Feature Requests

We've launched a greatly improved background change version and if you want custom backgrounds (locations, styles moods please comment here)

It would be nice to specify background options prior to image generation. I wanted only one type of background but got tons of options I couldn't use.

I think it would be a great addition to have your studio like portrait shots specifically aimed for social media content creators and managers. It could be like holding a laptop or sitting on a desk or workspace. Cafe vibe is nice but this one can be a great addition to the styles.

Change one specific part of an image without making any other changes to the image. Currently we would support: Clothing Expression Background Please share what you think would be helpful to you and why! We love to hear about use cases

There is clothing I love in some of my images, but I've been unable to get Secta to generate anything similar on the photos I love (even when I choose a different style of clothing). I would like a way to say "this photo wearing any of these clothing options" and be able to mark a bunch of the clothing that looks like me.

So, you've been very kind... I've lost a good 10 kilograms which is very generous of you. Unfortunately it doesn't look very realistic! I'm sure that there are others that would like the advantage of dropping a few kilo's at the press of a button. And - maybe big boobs are a thing (hello gender bias in ai/LLN models). I have a smaller chest than Secta would suggest and what's more, it's not the most interesting thing about me. At my age, I don't intentionally like to bring attention to my chest. (I've also noted that in some photos my chest is located unusually low...a verbal prompt to amend this would be very handy! A retouch option for both of these would immediately make the output's more realistic and go a long way to attracting women to your platform. #justsaying

Refine the clothing and background options for different countries. The options I'm seeing are very American - I'm in Australia and our 'look' is quite different whether it's business-formal attire, rural professional or farming. And our farm sheds (not barns) are a completely different style, as is our bushland, forests, crops etc.

Being of mixed racial descent, the AI results were pretty abysmal. My images fulfilled practically every Asian businessman stereotype. It occurred to me that the image capture from photos is flat, but some websites (eg. Mister Spex glasses "virtual try on") already capture the face dynamically. This would enable 3D mapping and give the AI much better training detail to work with. The two inputs combined should be much more effective than photos alone, and would also reduce the dependency on library images (that turned me into a bad stock photo). So how about building this in as an additional feature alongside the photo uploader?

Being able to identify what features have been drawn in the output image (so that I can generate new images with the same features and don't waste credits). E.g. I liked the coat worn in one photo, and wasn't sure which clothing option to choose to get more of the same. This may be reduntant if regenerating new images using mix-and-match from existing outpots (e.g. the background from photo A, expression from photo B).

Being able to specify what I like about each particular photo at the input stage (and want to see more of in the output). E.g. I might like the perfect haircut from photo A, the nicest smile from photo B, the best eyebrows from photo C). This could be either with a free-text field next to each image (serving as a prompt to the AI), or some kind of selector paint brush tool where I can highlight the bits I like on certain photos