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
Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16.safetensors vs. Wan22-Lightning/Wan2.2-Lightning_I2V-A14B-4steps-lora_HIGH_fp16.safetensors
Hello,
Thank you for your great work! I want to ask what's the difference between Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16.safetensors vs. Wan22-Lightning/Wan2.2-Lightning_I2V-A14B-4steps-lora_HIGH_fp16.safetensors? Does Wan22-Lightning come from this (https://huggingface.co/lightx2v/Wan2.2-Lightning/tree/main/Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1)? What about the Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16.safetensors?
I have seen some spaces (e.g., https://huggingface.co/spaces/multimodalart/wan-2-2-first-last-frame) using Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16.safetensors with Wan 2.2, so I assume this is a some LoRA on top of Wan 2.2.
Thank you!