Type | |
Stats | 652 0 |
Reviews | (63) |
Published | Jun 19, 2023 |
Base Model | |
Training | Steps: 1,020 Epochs: 340 |
Trigger Words | wowval |
Hash | AutoV2 E8AD2E1084 |
A commission of @findingavarice521.
Valeria D (aka WowVal) is an Instagram model and social media influencer.
1020-step TI trained on a dataset of 18 images.
Appreciate my work? My TIs are free, but you can always buy me a coffee. :)
Curious about my work process? I have summarized it here.
So... A lot has happened during these 3 weeks I've been on holidays. As some of you will have noticed, most of my TIs have been removed from the site. I'm slowly working on recovering them, but I guess it's gonna take time. Gotta say the mods have been very quick in republishing them until now, for which I really want to thank them, and I hope that won't change in the future. About 20 or so have been recovered, and I've sent requests already for more. I had more than 150 overall, so still a lot of work ahead. xD
With regards to new TIs, I'll keep uploading them for now and let's hope they won't be removed too. I'm trying to be as picky as possible with clothing and such, but let's see how it goes.
How to create a good prompt using my TIs
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 (wowval: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)"