niwrad·8 か月前·議論This is a good question -- I've wanted transparency from image models for a while. One work around is to ask for a "green screen" and to key out the background but it doesn't always work very cleanly.
niwrad·9 か月前·議論I've also added a text-to-image versions of the same test here: https://www.cinemodels.ai/benchmark?test=wink&type=text-to-v...Prompt: "A white female in their 30s winks at the camera with her right eye.She is standing in a quiet dark green forest, backlit by the sunset during golden hour."