JoePenna/Dreambooth-Stable-Diffusion

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) by way of Textual Inversion (https://arxiv.org/abs/2208.01618) for Stable Diffusion (https://arxiv.org/abs/2112.10752). Tweaks focused on training faces, objects, and styles.

49
/ 100
Emerging

This tool helps filmmakers, concept artists, and comic book designers train a Stable Diffusion model to generate consistent images of specific subjects, objects, or artistic styles. You provide a few images of a person, object, or style, and it outputs a customized AI model. This model can then be used to create new images incorporating those unique elements, like generating a specific actor in various scenes or props in different settings.

3,222 stars. No commits in the last 6 months.

Use this if you need to generate new, unique images of specific people, objects, or in a particular art style using AI, ensuring consistency across various creative prompts.

Not ideal if you want to train multiple distinct subjects consecutively without significant file management, or if you need to perfectly preserve the latent space of your training images.

filmmaking concept-art comic-design character-generation style-transfer
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

3,222

Forks

536

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/JoePenna/Dreambooth-Stable-Diffusion"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.