Wondering if i can just use the same wan2.2 lora i have without any nsfw images in the dataset? Or Is there a better way to do nsfw? Not seeing anything in the sub section just sdxl
Consistency is on point with this new model and it does NSFW as well - Training and sub workflow coming soon. Will also be releasing my Krea realism LoRA to subs / Course members, stay tuned! (Applied in these images)
You want ZIt with training adapter, steps 3000 - 4000 for 40 to 60 images lora. everything else default is fine.. low vram option with offloading if you are doing this locally.