Trained on Wan 2.1 T2V-14B model locally with 20 publicly accessible images using ai-toolkit trainer.
Recommended usage with LoRA strength 0.9, cfg 5, base shift 4. Trigger word is “woman”.
Example prompt (ComfyUI): A woman, wearing a shirt with a white blazer, with diamond earrings, looks directly at the viewer. Her hair swaying gently, her subtle smile widening slightly as she blinks, her eyes sparkling with a slight movement.
Want a custom/private LoRA? Good news—commissions are open! Request yours here: https://ko-fi.com/de_zoomer/commissions
Background
I've been deeply exploring how to create LoRAs with 100% accuracy to the original character. My focus is on quality of both likeness and generations.
I could use most of the knowledge from Hunyuan LoRA creation process, and I've consistently stayed up to date with the latest releases, exchanging knowledge in their communities.
My expertise is mainly with characters, so I’m not as familiar with LoRAs for style or anime, although the process might not differ too much.
If you want your own custom LoRa, feel free to message me! Commissions are open—check out my Ko-fi link above.
Enjoy using my LoRAs and have fun!
Description
FAQ
Comments (3)
Amazing! Can i ask, what workflow did u use for this Vids? 🙂
Great lora! I would strongly advise you dont use the trigger woman because with scenes with multiple women if you say "the woman on the left" so indicate which lora to use, then wan will put the lora on all women.
Amazing work. Could you please share your workflow for one of the sample videos? They don't have the embedded data in them :(
I couldn't achieve this superb result with the default Kijai T2V workflow. Thank you.
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.