---
title: Wan_Dancer_GGUFs
canonical_url: "https://www.modelscope.cn/models/realrebelai/Wan_Dancer_GGUFs"
md_url: "https://www.modelscope.cn/models/realrebelai/Wan_Dancer_GGUFs.md"
repository: realrebelai/Wan_Dancer_GGUFs
last_updated: 2026-07-18
license: apache-2.0
base_model:
  - Wan-AI/Wan-Dancer-14B
base_model_relation: quantized
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
downloads: 295
stars: 1
tags:
  - wan-dancer
  - music-to-dance
  - quantization
  - gguf
---

# Wan_Dancer_GGUFs

> Wan_Dancer_GGUFs - realrebelai 在 ModelScope 开源的模型。REDOWNLOAD QUANTS IF YOU ALREADY DID. THEY PREVIOUS QUANTS WERE CORRUPT!

realrebelai/Wan_Dancer_GGUFs 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可，基于 Wan-AI/Wan-Dancer-14B 构建。

- **Repository**: realrebelai/Wan_Dancer_GGUFs
- **License**: apache-2.0
- **Base model**: Wan-AI/Wan-Dancer-14B
- **Tags**: wan-dancer, music-to-dance, quantization, gguf
- **Downloads**: 295
- **Stars**: 1
- **Last updated**: 2026-07-18

Source: https://www.modelscope.cn/models/realrebelai/Wan_Dancer_GGUFs

---

<video src="https://cdn-uploads.huggingface.co/production/uploads/68761990332d15464ccc8dee/nngAubty5iJDp7iYisq0o.mp4" autoplay loop muted playsinline width="30%"></video>


# REDOWNLOAD QUANTS IF YOU ALREADY DID. THEY PREVIOUS QUANTS WERE CORRUPT!

Wan-Dancer is a hierarchical framework for minute-scale coherent music-to-dance generation.


# REQUIRES THE FOLLOWING FILES:

## YOU NEED BOTH THE GLOBAL AND LOCAL MODEL (SIMILAR TO WAN 2.2 MODEL FILES WITH HIGH AND LOW)

- TEXT ENCODER - https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors
- VAE - https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/vae/wan_2.1_vae.safetensors
- CLIP VISION H - https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/clip_vision/clip_vision_h.safetensors
- DISTILL LORA - https://huggingface.co/lightx2v/Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v/blob/main/loras/Wan21_I2V_14B_lightx2v_cfg_step_distill_lora_rank64.safetensors


workflow includes Rebels Audio Nodes for editing audio pre-generation if needed - https://github.com/RealRebelAI/Rebels_Audio_Nodes