• m532@lemmygrad.ml
    link
    fedilink
    English
    arrow-up
    1
    ·
    8 days ago

    That’s what they always say, and then… new stuff

    Qwen-Image (diffusion with a LLM as text encoder) came out 10 days ago and it understands the prompt like 20x better, than, for example, SDXL Turbo