lightx2v/Wan2.2-Distill-Loras
Back

lightx2v/Wan2.2-Distill-Loras
142.7K 5 227

unknown

lightx2v/Wan2.2-Distill-Loras

🎬 Wan2.2 Distilled LoRA Models

âš¡ High-Performance Video Generation with 4-Step Inference Using LoRA

LoRA weights extracted from Wan2.2 distilled models - Flexible deployment with excellent generation quality

img_lightx2v

🤗 HuggingFace GitHub License

🌟 What's Special?

âš¡ Flexible Deployment

  • Base Model + LoRA: Can be combined with base models
  • Offline Merging: Pre-merge LoRA into models
  • Online Loading: Dynamically load LoRA during inference
  • Multiple Frameworks: Supports LightX2V and ComfyUI

🎯 Dual Noise Control

  • High Noise: More creative, diverse outputs
  • Low Noise: More faithful to input, stable outputs
  • Rank 64 LoRA, compact size

💾 Storage Efficient

  • Small LoRA Size: Significantly smaller than full models
  • Flexible Combination: Can be combined with quantization
  • Easy Sharing: Convenient for model weight distribution

🚀 4-Step Inference

  • Ultra-Fast Generation: Generate high-quality videos in just 4 steps
  • Distillation Acceleration: Inherits advantages of distilled models
  • Quality Assurance: Maintains excellent generation quality

📦 LoRA Model Catalog

🎥 Available LoRA Models

Task TypeNoise LevelModel FileRankPurpose
I2VHigh Noisewan2.2_i2v_A14b_high_noise_lora_rank64_lightx2v_4step_xxx.safetensors64More creative image-to-video
I2VLow Noisewan2.2_i2v_A14b_low_noise_lora_rank64_lightx2v_4step_xxx.safetensors64More stable image-to-video

?

This model is sourced from an external transfer (transfer address: https://huggingface.co/lightx2v/Wan2.2-Distill-Loras ）,if the original author has objections to this transfer, you can click，
Appeal
We will, within 24 hours, edit, delete, or transfer the model to the original author according to the original author's request

user_srdgfhfa

user_srdgfhfa

unknown

Model Information

Active
Original author：
lightx2v
Model Type：
LoRA
Basic Model：
WAN2.2
Resource Name：
models/loras/wan2.2_i2v_A14b_low_noise_lora_rank64_lightx2v_4step_1022_modified.safetensors
MD5：
ca29c174bc4cff86e70d69b9e124da2f

🎬 Wan2.2 Distilled LoRA Models

âš¡ High-Performance Video Generation with 4-Step Inference Using LoRA

LoRA weights extracted from Wan2.2 distilled models - Flexible deployment with excellent generation quality

img_lightx2v

🤗 HuggingFace GitHub License

🌟 What's Special?

âš¡ Flexible Deployment

  • Base Model + LoRA: Can be combined with base models
  • Offline Merging: Pre-merge LoRA into models
  • Online Loading: Dynamically load LoRA during inference
  • Multiple Frameworks: Supports LightX2V and ComfyUI

🎯 Dual Noise Control

  • High Noise: More creative, diverse outputs
  • Low Noise: More faithful to input, stable outputs
  • Rank 64 LoRA, compact size

💾 Storage Efficient

  • Small LoRA Size: Significantly smaller than full models
  • Flexible Combination: Can be combined with quantization
  • Easy Sharing: Convenient for model weight distribution

🚀 4-Step Inference

  • Ultra-Fast Generation: Generate high-quality videos in just 4 steps
  • Distillation Acceleration: Inherits advantages of distilled models
  • Quality Assurance: Maintains excellent generation quality

📦 LoRA Model Catalog

🎥 Available LoRA Models

Task TypeNoise LevelModel FileRankPurpose
I2VHigh Noisewan2.2_i2v_A14b_high_noise_lora_rank64_lightx2v_4step_xxx.safetensors64More creative image-to-video
I2VLow Noisewan2.2_i2v_A14b_low_noise_lora_rank64_lightx2v_4step_xxx.safetensors64More stable image-to-video

?

This model is sourced from an external transfer (transfer address: https://huggingface.co/lightx2v/Wan2.2-Distill-Loras ）,if the original author has objections to this transfer, you can click，
Appeal
We will, within 24 hours, edit, delete, or transfer the model to the original author according to the original author's request