Creates a product image for any object in the scene, be that a sitting object, held object, or worn object. It can be triggered with the prompt "make a product image for <object>"
Works best with the Base checkpoints but also works with Distilled checkpoints. If you are receiving any subject or scene bleed, try increasing the strength or adding "white background" to the prompt. Including "mannequin" in the prompt will display outfits on a mannequin rather than floating in isolation.
You can use general terms without being too specific, such as:
make a product image for her entire outfitmake a product image for her topmake a product image for his pantsmake a product image for the held objectYou just need to be specific enough to properly identify what you're looking for. If you get too specific, there's an observed possibility that the base model may attempt to fill in improper details (i.e. during testing, referring to monk robes as 'robes' instead of 'outfit' caused it to fill in incorrect details that would fit more for a bath robe).
California AB 2013 Training Data Disclosure
This LoRA was fine-tuned using visual data consisting of still images collected from product listings, product reviews, and other forms of media that depict the item in a normal setting (e.g. TV stills, and still art). The training data includes copyrighted material owned by third parties. No training data was licensed or purchased. This LoRA is provided for non-commercial use only under the terms of its distribution.
The dataset consists of 53 image pairs (106 images total). Each pair was created by locating a suitable product image and a suitable image of the object outside of a studio setting. Data was collected in 2026.
Image data was processed through standard resizing, cropping, normalization, and labeling steps. Synthetic images and video were not included as part of the training dataset.
This model is intended for non-commercial, experimental, and educational use. Generated outputs may reflect copyrighted visual styles or themes associated with the underlying training data. Users are responsible for ensuring compliance with applicable copyright law, other intellectual property laws, and all other applicable laws.
Description
FAQ
Comments (7)
Not working, i am getting just copy of input image.
Is it require only base model and incompatible with distilled?
For Klein, it was tested with the base models, not the distilled versions. Which version are you using?
Seem to have gotten it to work with 9B distilled using "make a close-up product image for her [object], white background, remove the woman"
This seems to work for me too, thank you very much.
I think I may have a variation of your prompt that seems to be working and can be used as a template:
"Make a close product image for [object], on a white background, removing the person".
Example:
"Make a close product image for top-to-bottom outfit, on a white background, removing the person"
it's great and works really well for me, but I suggest that you add a note to the description. To make it work, people need to use the original Flux.2 Klein 9B BASE from black forest labs. If they are using any kind of merged checkpoint, those checkpoints will naturally be biased to extract also the woman, not just the clothes. the original one will consistently put the clothes inside a manekin using your original prompts, even with complex outfits. I did not test with 4B and Qwen, but I assume they follow the same logic: for optimal results, never use merged checkpoints, always used the original, raw checkpoints.
It doesn't work at all on 4b, I don't understand.