A request of @starsilver117802.
Cameron Goodman is an American actress and filmmaker, known for her roles in movies such as The Informer or The Dead Undead.
This is a 140-step TI trained on a dataset of 15 images with these settings.
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 (c4mer0ng00dm4n:0.99), a woman with beautiful hair, as a movie star in a (movie premiere), premiere gala, (near a movie theatre), natural skin texture, (sexy tight {red|yellow|blue|green|black|turquoise} mesh strapless dress), 24mm, 4k textures, soft cinematic light, adobe lightroom, photolab, hdr, intricate, elegant, highly detailed, sharp focus, ((((cinematic look)))), soothing tones, insane details, intricate details, hyperdetailed, low contrast, soft cinematic light, exposure blend, hdr, faded, (paparazzi in background), (painted lips:1.1), ((looking at viewer: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.
Description
140-step TI trained on a dataset of 15 images with these settings.
FAQ
Comments (4)
great TI! I recommend Laetitia Casta next, she's from the same time period.
Thanks! And sorry I missed this comment until now. Will consider Laetitia in the future, for sure. She was one of the greatest beauties of the 90s.
@JernauGurgeh I tried training a Lora on Laetitia but it didn't work out. The faces are all messed up and blurry. It's strange because I'm using the same config I used on many of my other (much better) Loras.
I think the data is the problem. The pictures from her prime are from the late 90s and early 2000s, and the resolutions are very low. Do you have any suggestions on how to handle such quality issues?
@hourglassfcupslimwaist Right, that can certainly affect the quality of the TI. My only advice is something you're probably already doing--try to use only at least decent quality pics. Even if you like a pic very much, in case its resolution is too low it's better not to use it. I don't know how many pics you're using in your dataset, but you could also consider training with less pics. I wouldn't go below 10, though.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.