Ultimate SFW Helper LoRa for Wan2.2 I2V
Trained on diffusion pipe with a dataset of 5131clips of various resolution, 1sec to 3sec or 5sec (3hr to complete 1 epoc, num repeat = 1)
Optimizer/learning rate: automagic
both model trained at 211 bucket
The lora contains multiple of the datasets of my existing loras and some additional ones, i made a big ass datset and trained it all together.
You can use this lora for help other concepts to get better results, being honest i havent tested with other creators lora, just mine, but it works awesome, you can make a man thrust his meat into a brick wall,, check the gallery.
The workflow im using is:
WAN 2.2 💠 T2V / I2V / S2V / T2I🔹4-6 steps🔹Loop 🔹Video extend 🔹WanVideoWrapper Workflow🔹K3NK (sample vids are 6 steps)
*you have it inside the my video's metadata, as allways.
Feel free to tinker and share your videos! 📹📼🎞️
Have fun! 😜
***** This LoRA is provided as is and intended for lawful and responsible use.
It acts as a general-purpose refinement layer, influencing how the base model expresses prompts and concepts rather than performing direct transformations. The resulting output is always driven by the prompt and the capabilities already present in the underlying base model.
The LoRA does not rely on paired inputs, before/after examples, or transformation-specific training. It focuses on improving coherence, detail, and stability across generations, including mature-themed outputs already supported by the base model.
No specialized datasets targeting identity exposure or content reconstruction were used during training. All faces and potentially identifiable features were masked or anonymized throughout the training process.