This week at

Fine Tuning Friday

we’re working with Qwen & WAN2.2 - Multi Character Video Generation! We’re creating a fine-tuning pipeline which includes: 1) Segment out the characters in the scene (using DinoV3) 2) Train a Qwen-Image-Edit LoRA for each color to go from mask -> character in correct location 3) Use WAN Image2Video to turn the still frame into a video Join us if you want to see if we can get consistent generations of Conan O’Brien interviewing Will Smith :) Have you been fine-tuning video/image models recently? If so join! We’d love to see you work. https://luma.com/fine-tuning-friday-8