WAN 2.1 nsfw LoRa

LORA
Reprint


Updated:

This is a LoRa based on NSFW Wan 14B T2V, which is a massive, 14 billion parameter text-to-video generation model, specifically fine-tuned for generating Not Safe For Work (NSFW) content. This model was created using a unified training methodology to build a solid understanding across the entire NSFW spectrum and generate videos with coherent motion natively.

Version Detail

WAN_2_1_14B Text2Video
LoRa Based on wan_14B_e15 "We strongly recommend using wan_14B_e15.safetensors for all general use cases and LoRA training. This final checkpoint represents the most refined state of the model." "The mixed-data training provides a strong, coherent grasp of anatomy and visual styles from the start. Coherent Motion & Actions: The video component provides foundational knowledge of common acts and temporal consistency."

Project Permissions

Model reprinted from : https://huggingface.co/NSFW-API/NSFW_Wan_14b/tree/main

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Related Posts