lightx2v made a 14B self forcing model that is a massive improvement compared to Causvid / Accvid. Kijai extracted it as a lora. Example on civitai was generated in about 35 seconds on a 4090 using 4 steps, lcm, 1 cfg, 8 shift, still playing with settings to see what is best.
Version Detail
WAN_2_1_14B Img2Video
Project Permissions
Model reprinted from : https://civitai.com/models/1585622?modelVersionId=1909719
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.