how do u load these mega models?
hi, i have a question, these mega models are suppose to have the clip and vae with them, right?(that's the only difference they have, other than being TI2V, right?
how do u load a gguf model? i mean which node has this option to load vae and clip with the gguf model?
thx and great work.
You have seperate nodes for model (load unet gguf) + clip text encoder (load clip gguf for gguf or load clip for umt5 scaled text encoder) + vae (load vae - default wan2.1 vae)
You have seperate nodes for model (load unet gguf) + clip text encoder (load clip gguf for gguf or load clip for umt5 scaled text encoder) + vae (load vae - default wan2.1 vae)
thx, then i have to load the clip and vae separately? so the only benefit they have, is being the combined model for Text and image to video, right?
You have seperate nodes for model (load unet gguf) + clip text encoder (load clip gguf for gguf or load clip for umt5 scaled text encoder) + vae (load vae - default wan2.1 vae)
thx, then i have to load the clip and vae separately? so the only benefit they have, is being the combined model for Text and image to video, right?
yep.
can we please get a workflow