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 VIDEOReplace the character in the video with the IMAGE REFERENCELOW VRAM--------You may wan to use the a different GGUF model, a smaller version Same goes for UMT text encoder<a target="_blank" rel="ugc" href="https://huggingface.co/QuantStack/Wan2.1_14B_VACE-GGUF/tree/main">https://huggingface.co/QuantStack/Wan2.1_14B_VACE-GGUF/tree/main</a>Wan2.1_14B_VACE-Q3_K_S.gguf (try this for low vram 7.8GB versus 18.7 GB for Q8)

Files with SHA256: 95106b512f0801bb9e179baf681e625fa2271c822ab7cf53acaa7089da239d65