This is the bones of my Hunyuan Video Extender this time with EVEN LESS extending, cos that only ever kinda worked and is now obsolete anyway, yay for framepack. I've removed Anything Everywhere nodes so this works with the current version of Comfy and compressed everything as much as possible.
Single Txt2Vid/Img2Vid/Vid2Vid processes all linked to the same Lora controls governed by a switch. Runs a small first pass to get a vague idea of a latent at 6 steps then iterates on that at 12-16 steps (your mileage may vary) to produce a better result. RIFE nodes can be bypassed.
Vid2Vid can be a little cranky with resolutions but 480x320 vids usually play nice.
Suggestions for improvements appreciated.
hunyuan_video_image_to_video_720p_bf16.safetensors - v1 (concat)
hunyuan_video_v2_replace_image_to_video_720p_bf16.safetensors - v2 (replace)
Description
FAQ
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.