Angelina Jolie is an American actress and filmmaker, known for many roles in films such as Girl, Interrupted (for which she won an Academy Award), Lara Croft: Tomb Raider, Salt, Mr. and Mrs Smith or Maleficent, among others.
Note: This embedding has been updated. Version 2.0 is a 140-step TI trained on a brand new dataset of 15 images with these settings. I'll probably upload a previous step (130) as version 2.1 later on, as I'm still unsure which one is better between the two.
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 (aj0li3_JG: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
180-step TI trained on a dataset of 15 images with these settings.
FAQ
Comments (8)
She has the sexiest belly-button !
Worthy of a star rating
Thank you
It always amazes me how great the quality is despite the tiny TI.
May i suggest some celebrity here?
Of course! Ideas are always welcome. 🙂
hey,
great so fare, i only can generate lora, what you use kohya ? you like hoop earrings ?
if i use this resolution i often get 2 faces, you upscale it ? i post also a pic, i like real faces ;)
Not sure if I'm following you, but I do upscale the pics (1.5x normally). I rarely use LoRAs when generating pics with my TIs (I think they don't tend to mix too well).
my intention is also to generate TI, but I don't know if the results are that much better than LoRA.
i used kohya_ss its a stand-alone, similar to yours but some differents, currently my training there is not progressing so well ;)
@sevenof9247 I used to think that TIs were able to achieve more accuracy than LoRAs when it came to recreating the likeness of a person, but I don't think so anymore. I've seen some amazing LoRAs and Lycoris done for celebrities. I think, in the end, what really matters is that you have a good dataset, a trustworthy work process and some good tools and prompts to showcase your work.
Good luck with your work, mate! :)
isee, thy for the hint ... ;)
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.