StellarBeing25

> this will be taken a look later since it needs more considerations Please move the Batch Folder and Batch Upload together under a Batch tab and restore the Multi...

FaceID portrait IP-Adapter requires 5 input face images to create better likeness which will now become so tedious to use without multi-input, please consider adding it back.

Just found FaceID portrait is not even working with 5 control units and generating artifacts.

Just wanted to add that this feature is already present in Rope face swapper app. Here is the demo video showing combine source faces feature - https://www.youtube.com/watch?v=zsgRc3opT68

Nice, but is it possible to faceswap directly with multiple source faces without creating a model first so that reactor can be directly used in the workflows with multiple face...

Just wanted to add that the IP Adapter node in ComfyUI got updated with new features like setting embeds combine methods that would be only possible in invokeAI with multi-input...

IP adapter v2 is just an updated node for ComfyUI with new features like the combine embeds method and weight type with style transfer support. It would be nice to...

I just want to set the default resolution of SD 1.5 models similar to SDXL resolutions, so HRF enabled or disabled would be enough for me, not sure about others.

> We are working on making it more flexible. It would be game changer for whole SD community if you all can make it work without face position ControlNet like...

Please also add combine_embeds and weight_type settings. The combine_embeds set on "average" gives better results in Face IPAapters with multiple face image input, and the weight_type set on "ease in"...