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_I2V_A14B_HIGH_lightx2v_4step_lora_v1030_rank_64_bf16.safetensors
Thanks for your work and effort, but I would like to know which sampler, how many steps, which low noise lora? Which strength should be used? Which shift? But the most important question for me is which low noise lora should be used with it.
Use 1.0 to 1.5 strength for this LoRA, and for low noise use the old 2.1 lightx2v LoRA.
Sampler settings are too situational to really say what's best, but around 4-6 steps should work.
Thank you :) Is there a special 2.1 Lora that works best with i2v? I have been using the t2v-v2-128, but when I use i2v 2.1, I get a lot of messages saying that various things cannot be loaded. Many thanks for your quick reply.
updated - works well
Which old 2.1 lightx2v LoRA is best for low noise? I have so many lightx2v loras atm.
which 2.1 Lora to use for LOW sampler for best results and what strenght and cfg?