I was very excited when it came out. Google have Imagen 3 (is that the same as Gemini Flash?), but you need special access to be able to edit images. I haven't tested it yet but I think it's a lot cheaper than OpenAI
instruction following is good most of the time, but hands are still regularly coming out garbled and there's a small percentage of failed generation in the mix. style following is also a bit hit and miss, I'm producing watecolor mostly, but every now and then a generation is photographic
I manually remove failed gens, but the proces doens't scale to where I'd like if I have to manually verify images. and I have to have a few automatic rejection in the pipeline, like top border not white or image not squared.
Yes! https://openai.com/index/image-generation-api/
I was very excited when it came out. Google have Imagen 3 (is that the same as Gemini Flash?), but you need special access to be able to edit images. I haven't tested it yet but I think it's a lot cheaper than OpenAI
imagen 3 is a standard diffusion model the new one is attached to gemini 2.0 flash experimental. model naming and working is super confusing there
Gemini has released new models, maybe they are better.
Also, I request you to expand further, why Gemini is not better?
instruction following is good most of the time, but hands are still regularly coming out garbled and there's a small percentage of failed generation in the mix. style following is also a bit hit and miss, I'm producing watecolor mostly, but every now and then a generation is photographic
site is not really ready for this, but if you want to get an idea go here https://d2uua1ig5ocnwt.cloudfront.net/ and search these:
amber ladybugs north
I manually remove failed gens, but the proces doens't scale to where I'd like if I have to manually verify images. and I have to have a few automatic rejection in the pipeline, like top border not white or image not squared.