Faith is the sixth member of the LastName family, for anyone who wants a consistent character for their SD 1.5 renders.
Faith is almost certainly out of your league. She's a musician and gymnast, who dreams of running away to join Cirque du Soleil (and almost certainly will). She was born during golden hour. She’ll take you camping on the beach, then wear a leather jacket over a loose-fitting top and somehow make it impossibly cool. As I said: she is almost certainly out of your league.
To use this embedding with the Automatic1111 web UI, save the downloaded file to /embeddings/faithlastnamesd15.pt, and then include the trigger word faithlastnamesd15 in your prompt. (All of the sample images have full prompt metadata, and are straight out of Standard Diffusion - no upscaling, inpainting, or img2img was used.)
Description
FAQ
Comments (6)
question: why not try making a character using a LORA? I've always had the impression that while loras were larger in file size, they gave better and more consistent result. You don't see TI's used much anymore, at leasts for people
Honestly, it's because I've found TIs to be just as effective for training a custom character, and they are much smaller. You can also easily combine multiple TIs in a single prompt.
FWIW, I wrote up a tutorial of the process I use to create them: https://github.com/BelieveDiffusion/tutorials/blob/main/consistent_character_embedding/README.md
@BelieveDiffusion That link gives me a github 404 error page. Seems like the whole account is different
@wxcvbnw Yes, unfortunately GitHub flagged the account, I think because of the nudity. I have appealed the decision (and updated the tutorial) and am waiting to hear back.
@BelieveDiffusion you might find it easier to host or mirror on gitgud.io
@vlk In good news: the tutorial is back online!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.