A LoRA adapter for Wan2.2-TI2V-5B that distills classifier-free guidance into conditional-only video generation, reducing the need for a separate unconditional inference branch.
This adapter does not provide few-step acceleration on its own.
This is an adapter and requires the corresponding base model.
Use with the matching few-step LoRA.
Recommended LoRA weights: few-step : CFG = 1 : 0.5.
These are adapter weights, not the inference CFG scale.
A LoRA adapter for Wan2.2-TI2V-5B that distills classifier-free guidance into conditional-only video generation, reducing the need for a separate unconditional inference branch.
This adapter does not provide few-step acceleration on its own.
This is an adapter and requires the corresponding base model.
Use with the matching few-step LoRA.
Recommended LoRA weights: few-step : CFG = 1 : 0.5.
These are adapter weights, not the inference CFG scale.
