VACE Skyreels V3 R2V Merge — GGUF GGUF quantized versions of Inner Reflections/VACE Skyreels V3 R2V Merge for use with ComfyUI GGUF. This is a merge of Wan 2.1 VACE with SkyReels V3 R2V by Inner Reflections, enabling VACE controlled reference to video generation. See the original model card for full details on capabilities and workflows. Quantizations Available Filename Quant Type Description wan 14B vace skyreels v3 R2V e4m3fn v1 Q4 K M.gguf Q4 K M Smallest, good balance of quality and size wan 14B vace skyreels v3 R2V e4m3fn v1 Q5 K M.gguf Q5 K M Recommended, better quality with moderate size Usage 1. Install ComfyUI GGUF custom nodes 2. Place the .gguf file in ComfyUI/models/unet/ 3. Use the Unet Loader (GGUF) node in your workflow 4. For workflows, see the original VACE Skyreels repo and the VACE Phantom repo (same workflows apply) Conversion Notes Quantized from the fp8 (e4m3fn) source weights This is a VACE variant with two 5D tensors ( patch embedding.weight and vace patch embedding.weight ), which required a modified convert.py to handle correctly Conversion done using city96/ComfyUI GGUF tools with a patched handle nd tensor method for multi 5D tensor support Credits Origi…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy