Closed sayakpaul closed 1 year ago
Check out this pull request on
See visual diffs & provide feedback on Jupyter Notebooks.
Powered by ReviewNB
Hi, small comment: in the gif, for the image-to-text generation example, it shows the UniDiffuser example image of an astronaut as the input, but "A stream in the middle stream in forest" as the output text. Is this an oversight?
Hi, small comment: in the gif, for the image-to-text generation example, it shows the UniDiffuser example image of an astronaut as the input, but "A stream in the middle stream in forest" as the output text. Is this an oversight?
You are right. I will take care of it.
Feel free to merge whenever @sayakpaul :-)
Corresponding PR: https://github.com/huggingface/diffusers/pull/2963
Most of the content is taken from the documentation of the pipeline.
Will merge as is unless there's any feedback.
Cc: @patrickvonplaten (as an FYI).