Introducing Red Sonja for Wan 2.1 and 2.2, by request.

Important: This model is 100% fictitious and is not based on images of any real person. The data set for the model was 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 my workflow 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 guidance

For my current favorite ComfyUI configuration, please refer to my article for all the necessary info you'll need to make the most of my Wan 2.1 LoRAs in Wan 2.2 videos.

This Red Sonja model was based on the previously released Shannon - Wan LoRA. With a lot of prompt guidance and many, many trial and error images, the Red Sonja character came to life. Yes, the armor was hard to get right. Yes, it also sometimes isn't correct in the output videos. If that happens to you and you otherwise really like the scene, you can try boosting the strength (or the 2nd step Low Noise strength in Wan 2.2) up to 1.25 or even 1.5 and that often helps. Keeping a lower strength is generally better for video output with better motion and prompt adherence, so only boost the strength above 1.0 when you need to.

The key word is "r3dsonja".

I hope you all have fun creating scenes with Red Sonja. Please don't forget to post here or link your posts back to this model so I can see what everyone is coming up with. Enjoy!