CivArchive
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    A commission of @Springbok707.

    Emma Watson is a British actress who needs no introduction. For this embedding, the original idea was to capture her 2010 looks, with that famous pixie haircut.

    Update: I've now updated the TI to look more like nowadays Emma. Version 3.0 is step 140 of a TI trained on a dataset of 15 images with these settings. It solves mainly some issues with her hair and her eyes present in v2.0.

    Curious about my work process? I have summarized it here.

    If you want to help me keep creating TIs, please consider buying me a coffee.

    Also, I appreciate 5-star ratings if you really like my TIs!

    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 (emm4w4ts0n: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

    140-step TI trained on a dataset of 15 images with these settings.

    FAQ

    Comments (16)

    malcolmreyOct 9, 2023· 4 reactions
    CivitAI

    oh wow, two embeddings of emma watson in the span of an hour :-)

    JernauGurgeh
    Author
    Oct 9, 2023· 1 reaction

    This has to be some Gryffindor wizardry. xD

    MolesterrOct 9, 2023· 1 reaction

    There is no doubt that the spell she cast on us when we were still young still has an effect. Honestly, I would like to see more work on young characters that mark my childhood, as well as others that are blossoming. It's a shame that everything is taken to extremes nowadays.

    DashdashieOct 15, 2023· 2 reactions
    CivitAI

    Can you do Dasha Taran? I love the work you do!

    JernauGurgeh
    Author
    Oct 15, 2023

    I'll add her to my list.

    exilificOct 23, 2023
    CivitAI

    how do i download embeddings?

    JernauGurgeh
    Author
    Oct 23, 2023· 2 reactions

    You just need to press the donwload button in the embedding page and install it in your stable-diffusion-webui\embeddings folder.

    andysingal611Oct 27, 2023· 1 reaction
    CivitAI

    Can i use it with SDXL?

    JernauGurgeh
    Author
    Oct 27, 2023

    Unfortunately, SD 1.5 embeddings do not work with XL. Sorry, mate.

    JernauGurgeh
    Author
    Oct 28, 2023· 4 reactions
    CivitAI

    Thanks for the 1000 likes, everybody!

    JernauGurgeh
    Author
    Jan 30, 2024
    CivitAI

    Thanks for the buzz tip, @hick221!

    fcukitMar 3, 2024· 4 reactions
    CivitAI

    Not being negative to author - this is exceptional work and they should be proud - but I sometimes wonder how the subject (Emma in this instance) feels about this. It feels somewhat invasive. But I don’t feel that way for any of the other subjects. Maybe it’s because I kinda watched this one grow up?

    flatguystrifeMar 23, 2024· 1 reaction

    I agree 100 %. I'd add that maybe it's because she grew into a fine, nice, woman and seems like a good person despite being rich and popular.

    I've made pretty pics using this TI, but I haven't made porn. It just feels wrong.

    I've made loras of girls and used them to make porn, but those are all pornstars. They've consented to being nude and / or having sex on camera.

    thiagojramosApr 21, 2024· 1 reaction

    Let me hit her up on WhatsApp, hold on

    user1234123Jun 14, 2024

    Imo humanity will become desensitized, celebrities will find a way to take control of their image and make the recreations even better. (Stability was already exploring this with blockchain and announced partnership with otoy, not a fan of that btw)

    Actual porn actors and actresses will disappear.

    Nobody will have to work anymore because the machine will take care of all of that. Sex won't be thought of as it is now. Though good parenting still would be extremely important and even moreso in this new environment with AI.

    One day I imagine I will see a nearly perfect recreation of myself with boobs added to me and a detachable penis on the tv, my family will see what the person did to my image, I will look at it and say.. "wow that's creative" my family will laugh and nobody will care and move on with their lives. It's just the initial shock factor here. Tbh, that will never happen and maybe it won't pan out like this at all, and let's face it nobody gives a crap about putting me on tv. lol

    goviman2Aug 7, 2024
    CivitAI

    She looks gorgeous, i´ll never get that quality, i´m sure, but the fun is in trying. Thank you.

    TextualInversion
    SD 1.5

    Details

    Downloads
    16,577
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    10/9/2023
    Updated
    5/7/2026
    Deleted
    5/23/2025
    Trigger Words:
    emwats0n

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.