TIP: Use <code>thisisfine</code> in your prompt!The latest version looks good from 0.4 to 1.0. Please see the example prompts!If you liked this LORA, please consider following me on <a target="_blank" rel="ugc" href="https://twitter.com/lewdslotta">Twitter</a> and <a target="_blank" rel="ugc" href="https://www.pixiv.net/en/users/81897676">Pixiv</a> (to see latest in LORA news and some cool generations), or subscribing on <a target="_blank" rel="ugc" href="https://www.patreon.com/lottalewds">Patreon</a>.

LottaLewds' ThisIsFine

Not necessarily better than v0. v0 was trained on real art, v1 was trained on a ton of generations from v0, with the aim of being a bit less grainy and painted. More vector work. Will tend to give chibi or cutesy results. You can prompt away from that of course.Generations from AOM2_hard and Anything-V3.0.vae

Files with SHA256: 659ab11f08e542192a1c9177aa834f1e5d72f4a1473fca60094f587c2a3873ea