A commission of @Zorglub.
Note: Please also check @sstylerdurden879 fantastic 80s version of Monica.
Monica Bellucci is an acclaimed Italian model and actress. She's best known for her roles in blockbusters such as The Matrix Revolutions or Spectre, among many others.
This is step 120 of a TI trained on a dataset of 15 images with these settings. (I'll probably also upload step 130 later at some point as version 1.0.)
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.
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 (mbe11ucci:0.99), a woman as a movie star, modelshoot style, (extremely detailed CG unity 8k wallpaper), photo of the most beautiful artwork in the world, professional majestic oil painting by Ed Blinkey, Atey Ghailan, Studio Ghibli, by Jeremy Mann, Greg Manchess, Antonio Moro, trending on ArtStation, trending on CGSociety, Intricate, High Detail, Sharp focus, dramatic, photorealistic painting art by midjourney and greg rutkowski, (white turtleneck top:1.2), ((movie premiere)), (long skirt), ((standing near a movie theater)), ((paparazzi in the background)), (looking at viewer:1.2), (detailed pupils:1.3), ((closeup portrait:1.1))"
Description
120-step TI trained on a dataset of 15 images with these settings.
FAQ
Comments (15)
High quality! This is amazing, but I have a question. The mbe11ucci-120 used in the sample,,, has a different name than the one you released. Is it the same version?
the "-120" part means it is step 120 of the TI. I always test my embeddings with their step version number in the filename, then rename the one I like most without the number for publishing it here at CivitAI. That does not affect in any way whatsoever how the TI works. You can copy one of the prompts I've posted in my example pics and get an exact copy of the image, provided you follow all of the steps correctly.
If you need any help with this, please let me know! :)
@JernauGurgeh Aha, that explains it well, thanks for the reply, your work is really the best Lora. I will use it well^-^.
Looks very good. I just wish TI's played well with Lora's, never have much luck with them when I'm trying to get something more "artsy". But I'll give it a try anyway.
Yeah, I've had the same experience mixing TIs and LoRAs, unfortunately... That's the main reason I use LoRAs very sparely too. Thanks for downloading my TI, anyway! :)
Sometimes the trick to making an image look more "Artsy" and in a "painted effect style "
is to lower the CFG-Scale (test - 4, 5 , 6) and also lower the Sampling Steps to
around 15 or 20.
Also writing in the prompt script
" in the art style of _____add name of famous artist painter here_____ " ,
also helps the AI create a more artsy style of image.
Cheers
MAX
Wow, amazing work
¡Gracias! :P
Your work is unbelievable 🙏🏽🙏🏽🙏🏽
Can you please do Myriam Fares - https://instagram.com/myriamfares?igshid=MzRlODBiNWFlZA==
I think you will find some great high end res pictures for great result.
Thank you very much
Thanks! 🙂 I'll add her to my list.
Excellent work! I have tried in different conditions, all woking well. Thank you!
Glad to read that!
Awesome! You keep getting better and better. This Monica is sublime!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.