You can click on the link below to try it out directly. If the effect is good, you can deploy it locally
https://www.runninghub.ai/post/1969183959009665026/?inviteCode=sdhs0trb
Fan benefits,register to get 1000 points,daily login 100 points,play 4090!Experience the super power of 48G.
https://buymeacoffee.com/a592991299o
The heavyweight model Wan Ultimate, this workflow version is KJ version and has been tested to be better than ComfyUI version. This model still has great potential for exploration and currently supports role replacement and action migration. I have noted the usage instructions in the workflow and feel free to consult if you have any questions.
Suggested configuration:
16GB video memory: 480p
24GB video memory: 720p
Model download address:
relighting-lora： https://huggingface.co/Kijai/WanVideo_comfy/blob/main/WanAnimate_relight_lora_fp16.safetensors
Kijai moderator model: https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/tree/main/Wan22Animate
Kijai version of gguf model: https://huggingface.co/Kijai/WanVideo_comfy_GGUF/tree/main/Wan22Animate
Comfyui official model download link: https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/diffusion_models/wan2.2_animate_14B_bf16.safetensors
KJnodes project page: https://github.com/kijai/ComfyUI-KJNodes
Kj wanvideo warp project page: https://github.com/kijai/ComfyUI-WanVideoWrapper
Description
FAQ
Comments (2)
I got this error msg. (win10) Spent hours with chatgpt trying to fix to no avail, any ideas?: torch.backends.cuda.matmul.allow_fp16_accumulation is not available in this version of torch, requires torch 2.7.0.dev2025 02 26 nightly minimum currently
any of these types of workflows set for a 8G VRAM out here? these seem very interesting