WAN 2.2 💠 T2V / I2V / S2V / T2I🔹4-6 steps🔹Loop 🔹SVI Video extend 🔹WanVideoWrapper Workflow🔹K3NK
NOTICE: IF YOU ARE NEW TO COMFYUI, I DONT RECOMMEND STARTING WITH THIS WORKFLOW, IS AN ALL IN ONE WORKFLOW YOU WILL GET CONFUSED.
I UPDATED v2.3, YOU CAN CHOOSE IF YOU WANT RES4LYF OR WVW SIGMA SPLITTING
Since v1.8 im using subgraphs, you need latest comfyui with the latest frontend updates, also probably you will need to update Comfyui Manager.
For me was: setting nightly vers on the manager then update confy from the manager too.
* i allways leave the image overlay enabled, it will error if you dont have an image on it, sorry :S
v2.0
You can choose whether to merge with the loras or not, change the lora connection from the model loader to the set loras node, after that uncheck merge_loras
The toggled i added for radial sage, requieres Sage Attention to be installed, if you dont have it you should unplug the conexion i made to the attention type on the model loaders..
Be sure to update WanVideoWrapper nodes ..
The workflow works just fine with Wan2.1 if you bypass first sampler and model loader
This workflow is included with all my uploads as metadata, drag and drop a vid to comfyui.
I run a 4090 locally
You can use it as other modes if you activate this option for enabling the required nodes.
Make sure you load the correct models on the model loaders
Kijai's WanVideoWrapper Node
Wan2.2 Kijai's models
Lightx2v LoRa needed for lower steps (faster generations)
Wan22-Lightning Lightx2v alternative, newer and better in some scenarios
NSFW Clip Vision (not really needed in wan2.2)
RES4LYF Nodes
MMAUDIO
https://huggingface.co/Kijai/MMAudio_safetensors/tree/main
once installed replace nodes.py file in the mmaudio node folder with this one: https://github.com/phazei/ComfyUI-MMAudio/blob/master/nodes.py
WAN 2.2 💠 T2V / I2V
MMAUDIO NSFW
https://huggingface.co/phazei/NSFW_MMaudio (download and rename it to "mmaudio_nsfw_large_44k_v2_fp16.safetensors")
BOYONODES
K3NK IMAGE GRAB
Description
Duplicated the model and lora loaders, so now theres 1 block for the i2v, another for the t2v, no more need to changing every lora/model every time, set up your paths, then change using toggles.
i udpated some of the switches for it to work with models, also radial sage is optional as allways but only affects the high model. Radial sage gives a lot of errors if you using different sized images in the i2v node so..
Changed lora loaders to multi-loaders
FAQ
Comments (15)
v1.3 works pretty well, Had some great results. But i get the following error when attempting to run v1.4 & v1.5:
Loop Detected TypeError: Cannot read properties of undefined (reading '0') at http://127.0.0.1:8000/extensions/cg-use-everywhere/use_everywhere_utilities.js:196:81 at Array.findIndex (<anonymous>) at find_all_upstream (http://127.0.0.1:8000/extensions/cg-use-everywhere/use_everywhere_utilities.js:196:48) at recursive_follow (http://127.0.0.1:8000/extensions/cg-use-everywhere/use_everywhere_utilities.js:228:5) at recursive_follow (http://127.0.0.1:8000/extensions/cg-use-everywhere/use_everywhere_utilities.js:221:16) at http://127.0.0.1:8000/extensions/cg-use-everywhere/use_everywhere_utilities.js:230:17 at Array.forEach (<anonymous>) at recursive_follow (http://127.0.0.1:8000/extensions/cg-use-everywhere/use_everywhere_utilities.js:228:45) at http://127.0.0.1:8000/extensions/cg-use-everywhere/use_everywhere_utilities.js:230:17 at Array.forEach (<anonymous>), undefined
i dont recall using those cg-use-verywhere nodes in this workflow.. maybe a conflict, try moving that node out of the folder to test if works without it
get image size ? not found
You need masquerade-nodes-comfyui
Love your workflow, however 1.5 renders black videos for some reason. I am rolling back to the older work flow till fixed. Also, would be amazing if you could have a toggle to turn off the block swap, for those of us with 5090 cards that might not require it. Thanks again for all your dedication to the craft and for releasing these for all :)
((((((
Error
Loop Detected TypeError: Cannot read properties of undefined (reading '0') at http://127.0.0.1:8188/extensions/cg-use-everywhere/use_everywhere_utilities.js:196:81 at Array.findIndex (<anonymous>) at find_all_upstream (http://127.0.0.1:8188/extensions/cg-use-everywhere/use_everywhere_utilities.js:196:48) at recursive_follow (http://127.0.0.1:8188/extensions/cg-use-everywhere/use_everywhere_utilities.js:228:5) at recursive_follow (http://127.0.0.1:8188/extensions/cg-use-everywhere/use_everywhere_utilities.js:221:16) at http://127.0.0.1:8188/extensions/cg-use-everywhere/use_everywhere_utilities.js:230:17 at Array.forEach (<anonymous>) at recursive_follow (http://127.0.0.1:8188/extensions/cg-use-everywhere/use_everywhere_utilities.js:228:45) at http://127.0.0.1:8188/extensions/cg-use-everywhere/use_everywhere_utilities.js:230:17 at Array.forEach (<anonymous>), undefined
You need to update your ComfyUI
@noairi151 WanVideoSampler
FileNotFoundError: [Errno 2] No such file or directory: 'C:\\Users\\aaaa\\AppData\\Local\\Temp\\torchinductor_aaaa\\triton\\0\\HVQFJUMSOPV4EXRMCSBBQWTQKYCNAAHURATPVV4FIKRNQFOYDJ2A\\tmp.pid_20900_f98688cf-1c0b-4ec1-8f7f-a3f071db09d0\\__grp__triton_red_fused__scaled_dot_product_efficient_attention__to_copy_add_mean_mul_pow_2.json' Set TORCHDYNAMO_VERBOSE=1 for the internal stack trace (please do this especially if you're reporting a bug to PyTorch). For even more developer context, set TORCH_LOGS="+dynamo"
@noairi151 These workflows are only for the chosen ones))) I have been trying to launch versions 1.3-1.5 for several days now, and I have never been able to launch even one generation. Even if I drag your finished video into the workflow and launch the generation, errors appear that I have not enabled some nodes, but how then was the video generated with these nodes not enabled?)))
@Crescend_Flower Try disable the torch compile node next to the VAE loader node, above the LOW model loader.
Go to your custom-nodes folder and move your "cg-use-everywhere" folder in a temporary folder. This is what fixed the "loop detected typeerror...' for me.
Just a QQ as a newbie - I've being using the lightning I2V loras set to strength 1 and the scaled models linked in the description (I2V A14B fp8 e4m3fn) but my outputs are very grainy. Otherwise, all the other settings are as default, outside of enabling I2V. What am I doing wrong?
No SetNode found for results_04(GetNode). Most likely you're missing custom nodes
Also, cannot find any missing nodes. I have the ComfyUI-KJNode Set installed
thats what i said in the description, you can bypass the nodes in the combiner section that are not used, but the moment you toggle the whole section they will become enabled again, just ingore those warnings
@K3NK ack, Im so sorry.
@singularity42 dont worry, im trying simplifying this by using node grouping, by starters, the get/set nodes does not work if you group them, im still figuring out if it can be used..