Feature Requests

I would like to upload several images of myself and my family to build a private database that includes us. This would allow me to include one or more of us in my descriptions and have images generated that include us. This functionality seems feasible with some coding adjustments.

Hi, please advise how we can make remix using reference image weight like the share images, he one named Rf.1 i used it as reference to force the generated image directions to math the Ref image but not to be merged with it, this feature is available on ideogram along with cinematic styles which are the only valuable feature with ideogram, if we got it in recraft it would be artistic add value feature

Would be very happy with the ability to highlight multiple images and then have the option to either upscale, or upscale and then creative upscale and it put in a queue so we can come back when it is complete with a zip download, as it can be time consuming waiting around

Nice feature like in Krea AI. So you can go more creative and have more controls on the output. When you can control the significance (strenght)of each image. Also it would br nice to add more upscaler models for more smooth upscaling (resizing) without make image soapy and with lots of unessesary artifacts. Espessialy when working with photorealism,photography (kind of Scunet,DAT or ESRGAN models). And one more thing: it would be realy good if we can edit custom styles,see what images it containes to replace some assets if needed and tweak it more for more accurate styles results.Thanks. Big Ups Recraft team! Love your product!

When choosing the style it's great that we can pin to the top our favorites, that's really helpful and time saving. But it would be great to be able to drag to reposition them in the order we want. Currently when you add a new one it comes out at the front, but usually it's not my most used style. So I find myself having to de-pin all of the styles instead of the new one, and then pinning them back in the reverse order of how I want them to appear. That defeats the purpose of time-saving and is going to limit the usefulness of this feature as I will get to a point where I won't add new styles. It would be easy to fix this by allowing us to drag and drop to position them how we want. I added this as a previous feature request, but within a project having the style persist for each new image instead of resetting to the default V3 Raw would be great too.

Hello, I want to download the image set section as SVG in bulk, not individually.

All of the Illustrations we create are only rendered at 96dpi, irrespective of the size of the image we create. This makes it too low for good printing. We can of course upscale or upgrade it but it still renders at 96dpi. Whilst we can create an SVG, the styling comes out better in the Illustration mode. So, please, can you give us the option to choose 300 DPI when creating larger images for printing?

Asian facial expressions are very lacking. Please add features like IP Adapter to make it easier to create different face styles. It's an open source technology.Of course, it would be best if you could provide a character training feature like Freepik ai, but the IP Adapter feature is a good option for a quick try.Please see the link below. https://github.com/tencent-ailab/IP-Adapter

Close-Up, Side Profile, Extreme Close-Up, Medium Close-Up, Medium, Rear-View Over-The-Shoulder, From Behind, Three-Quarter, Eye Level, Hero, Low Angle, Ground Level, Aerial, Over The Top, Top-Down, High Angle

Generate videos from 2 images. A start and end image as on https://lumalabs.ai/dream-machine