Type | |
Stats | 851 |
Reviews | (117) |
Published | Dec 10, 2023 |
Base Model | |
Training | Steps: 135 Epochs: 405 |
Usage Tips | Clip Skip: 1 |
Trigger Words | sh4r0nst0ne |
Hash | AutoV2 D7463064D9 |
Sharon Stone is a world-renown actress born in 1958. She has starred in films such as Basic Instinct, Total Recall and Casino, among many others.
This is a 135-step TI trained on a dataset of 15 images with these settings. The embedding is based on Sharon's 80s and early 90s looks. It's a bit finicky, so I suggest you take my example prompts and use them as a base to build your own in case you're not getting good results.
Curious about my work process? I have summarized it here.
Do you have a specific idea for a TI in mind? Visit my website and let me know.
Building a good prompt with 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 (sh4r0nst0ne:0.99), a woman, perfect hair, posing seductively, (modern photo, __attire_mix__), (closeup portrait), jewelry, 24mm, (analog, cinematic, film grain:1.3), (outside of Berghain Panorama Bar, nighttime, gritty), ((detailed eyes)), (epicPhoto), (color picture:1.1)".
Please also note that I'm using the "add detail" LoRA for my example pics. I recommend setting it around 0.5 for best results. CLIP Skip should always be set at 1 when generating pics with this TI.