I'm not sure what I'm doing wrong. I was informed that the Wan 2.1 Lora works with Wan 2.2, but unfortunately, that hasn't been the case for me.
When I tried using the Lora with Wan 2.2, it didn't resemble the subject at all. Since I'm new to Wan 2.1, I'm still in the learning process. If anyone can direct me to a good training video for the Ostris AI toolkit with Wan 2.2, I would really appreciate it!
I'll also post a few blooper videos below. Perhaps someone kind individual can help me understand what I'm doing wrong.
https://civarchive.com/user/The_Last_Goblin_King
His skin workflow: https://civarchive.com/models/1986468/fluxsrpo-skin-saver-works-with-any-image-i2i-workflow-no-hassle-flow
“No imagery of any Person of Interest was used in creating this LoRA.”
Please be patient. The Civitai system has flagged a few images, including the video, for review. /Sigh
Warning: I suffer from insomnia and often pass the time creating AI art. As I wait for my medication to kick in, my concentration lapses and my prompts become worse. My apologies for that. On the upside, it does create some interesting images. :)
If you enjoy my work, please click the thumbs up. Thank you! /Bow
>>> UPLOADING/SHARING MY MODELS OUTSIDE CIVITAI IS STRICTLY PROHIBITED* <<<
Description
FAQ
Comments (2)
Hi,
happy to see you followed my previous request and started Wan 2.2 character Lora :).
Here the video i watched to train my wan 2.2 character Lora. It's for wan 2.1, but to use your Lora for wan 2.2, you just need to put your Lora both in high and low noise sampler at around 0.8-1.
https://youtu.be/QhNsgJG1njw?si=J364fXX5LpfnWmxd
I followed the steps for training my wan 2.2 Lora character, and my character Lora work perfectly for Wan 2.2.
You can also watch all Lora training tutorials videos the creator of AI Toolkit make on YouTube:
https://www.youtube.com/@ostrisai/videos
you will see that the last training tutorial video is for training a slider Lora, which is trending now in Civitai.
https://youtu.be/e-4HGqN6CWU?si=t5JrWqVhhq8SxjFx
Thank you. ^_^ I will try this.




