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.
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.
Stars
3,222
Forks
536
Language
Jupyter Notebook
License
MIT
Category
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.
Higher-rated alternatives
huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
bghira/SimpleTuner
A general fine-tuning kit geared toward image/video/audio diffusion models.
mcmonkeyprojects/SwarmUI
SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an...
nateraw/stable-diffusion-videos
Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
TheDesignFounder/DreamLayer
Benchmark diffusion models faster. Automate evals, seeds, and metrics for reproducible results.