<a target="_blank" rel="ugc" href="https://www.instagram.com/itsandreabotez/?hl=en">Andrea Botez</a> is a Canadian chess player and streamer, the younger sister of <a rel="ugc" href="https://civarchive.com/models/12306/alexandra-botez-chess-player">Alexandra Botez</a>.Update: Retrained from scratch. I'm having trouble deciding between steps 1200 and 1000. The former seems more consistent, but the latter has produced some great results, so I will probably upload it as version 3.0 later.Version 3.1 is a 1200-step TI trained on a dataset of 18 images with my <a target="_blank" rel="ugc" href="https://imgur.com/a/dOJEZg2">usual settings</a>.Appreciate my work? My TIs are free, but you can always <a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/jernaugurgeh">buy me a coffee</a>. :)Curious about my work process? I have summarized it <a target="_blank" rel="ugc" href="https://civarchive.com/models/56570/renata-valliulina?commentId=118383&amp;modal=commentThread">here</a>.<h2>How to create a good prompt using my TIs</h2>You're obviously free to experiment, but bear in mind that my TIs are trained with a more or less fixed phrasing, that normally starts with:"photo of EMBEDDING_NAME, a woman"So I recommend always starting your prompt like that and then building the rest of the prompt from there. For instance, "photo of beautiful (4ndr34b0t3z:0.99), a woman as a movie star, hair upsweep updo, sweater off-shoulders, trousers, at a movie premiere gala, dark moody ambience (masterpiece:1.2) (photorealistic:1.2) (bokeh) (best quality) (detailed skin:1.2) (intricate details) (nighttime) (8k) (HDR) (cinematic lighting) (sharp focus), (looking at the camera:1.1), (closeup portrait:1.1)"

Andrea Botez

Adding step 1000 as version 3.0 as promised. As I mentioned in the description, I think step 1200 is the superior version because of its consistency, but this one has produced some remarkably good pics, so I think it's worth sharing.

Files with SHA256: eb7e333dfacb9061fd784d84003226f404e574b1345ec91d1bfc4210d16dcf0d