This Lora is made to enhance to ability / quality to create anthro and furry, and creatures for Wan 2.2 T2V there is also an I2V variant you can found here: https://tensor.art/models/899555585878445812/Furry-Enhancer-Wan-2.12.2-Wan-2.2-I2V-V1.0-HN
for more information and download please visit https://civitai.com/models/1782485/furry-enhancer-video
High / Low Noise Lora:
This enhancer version is for Wan 2.2 T2V like the I2V its made for anthro / furry and fantasy creatures sfw and nsfw
its splitted in basically 2 Loras: low and high noise
both loras for T2V are trained on the same dataset. I its my own dataset before i trained with the wan 2.1 Lora but add more pictures and videos
it's completely synthetic so no real persons or art is used for the dataset.
i recommend using both loras in the video metadata there is a comfy workflow for using it.
for the workflow all videos contain the workflows but i also packed the workflow in the "training" zip file.
for this workflow i can recommend a step count between 8- 10 steps
the model is only tested with the standard model and wan 2.2 lightning
the model weight in all my testings was 1.0
More information to wan 2.2 t2v you found here
Note: this is V1 of this model so it sometimes still can fail also its very "spicy" and need for example descriptions for clothing
Important:
training such loras is very costly so if you like to support me please give a like and Check out my other models too.