Faster image and video generation with SDXL, Flux, LTVX and Hunyuan Video is here thanks to the power of caches. Speed up a little - or a lot! TeaCache claims a 1.4x lossless speedup, and at a push I’m e found you can just about get to 3x speedup with images.
13/01/2025 Update: WaveSpeed now also supports SD3.5 as well 😀
These handy ComfyUI nodes are quick to install, and then all you need to do then is pop a cache node into your existing workflow for an instant speed boost!
I put a couple of options through their paces, with some interesting results...
Links:
https://github.com/welltop-cn/ComfyUI-TeaCache
https://github.com/chengzeyi/Comfy-WaveSpeed
Want to support the channel?
https://www.patreon.com/posts/boost-sdxl-flux-119802818
== Beginners Guides! ==
ComfyUI has been around for a while now, but if you’re just starting your AI journey it’s a good idea to start at the beginning…
1. MS Windows Beginners Need Anaconda for Python - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflows for Beginners - https://youtu.be/VM9snsuoqBc
== More Flux.1 ==
* Using Flux in ComfyUI - https://youtu.be/DLUx-mK4g0c
* AI Enhanced Prompting with Flux - https://youtu.be/4d5zIBNuMRA
* Train your own Flux LoRA for Free at Home - https://youtu.be/7AhQcdqnwfs