Powergirl has always been a fun comic book character to work with in AI. While Powergirl costume LoRAs have been around for a while in SDXL, Pony, and Flux, I haven't seen anything posted to Wan. Rather than try and create another clothing model, I instead aimed for the full character with the face, the hair, the body, and the clothing. This way it's much easier to create multiple videos with a consistent character face and body.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.UPDATE: For the best results, please give <a target="_blank" rel="ugc" href="https://civarchive.com/models/1999304/wan-22-comfyui-workflow-for-wan-21-loras">my workflow</a> a try. This workflow is what I use to make all my videos using my models and it produces great results in Wan 2.2 using LoRAs that were created with the Wan 2.1 model.ComfyUI workflow guidanceFor my current favorite ComfyUI configuration, please <a target="_blank" rel="ugc" href="https://civarchive.com/articles/23316">refer to my article</a> for all the necessary info you'll need to make the most of my Wan 2.1 LoRAs in Wan 2.2 videos.There are a variety of Powergirl versions out there so I rather than try and copy a specific artist's concept, I just went with my own idea of a fun Powergirl look. If you disagree with my results, I encourage you to make your own version too. I mean that seriously. Please do post your own versions too! The more the merrier.This Powergirl is busty (of course) and has the window where the "S" would go. Her hair is the familiar short bob/pixie cut. Her figure is muscular and even a bit thicc around the thighs. She's curvy and proud of it. The costume can be a little inconsistent in the fine details like the cape chain near the neck and the specific look of the boots and gloves. Also, Wan is just like every other AI image system I've tried in that it has a really hard time with people wearing capes when viewed from behind. This model is no different. You can try and get around it by saying "she is not wearing a cape" or using prompts like "the wind is blowing her cape to the side", but it's still hit and miss.When making sample movies for this LoRA, I realized I was in the habit of imagining static images for Flux/SDXL/whatever, but Wan videos really want specific action descriptions. Without a clear action to follow, Powergirl will just be standing there looking at you. So be creative with the action sequences.A word of warning: Do NOT tell Wan that the woman in the video is "wearing a superhero costume" or any words like that. Wan knows about Supergirl, so if you use anything with "super" in it, you're likely to get "S" logos on clothing all of a sudden. This LoRA is pretty strong when it comes to the clothing, so you should be able to just say "A woman" or "A blonde woman with short hair" or whatever.I hope you have fun making movies with Powergirl. 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!

Files with SHA256: 5b5c89fdb60a0e59e9726ebc54e4a8a23915cefe76470cd5df6f08f50d04994a