⌚ Time traveling detective! Now with all 4 of her outfits and all accessories, as well as a generic "amelia watson" tag for all your other needs. Check the third image for basic prompts and the other images or the right side for extra tags.
Works at weight 1 but might need hires fix sometimes. Made using my Lora guide.
Description
Holy shit this took 4 tries to get right. Trained with 590 images of Amelia Watson; 190 images of her detective outfit, 100 images of her casual outfit, 60 images of her formal outfit, 40 images of her kimono outfit and 200 generic images.
Download the dataset if you're interested.
Works at weight 1 but might need hires fix sometimes.
FAQ
Comments (4)
other guy saying "you're training wrong" is silly - its the LoRAs where the default outfit is hard-baked in that are doing it wrong. If you just have the default outfit associated with the whole LoRA/tag, then their default outfit bleeds into whatever clothes you try (like swimsuit) and really makes it more inflexible.
This is a great LoRA and its super easy to use CivitAI helper to import all the tags if someone is going for a specific outfit. The only real improvement would be to have each outfit associated with a single keyword (e.g. 'default', 'casual', etc).
Training a specfic outfit to a single tag on top of the character tag is exactly how I myself, and hundreds of other LoRA I downloaded, did it.
Thanks for proving my point :)
I'm an avid LoRA creator myself. I can assure you, if you use only one tag to outfit the character, then flexibility goes out the window. Outfit blending WILL happen if you don't tag properly. Not only that, you can't put them in a maid dress, or a swimsuit without really fighting the prompt. This LoRA strikes a good balance between being flexible for your own artistic desires, and containing Amelia's outfits.
Either way, if you want 1 tag to replicate a character, this LoRA isn't it. For those who want a more hands-on 'dress-up' experience, this is it.
Can you please update the LoRA normal with the all outfits? this year Ame will gone soon this month, I feeling sad 😔
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.






