The benchmark builds upon the previous DOCCI dataset.
We’ve released TECCI, a new dataset focusing on challenging image edits! (Including visual puzzles and much more)
Like DOCCI, all images are donated to the public domain, so you get the bytes with the data. See Aishwarya’s thread for more details and pointers.
Very cool to see the latest release of these images from the BCU (Baldridge Cinematic Universe)
We’ve released TECCI, a new dataset focusing on challenging image edits! (Including visual puzzles and much more)
Like DOCCI, all images are donated to the public domain, so you get the bytes with the data. See Aishwarya’s thread for more details and pointers.
The benchmark builds upon the previous DOCCI dataset.
We’ve released TECCI, a new dataset focusing on challenging image edits! (Including visual puzzles and much more)
Like DOCCI, all images are donated to the public domain, so you get the bytes with the data. See Aishwarya’s thread for more details and pointers.