This is a slapping together of bits that work to make decent Img-2-Vid, none of it is my work outside of arranging things. I strongly recommend using my <a target="_blank" rel="ugc" href="https://civarchive.com/models/1346892/hunyuan-video-extender">newer WF</a> over this one as it can do moar!(v1.2 -- Double Blocks Loras 'model' output can be linked to the 'model' input on the Flexi Lora Loader node, also added a TeaCache Sampler (with 1.6x and 2.1x speeds) and a VRAM Cleaner.Loras used:<a target="_blank" rel="ugc" href="https://civarchive.com/models/1197600/breast-expansion">Breast Expansion</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/1094156/titty-drop-hunyuan-video-lora">TittyDrop v1.1</a><a target="_blank" rel="ugc" href="https://docs.comfy.org/advanced/hunyuan-video">Img2Vid info and links to checkpoint.</a><a target="_blank" rel="ugc" href="https://github.com/ronsantash/Comfyui-flexi-lora-loader">Info on Flexi Lora Loader.</a> (All I know is varied weights as a vid is sequenced = more coherence)

Hunyuan Img2Vid with Flexi Lora Loader v1.2

Slight alteration to WF a removal of a note and linked the Difffusion model to the Double Blocks Lora loader as it should have been in the first place.

Files with SHA256: b0d1dac8752869faf4f04685d33c1a12b86da9b717acf80f48d9162bee7af2a0