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)
MODELS (GLOBAL + LOCAL):
https://huggingface.co/realrebelai/Wan_Dancer_GGUFs/tree/mainTEXT ENCODER - https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors
CLIP VISION H - https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/clip_vision/clip_vision_h.safetensors
workflow includes Rebels Audio Nodes for editing audio pre-generation if needed - https://github.com/RealRebelAI/Rebels_Audio_Nodes
Description
wan dancer gguf
Comments (3)
Thanks for making this. When I use it, the preview generates fine. But the final video just comes out black with the audio playing. Any suggestions?
the 2nd pass gives me an error in comfyui...
Exception during processing !!! Error while processing rearrange-reduction pattern "b (t n) c -> (b t) n c"
Im not sure, i must appologize though as i dont use this site anymore. Any trouble shooting can be brought to huggingface!
That being said, it seems you may have a mismatch of frame count? Not sure im not by my computer at the moment to troubleshoot.
Id like to add that its not your fault for what im about to say but i have closed down support on this page and site. Too many bad apples ruined the bunch.