sofa to background, Output Image: image/b7ab_replace-something_7908da62_7908da62.png
To solve this issue, we need to leverage more accurate Visual Foundation Models (VFM).
Did you get my error? AttributeError: 'NoneType' object has no attribute 'resize'
are you using other models than ImageCaptioning, ImageEditing and Text2Image?
Did you get my error? AttributeError: 'NoneType' object has no attribute 'resize'
are you using other models than ImageCaptioning, ImageEditing and Text2Image?
I have the exactly same error. Looking for solutions. Thanks.
I have the same issue. After debugging, it appears that the area_ratio is too small, which indicates that the replacement failed. https://github.com/microsoft/visual-chatgpt/blob/3cfc0a052d67d29e96065b3ea2bf8e22690da785/visual_chatgpt.py#L201
I am using python visual_chatgpt.py --load "ImageCaptioning_cuda:0,ImageEditing_cuda:0,Text2Image_cuda:0"
I am getting this error any idea?