Type | |
Stats | 1,480 |
Reviews | (142) |
Published | Jun 23, 2023 |
Base Model | |
Training | Steps: 1,000 Epochs: 333 |
Trigger Words | nk1nsky |
Hash | AutoV2 EE03B7629E |
Nastassja Kinski is a German actress and former model, known for roles in many films, including Tess (for which she won a Golden Globe) and Paris, Texas. With this embedding I've tried to capture her looks in the 80s and 90s.
This is a 1000-step TI trained on a dataset of 18 images with my usual settings.
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.
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 (nk1nsky:0.99), a woman, closeup zoomed in tight crop portrait, sitting at a (table on a seaside boardwalk cafe bar drinks cocktails:1.2) wearing a (button shirt:1.3) (drinks on table:1.3) (Lighting-Gold:1.2) foreground objects background details (masterpiece:1.2) (photorealistic:1.2) (bokeh:1.2) (best quality) (color grading) (detailed skin:1.3) (intricate) (8k) (HDR) (cinematic lighting:1.3) (sharp focus)"