kijai
24683f1dad
commit 6a01a8a1d80d36b5b8ac979a36069c8eb0c2f9a7
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Thu Aug 14 15:40:50 2025 +0300
Update wanvideo_2_1_I2V_FantasyPortrait_example_01.json
commit e3cf4bf5bc13321e6d8f91fcb7ee92210a7adf01
Merge: bbf14ec f3d5f6b
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Thu Aug 14 15:08:53 2025 +0300
Merge branch 'main' into fantasy_portrait
commit bbf14ec9e9965c1a8582eea02b50913e79a036d0
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Thu Aug 14 02:16:11 2025 +0300
update
commit 8192f9f4302b3933e48641a8ef313929e3e263aa
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Thu Aug 14 01:46:15 2025 +0300
progress bar, fix context windows
commit 39fab8ad4d950a974ba49bd177814f30f518b478
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Thu Aug 14 01:29:15 2025 +0300
Update nodes.py
commit 36f472c0134e6342ab8c2062a7e3f0b0c829003b
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Thu Aug 14 01:14:24 2025 +0300
Add start/end percent
commit 16f5922c6bc575754412c9b473907377562b956c
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Thu Aug 14 00:58:57 2025 +0300
init
ComfyUI wrapper nodes for WanVideo and related models.
WORK IN PROGRESS (perpetually)
Why should I use custom nodes when WanVideo works natively?
Short answer: Unless it's a model/feature not available yet on native, you shouldn't.
Long answer: Due to the complexity of ComfyUI core code, and my lack of coding experience, in many cases it's far easier and faster to implement new models and features to a standalone wrapper, so this is a way to test things relatively quickly. I consider this my personal sandbox (which is obviously open for everyone) to play with without having to worry about compability issues etc, but as such this code is always work in progress and prone to have issues. Also not all new models end up being worth the trouble to implement in core Comfy, though I've also made some patcher nodes to allow using them in native workflows, such as the ATI node available in this wrapper. This is also the end goal, idea isn't to compete or even offer alternatives to everything available in native workflows. All that said (this is clearly not a sales pitch) I do appreciate everyone using these nodes to explore new releases and possibilities with WanVideo.
Installation
- Clone this repo into
custom_nodesfolder. - Install dependencies:
pip install -r requirements.txtor if you use the portable install, run this in ComfyUI_windows_portable -folder:
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper\requirements.txt
Models
https://huggingface.co/Kijai/WanVideo_comfy/tree/main
fp8 scaled models (personal recommendation):
https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled
Text encoders to ComfyUI/models/text_encoders
Clip vision to ComfyUI/models/clip_vision
Transformer (main video model) to ComfyUI/models/diffusion_models
Vae to ComfyUI/models/vae
You can also use the native ComfyUI text encoding and clip vision loader with the wrapper instead of the original models:
GGUF models can now be loaded in the main model loader as well.
Supported extra models:
SkyReels: https://huggingface.co/collections/Skywork/skyreels-v2-6801b1b93df627d441d0d0d9
WanVideoFun: https://huggingface.co/collections/alibaba-pai/wan21-fun-v11-680f514c89fe7b4df9d44f17
ReCamMaster: https://github.com/KwaiVGI/ReCamMaster
VACE: https://github.com/ali-vilab/VACE
Phantom: https://huggingface.co/bytedance-research/Phantom
ATI: https://huggingface.co/bytedance-research/ATI
Uni3C: https://github.com/alibaba-damo-academy/Uni3C
MiniMaxRemover: https://huggingface.co/zibojia/minimax-remover
MAGREF: https://huggingface.co/MAGREF-Video/MAGREF
FantasyTalking: https://github.com/Fantasy-AMAP/fantasy-talking
MultiTalk: https://github.com/MeiGen-AI/MultiTalk
EchoShot: https://github.com/D2I-ai/EchoShot
Examples:
https://github.com/user-attachments/assets/c58a12c2-13ba-4af8-8041-e283dbef197e
TeaCache (with the old temporary WIP naive version, I2V):
Note that with the new version the threshold values should be 10x higher
Range of 0.25-0.30 seems good when using the coefficients, start step can be 0, with more aggressive threshold values it may make sense to start later to avoid any potential step skips early on, that generally ruin the motion.
https://github.com/user-attachments/assets/504a9a50-3337-43d2-97b8-8e1661f29f46
Context window test:
1025 frames using window size of 81 frames, with 16 overlap. With the 1.3B T2V model this used under 5GB VRAM and took 10 minutes to gen on a 5090:
https://github.com/user-attachments/assets/89b393af-cf1b-49ae-aa29-23e57f65911e
This very first test was 512x512x81
~16GB used with 20/40 blocks offloaded
https://github.com/user-attachments/assets/fa6d0a4f-4a4d-4de5-84a4-877cc37b715f
Vid2vid example:
with 14B T2V model:
https://github.com/user-attachments/assets/ef228b8a-a13a-4327-8a1b-1eb343cf00d8
with 1.3B T2V model
https://github.com/user-attachments/assets/4f35ba84-da7a-4d5b-97ee-9641296f391e