Thanks but it doesnt work. It takes the reference from image of the product and creates similar images. What I am looking for is to use the same product image
The specification of exactly what you want probably needs to be refined, but for that it's probably helpful on your end to know what is available and what is needed.
There are different methodologies for taking Stable Diffusion and adding some new concept (like a product with some images) to it. Hypernetworks, textual inversion and dreambooth are three methods.
I was trying to put the concept of specific people that I had a number of good photos of into Stable Diffusion. They say for images of people that dreambooth is better than hypernetworks and textual inversion, and it was. Hypernetworks were nowhere near as good for pictures of people, but I got a good picture once in a while. I never got anything good from textual inversion for pictures of people.
A more recent technique that is being used to put new concepts into Stable Diffusion is LoRa. I'm not that familiar with it but it being used and is another alternative method.
I have an Nvidia RTX 3060 card and spent hours (sometimes a day) making each model, and usually I had dozens of decent pictures (sometimes over 100) of each subject. It came out well. I needed a number of high quality photos from different angles of each subject. Not just from different angles but some full body shots, mid body shots and then some shots of just the face. Also if they were wearing glasses in 95% of the photos, most of the output would have them wearing glasses. Also if most of the photos I had were of them in group photos and I could barely crop their face out from the faces around them in the group shot, it was harder to do.
If you're willing to put in a little work it's possible, but you're going to have to get your product rendered or photographed at the angle you want it to appear in the photo, then mask the product while having the AI generate the rest of the image.
I've done this with some success using t-shirt mockup templates to get the color, shadows, folds and creases in the clothing right then regenerated everything around the shirt.
