For more Workflows and updates, Join my Discord:
This is probably the most dumbed down and reliable version of Wan 2.2 I2V workflow you can find.
Great if you're a beginner, or advanced enough to realize that basic wins every time.
Description
Added a single LoRA loader (Will add more once I test)
Added nodes for removing the first 6 frames of the video, these are mostly junk frames that are static and hurting the flow of the video
FAQ
Comments (34)
Is it really 48 FPS? your description shows, but code looks like its 32FPS. Is there a clean way to get a 48 FPS output from wan?
My bad.
That's 32, I'll fix it.
You can interpolate times 3 tho.
Do I need to connect some wires?
Error:
KJ Get/Set
No SetNode found for upscale_1(GetNode). Most likely you're missing custom nodes
The Comfy Videao helpersuite node seems to float unattached to anything.
Sorry, I'm new to Comfyui...
Please install the missing nodes via the manager.
I'm using get set nodes to reduce clutter.
I am testing the LoRa workflow:
Comfyui refuse to download ComfyUI-WanVideoWrapper from the manager for security reasons, so I install it manually, but I got this error:
LoadWanVideoClipTextEncoder
'log_scale'
check here: https://ibb.co/Xfbcgh92
Any help?
Did you update ComfyUI to the latest version?
Did you find a solution for this?
@Hearmeman Yes, its already up to date
@gastonarte Not yet! I will try t refresh install of comfyui and back to you
I did another
1. fresh installation of comfyui + comfyui manager.
2. Load the workflow and got these missing nodes:
Missing Node Types
SetNode
GetNode
The manager does not show any missing nodes
@90Splash
Search for KJNodes in the Custom Nodes
@Hearmeman It works, just stuck with "sageattention":
Can't import SageAttention: No module named 'sageattention'
I have to install it
I am also have the same issue with log_scale after updating everything
@i_love_potatoes the SageAttention error?
@90Splash Change the attention mode from sage_attn to flash_attn or sdpa.
@Hearmeman yes, it should work, but it seems the workflow is super heavy on my RTX 4090 (48GB RAM) laptop, so it crashes!
@90Splash Use FP8
A laptop RTX 4090 is not a desktop RTX 4090
@Hearmeman I will give it a shot, thanks for the support!
@90Splash Thanks for the buzz buddy!
Thank you! Could you please upload a workflow that just does the frame interpolation part? I have some videos I've already generated that could use the upscale and FI. I think other people would find that very helpful as well. Please and thank you!!!!
I'll have to use a GGUF. Even the fp8 Wan model crashes comfy oh well. I'll try that lora though in my GGUF WF since it runs pretty quick
On Runpod, what template do you use when you deploy?
It's too slow for a 12G Vram device, is it possible to create a workflow with GGUF loader? Thanks!
This is somewhere in my to do list, stay tuned
could you upload the latest workflow with native comfyUI nodes?
Will do it probably tomorrow
@Hearmeman Pleaaase! hahah
Hey hey @Hearmeman would it be possible to share the comfyui workflow, for the videos you made where girls doing a boobs job? I have set your RunPod docker, however there is no lora node to setup. If I can buy that workflow, that would be fine too
@Coltson When did you set up my RunPod docker?
The workflows starting with Wan_Video have LoRA support.
the native one don't, working on it.
@Hearmeman I have setup just 30 minutes back my runpod. I found there a template Wan_Video_Text2Video-Upscaling-FrameInterpolation.json is this workflow used in the b*bs videos you showcased, please?
@hadeng @mirtmirt done
I sent you a DM bro! :)
Ever considered 'Bro' might be 'Sis'?
;)
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.