CoolFace
Modelpublic

BlackStone-Yu/VACE_Skyreels_V3_R2V_Merge-GGUF

sourceHugging Faceupdated 3mo agoView on Hugging Face
0likes102downloads
Model Card

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

FilenameQuant TypeDescription
wan-14B_vace_skyreels_v3_R2V_e4m3fn_v1-Q4_K_M.ggufQ4KMSmallest, good balance of quality and size
wan-14B_vace_skyreels_v3_R2V_e4m3fn_v1-Q5_K_M.ggufQ5KMRecommended, better quality with moderate size

Usage

  1. 1.Install ComfyUI-GGUF custom nodes
  2. 2.Place the .gguf file in ComfyUI/models/unet/
  3. 3.Use the Unet Loader (GGUF) node in your workflow
  4. 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