Trained on Wan 2.1 T2V-14B model locally with 20 publicly accessible images using ai-toolkit trainer.
Use with LoRA strength between 0.7-1. 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 (7)
wow, amazing results!
😍 👍🏻
Are all your results just from text-to-image? I was wondering if you also get good results from using a flux-generated image (using the appropriate celeb LoRA) then using image-to-video Wan with your Wan LoRA. Maybe getting realistic video results that are easier to predict/guide (due to having a starting image)?
Hi, I have a newbie question. I noticed that the trigger word you use in your Loras is "woman." I'd like to know how I can specify the person in the prompts when I want to use multiple Loras, since both have the trigger word "woman."
Oof, did she really do that to her face?
I have another newbie question xD. I've used this Lora and the results are truly incredible, but I've had a problem with all of them. When I want to create a video of Anya with another completely random woman, the 2 women have the same face and body as Anya. I've tried indicating in the prompt for example: "a woman (the trigger word ) named Anya and a nurse named Sara." By doing this I can differentiate each character and their actions in the video, but both women have the same face. I've tried with 0.8 and 1.0. Any recommendations?
What requeriments are to train a lora like this one? What gpu do you have?
Details
Files
Available On (3 platforms)
Same model published on other platforms. May have additional downloads or version variants.