Take the motion from an existing video, and replace the character with a character with a reference image.
Basic WAN VACE WORKFLOW using GGUF - Take a video and replace character with character from image.
Use Motion from a VIDEO
Replace the character in the video with the IMAGE REFERENCE
LOW VRAM
--------
You may wan to use the a different GGUF model, a smaller version
Same goes for UMT text encoder
https://huggingface.co/QuantStack/Wan2.1_14B_VACE-GGUF/tree/main
Wan2.1_14B_VACE-Q3_K_S.gguf (try this for low vram 7.8GB versus 18.7 GB for Q8)
Description
Initial release
FAQ
Comments (1)
can you do a no low vram workflow for wan 2.2
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.