NODE FIX: The latest Comfy update broke the WaveSpeed (applyFBCacheOnModel) node. I have replaced it with an equivalent tea cache node, so you can retain same speed and quality outputs. This node should also be in Comfy Manager, so it will be easier to install and keep updated.
People keep asking me for my workflow, so I'm sharing it here. It honestly isn't anything special and I haven't bothered trying to optimize it much after I hit the sweet spot with it a few weeks ago. It is very likely that there are faster/more efficient ways to get similar results now.
The workflow used to have TorchCompile included in it, but it wasn't giving any perceived improvements and causing issues with my comfy, so I took it out. Feel free to add it back in if you would like to try to gain the speed increase and VRAM reduction with it.
The settings in this are what I produce my videos at. I sometimes upscale using the optional Simple Upscale, but a lot of the time it is quicker for me to take the original video output and pass it through Topaz. To be honest though, the initial video is decent enough to post even without upscaling. If you want to get fancy with it, change the simple upscale to an upscale with model.
On at 4090FE with 24gig of VRAM, I get the following:
89 frames = average of 11s/it, which equates to roughly 3 minutes to gen
121 frame = average of 14s/it, which equates to roughly 4 minutes to gen
145 frames = average of 22s/it, which equates to roughly 5.5 minutes to gen
Feel free to try lower frames with bf16 model too. I use fp8 to max out my frame count.
Mileage may vary for others. Enjoy!
NOTE: If you can't find the node title "applyFBCacheOnModel" in comfy-manager, you may have to install it manually from here: https://github.com/chengzeyi/Comfy-WaveSpeed?tab=readme-ov-file
Description
WaveSpeed node broke with last comfy update. Replacing with another tea cache node.
FAQ
Comments (9)
FOR THOSE HAVING ISSUES WITH "applyFBCacheOnModel"
Navigate to you're ComfyUI folder and go to: \ComfyUI\custom_nodes
in the address bar type in CMD and run this command below:
-----------------------------------------
git clone https://github.com/chengzeyi/Comfy-WaveSpeed.git
-----------------------------------------
This will install the WaveSpeed custom nodes. If ComfyUI is already running. Restart comfy and refresh your browser. That should do it!
Works perfectly, thanks. What is the max resolution and frames/length in portait you can go with your 4090FE? The 432x768 @89 frames ran about 2:32 @10.86s/it for me, pretty fast. I would like to go higher but my VRAM looked like it was already using over 20. I'm on a 4090 (Asus OC) too.
Incredible.
Oh yeah! Thank you for the wisdom, sir
Wanted to let people know that this actually gives very high-quality results in general, and not just NSFW stuff.
What should i get for the upscale model?
Getting error Missing node type applyteachache patch. Using node manager, after downloading and restarting, still get error with node option to try to fix in manager but doesn't fix. anyone else have this issue?
Just curious if you have tried the AccVideo Huny models? They seem much faster, but I am wondering what all optimizations and so forth can still be applied.
I'm a bit of a novice. Can I run this with 8gb vram? If yes, can you explain? Which models should I use?
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.