Open mischaschaub opened 1 year ago
Hi @mischaschaub,
all images can be accessed here in the outputs
variable, before the video is produced.
result = self.inference
result is a set of images compatible with the huggingface pipeline, that is, use numpy to handle the array of images and with cv2 you will be able to save... loop to save each image.
Would it be possible to save all rendered picts out, before they are compressed to a movie?