Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feature] Generate an avatar out of text / parameters #1

Open
AmitMY opened this issue Nov 26, 2024 · 1 comment
Open

[Feature] Generate an avatar out of text / parameters #1

AmitMY opened this issue Nov 26, 2024 · 1 comment
Labels
enhancement New feature or request

Comments

@AmitMY
Copy link
Contributor

AmitMY commented Nov 26, 2024

Problem

Getting a high quality image of a person with the right stance etc is proving difficult in many cases.
And generating an image out of a prompt can be tricky - with various things not being accounted for.

Description

Build a prompt template with some controls to allow generating a good human.

What we have so far:

A professional sign language interpreter, a white woman with blue eyes, her hair neatly tied back in a simple ponytail. She is wearing a plain black shirt without any earrings, necklaces, piercings, rings, or bracelets. She stands against a green screen background, with her hands positioned clearly in front of her abdomen, showcasing precise and well-defined hand shapes that emphasize clarity and accuracy. #studio #wide_shot

SD3 Medium with negative prompt

earings, neckless, rings, disfigured

image

FLUX schnell
image

FLUX dev
image

@AmitMY AmitMY added the enhancement New feature or request label Nov 26, 2024
@AmitMY
Copy link
Contributor Author

AmitMY commented Nov 27, 2024

Todo: add smiling, showing teeth

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

1 participant