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/1969225393628717058/?inviteCode=1cqzbf7a
Fan benefits,register to get 1000 points,daily login 100 points,play 4090!Experience the super power of 48G.
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 (19)
is this can use in nsfw?
Perhaps, but it will take some time for this technology to be perfectly replicated on ComfyUI.
@WarmBlood_Aban thanks for replying.. I wonder somebody
have a successful case to share
그냥 그럴 시간에 야동을 봐라 왜 첨단 기술을 갖고 그런거 밖에 생각을 못하니
In the DEMO VIDEO, the motion from the provided video clip is copied and applied onto the supplied image.png, whereas this workflow copies the content of the image (e.g., a character, a face) and pastes it onto the provided video.
Can you create a WF to be able to do exackly as at demo video from wan22 ?
its just a rearanged workflow from kijai - you might have better luck https://github.com/kijai/ComfyUI-WanVideoWrapper/blob/main/example_workflows/
At present, this is the best workflow I have tried, which can reproduce 80% of the official effect. To perfectly reproduce it, it probably depends on the official effect of ComfyUI.
no one on here makes shit any good, it's all garbage lmfaooooo none really ever work, well not the kind that make you download sketchy crap. lmfao
@AIGC_Singularity 100% a lie lfmao
And that's why I stopped using WAN. So stupid.
And that's why I stopped using civitai. So stupid.
why is it stupid? i dont understand?
@kjj432 Begause NSFW yellow, 2) begause its have error on start and nothing happen 3) Begause have stupid tag filter on School uniform, school, teenage, and i have 3 days ban begause stupid auto algoritm think its TOS content. 4) Remix lora its over 2+ dont can generate its not start or doing Pixeled images. and more more.
Local+ Comfyui+Automatic best. i have 3090 nvidia. . But only need this its Civitai link Program.
@meikerAI3d yeah making it work locally is a hassle for normal users but it is worth it
can you add lora node? for me it always censores. it is so annoying
Is there a way to bypass sage attention? I've never been able to get triton or sdae attention working on my pc :/
You can use your Python and PyTorch versions to find the wheelchair at Huggingface and install it with just one click. Or you can tell me the versions of Python, PyTorch, and CUDA, and I will find them for you when I have time. I will send you the link so that you can operate them.
select "sdpa" in attention mode
try install wheel
if you're on comfyui (python313)
https://huggingface.co/Wildminder/AI-windows-whl/blob/main/sageattention-2.2.0.post3%2Bcu130torch2.9.0-cp313-cp313-win_amd64.whl