ELLA-Diffusion
Ella can sometimes make already-correct results much less correct
RealCartoon 3D V15
Princess Peach is standing next to Tifa Lockhart, they are outside on a summer day, they are wearing bikinis. high quality, best quality, masterpiece
Without Ella:
With ELLA, same seed:
Using Ella in this case turns Princess Peach into a random pink-haired girl instead of the recognizable character.
During ELLA's training, a large number of synthetic captions were used, which typically do not include names or character names. Therefore, if your prompt contains a name, ELLA's performance is very poor. You can try replacing the name with 'a woman' and concatenate the output of CLIP.
@budui Thanks for explanation. And this is what I think there should be tricks to generate the better synthetic captions or mixing short captions and synthetic long captions.
During ELLA's training, a large number of synthetic captions were used, which typically do not include names or character names. Therefore, if your prompt contains a name, ELLA's performance is very poor. You can try replacing the name with 'a woman' and concatenate the output of CLIP.
We want to prevent this issue on our end as well. What did you mean when you said "concatenate the output of CLIP"? Where would the name be introduced again?
