ComfyUI Relighting ic-light workflow

[@paganiriccardo]

Another step further in terms of control in sd. Thanks very clear explanation

[@PixelEasel]

thanks!

[@honyeechua9670]

perfect workflow what i looking for !

[@PixelEasel]

thanks! happy you find it!

[@keios8862]

the results are quite nice, I'm looking forward for SDXL version.

[@PixelEasel]

definitely

[@DJVARAO]

Thank you! amazing new nodes.

[@PixelEasel]

it's really nice!

Amazing. Thank you :)

[@PixelEasel]

thx!

[@ferencczuczor7766]

Great tutorial, Thanks! How does this work on full body photos? I am getting distorted faces :-( Thanks a lot

[@PixelEasel]

thanks! like any sd 1.5, you can use reactor

[@daryladhityahenry]

Hi! Do you know how to make IC light try to set light from the front? I always get the light from the back side.. And it's confusing since the masking only 2 dimensional. lol :D

[@ojciecvaader9279]

great... I wonder if it can simulate photo studio with controling lights...

[@PixelEasel]

thanks! I think that in the near future it will be possible

[@RussellKlimas]

I keep getting this error: Error occurred when executing FrequencyCombination: operands could not be broadcast together with shapes (1024,3,1024) (64,3,64) Suggestions?

[@minhnhatminhnhat7386]

Thanks alot

[@PixelEasel]

you welcome!

[@_kato_chi_]

Hello, good afternoon, could you help me? I am having a problem with the IP-Adapter, I am using the following models checkpoints= realisticVisionV51_v51VAE.safetensors ic-light= iclight_sd15_fc_unet_ldm.safetensors clip_vision= model.safetensors IPAdapter= ip-adapter-plus_sd15.safetensors but I get this error Error occurred when executing IPAdapterAdvanced: Error(s) in loading state_dict for Resampler: size mismatch for proj_in.weight: copying a param with shape torch.Size([768, 1280]) from checkpoint, the shape in current model is torch.Size([768, 1024]). How should I do to correct this error? Thank you very much in advance, it is the best video I saw that explains how to correctly use ic-light in comfyui

[@PixelEasel]

not sure, if u use any resize node , try to replace it with another

[@DoHoan_FX_Supervisor]

I'm not sure why even though I have a good VEA foreground, it seems to still be undergoing modifications, which is not what I intended.

[@PixelEasel]

not sure what do you mean

[@antonmanukyan3307]

the mask is not created, the image appears to be in the background instead of the foreground

[@PixelEasel]

what do you mean?

[@AlexDisciple]

I've tried this but the faces end up getting really messed up. Is there a trick to preserving the face quality?

[@HemantkumarSharma-n1s]

You can upscale the image that can help also before creating the initial image you can use the IP adapter

[@PixelEasel]

you can use reactor as last step

[@finetuners]

Too bad there's no SDXL

[@PixelEasel]

will have different solutions soon