MoonMoon82
MoonMoon82
I still have some hope this attention mask node could be developed..
My hope is fading :-(
Hi @shawnington , how does this commit (https://github.com/comfyanonymous/ComfyUI/commit/0fecfd2b1a2794b77277c7e256c84de54a63d860) solve the missing attention mask for LORAs ?
Same issue, last commit e5ed9fcc
@BlenderNeko Maybe you have an idea how this "reference_only" preprocessor could work in comfyui ?
@addddd2 I opened a feature request some weeks ago to get something like img2img with reference_only node: https://github.com/comfyanonymous/ComfyUI_experiments/issues/5 I already tried it on my own, but I guess this kind...
@taabata There already was an discussion about it and sovled it: https://github.com/comfyanonymous/ComfyUI/discussions/603 now there is a inpainting preprocessor available: https://github.com/Fannovel16/comfy_controlnet_preprocessors which works quite well so far
@MaddyAurora Thank you for your detailed feedback ! I already noticed that some checkpoints come with more or less usefull VAEs, so I tended to use a separate VAE file...
This is never going to be implemented, isn't it?
@AlexD81 , @manzonif , @jakeute, @suede299 I found these two custom nodes in AnimageDiffEvolved which seem to do what I was searching for: ADE_RegisterLoraHook  ADE_ConditioningSetMaskAndCombine  The first node...