ComfyUI product photography composite + relighting workflow #comfyui #stablediffusion #relight

product photography composite + relighting workflow

This workflow is specifically designed for product images but works well with various types of images. It allows for seamless integration of the product into a new environment, intelligently adjusting lighting and colors while preserving the original appearance of the object exactly as it was photographed.
#comfyui #stablediffusion #controlnet #relight #composition #aiphotography

workflow

[ZergRadio]

Very interesting, gonna try this one.
Thanks for you hard work man!

[johannaklammer]

Hi, great video! Can you tell me how to insert a product photo into a specific uploaded image using coordinates? So that the style in your video is not applied, but my uploaded background is simply used! At the same time, so that the size and location of the object can be changed

[YannBula]

is this your voice or an AI voice? doesn't sound bad, just curious lol. thanks for the vid

[JulianSiregarKph]

Very interestng, but i have some error when i run the workflows

Error occurred when executing LaMaInpaint:

The size of tensor a (416) must match the size of tensor b (424) at non-singleton dimension 3

[MerlinStark-iglt]

I always get an error: KSampler
Input channels 20 does not match model in_channels 8, 'opt_background' latent input should be used with the IC-Light 'fbc' model, and only with it
I didn't changed anything and didnt use the opt background. just foreground like you in your video. Can you tell me what i am missing? The only thing whats diffrent to your setting is, im using the v1/1 stablediffsuion v1.5.safetensor for checkpoint.

[MagaliGrande]

Hi, thanks :) Where I find briarmbg (remove background Mixlab) and in which folder should I put it please? :)