Instructions to use Kijai/WanVideo_comfy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Kijai/WanVideo_comfy with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Wan 2.2 lightx2v lora usage details
#50
by llama-anon - opened
are we supposed to put 2 steps per stage (2+2) or 4 steps per stage
also should we put weight 1.00 or 0.125 on the loras from this repo
anything else?
thanks for converting their loras so quickly!
With the ones I shared you can use the normal 1.0 strength.
Too early to say best settings, but minimum that works is 2+2 for 4 total steps, but it does seem better with more steps.
Thank You for clarifying!
llama-anon changed discussion status to closed
but i am seeing not much of improvements am i missing the configs 4 steps is not that good
why camera prompt not working anymore with the lora