Input Guidlines
In order to get the most out of the Kaedim Platform we have some guidelines on the types of images we accept for processing, as well as what will most likely get dismissed.
At Kaedim, we are focused on creating individual models, primarily for hard surface objects, used to populate games and Metaverse environments.
✅ Single object- Please make sure your image illustrates a single object.
- Requests of whole scenes involving multiple objects will be dismissed.
- Characters with a lot of accessories or armoury on them will have to be passed separately from them. Learn more at Characters
- When using the multiple images option, all images have to be of the same object, but from different points of view. Learn more at Single vs Multiple Image Inputs
✅ White background- Your object needs to have a white or monochrome background.
✅ Photo/Art/Sketch- Your 2D input can be a photo of an object, a piece of concept art or a sketch (pencil/pen and paper).
✅ Clear- Object clearly in the foreground of the image, no blurry images.
Below are some examples of image requests that may not be processed
Given that text is not an individual 3D object it may not be processed. If the image is primarily of an object but has some lettering on, this should be okay.
This includes any nude or sexual content, offensive imagery, blood and gore etc. Any images of this type will be automatically dismissed.
If it is not obvious in the image which single object you are wishing to have processed, your image may not be processed. We are focused on creating individual objects, so attempts to request multiple objects in one image request are outside the scope. Separate them and pass them as individual requests.
If you are trying to pass really complex characters or hero assets that wear a lot of clothing and accessories, this will probably not get processed. We would encourage you to try and separate the different parts as much as possible. For example, pass clothes as different pieces, armoury and accessories as different requests each of them. Learn more at Characters
Due to the lack of 3D data in the field of realistic humans, this is a category we are not servicing yet. If you upload your selfie, sorry, but it will get dismissed. However, all other cartoonish characters and anthropomorphic creatures will get generated.
Similar to the above, but we encourage you to try. Usually, the output will be a simplified version (without fur etc.)
A realistic full-grown tree will probably get dismissed. However, simpler greenery and/or stylised greenery should be okay.
Having said that, feel free to experiment with different inputs as sometimes the software surprises us!
Note: For your own safety, please never upload inputs that illustrate any personal information or any means of identifying yourself (i.e. passports, ID, address).
Last modified 26d ago