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
- Downloads last month
- 12,264
Hardware compatibility
Log In to add your hardware
3-bit
4-bit
5-bit
6-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for realrebelai/Wan_Dancer_GGUFs
Base model
Wan-AI/Wan-Dancer-14B