Wan 2.2 Notes - This model works very well with Wan 2.2. Output with plain wan 2.2, causvid v2, and lightx2v all seem to work well. Videos using Wan 2.2 are being posted and will be visible once Civitai's processor gets around to it. The LoRA settings you have used in the past should continue to work with Wan 2.2, just don't forget to apply this LoRA to both of the model -> ksampler pipelines to get the best results. After some experimentation, I found that you can mix CausVid and LightX2V in the two model pipelines. They are good at slightly different things. For my taste, I prefer the output I get with CausVid for the first high noise render, then LightX2V for the final low noise render. You can do your own experiments and decide what fits your tastes the best.
Edited - I revised my Wan 2.2 notes above because my original test videos had an error in the workflow which led me to some wrong assumptions. With a corrected workflow, the LoRA works extremely well at just about any resolution and configuration.
This Supergirl LoRA is a full character model, not just a costume model. You can use it to create multiple videos with a consistent face and body to go with the costume. This Supergirl isn't based directly on any single comic book, TV, or movie version. It's a mix of what Flux thought Supergirl's costume should look like along with some other character models thrown into the pot. THe result is a pretty blonde woman with an iconic Supergirl outfit that includes a short red skirt, a red cape, and tall boots.
Important: This model is 100% fictitious and is not based on images of any real person. She originated with images generated from still image checkpoints and has evolved from there using only AI rendering. No images (neither actual nor AI-generated) of any real person were ever involved in the making of this model.
Because Wan also has an idea of what Supergirl should look like, you can strengthen the costume by specifying "a woman wearing a supergirl costume" in your prompt. On the other hand, if you want her to dress down and combine jeans with her bodysuit, you can get away with that, too, although the costume portion of the model will make those videos inconsistent.
No revealing images were used to train this model, so if you want to put Supergirl into adult situations, you'll have to work that up on your own with some of the other LoRA tools and a big dose of prompting creativity.
I hope you have fun making movies with Supergirl. Please don't forget to post your videos here or else tag this LoRA in the generation info so I can see what other people are making with the model. Enjoy!