Wan2.1-Fun-14B-InP-HPS2.1_reward_lora_comfy
Back

Wan2.1-Fun-14B-InP-HPS2.1_reward_lora_comfy

FUN

WAN

REWARD

Wan2.1-Fun-14B-InP-HPS2.1_reward_lora_comfy

Alibaba-PAI
We explore the Reward Backpropagation technique 1 2 to optimized the generated videos by Wan2.1-Fun for better alignment with human preferences. We provide the following pre-trained models (i.e. LoRAs) along with the training script. You can use these LoRAs to enhance the corresponding base model as a plug-in or train your own reward LoRA.

Wan2.1-Fun-14B-InP-HPS2.1.safetensors
Official HPS v2.1 reward LoRA (rank=128 and network_alpha=64) for Wan2.1-Fun-14B-InP. It is trained with a batch size of 32 for 3,000 steps.

Converted By Kijai:
https://huggingface.co/Kijai/Wan2.1-Fun-Reward-LoRAs-comfy

Converted to ComfyUI compatible format from:
https://huggingface.co/alibaba-pai/Wan2.1-Fun-Reward-LoRAs/tree/main

This model is sourced from an external transfer (transfer address: https://huggingface.co/alibaba-pai/Wan2.1-Fun-Reward-LoRAs/tree/main ）,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

Pinto 平托

Pinto 平托

FUN

WAN

REWARD

Model Information

Original author：
Alibaba-PAI
Model Type：
LoRA
Basic Model：
WAN2.1
Trigger Words：
WAN

Alibaba-PAI
We explore the Reward Backpropagation technique 1 2 to optimized the generated videos by Wan2.1-Fun for better alignment with human preferences. We provide the following pre-trained models (i.e. LoRAs) along with the training script. You can use these LoRAs to enhance the corresponding base model as a plug-in or train your own reward LoRA.

Wan2.1-Fun-14B-InP-HPS2.1.safetensors
Official HPS v2.1 reward LoRA (rank=128 and network_alpha=64) for Wan2.1-Fun-14B-InP. It is trained with a batch size of 32 for 3,000 steps.

Converted By Kijai:
https://huggingface.co/Kijai/Wan2.1-Fun-Reward-LoRAs-comfy

Converted to ComfyUI compatible format from:
https://huggingface.co/alibaba-pai/Wan2.1-Fun-Reward-LoRAs/tree/main

This model is sourced from an external transfer (transfer address: https://huggingface.co/alibaba-pai/Wan2.1-Fun-Reward-LoRAs/tree/main ）,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