Bharat-Runwal/Continual-Diffusers
Pytorch library for Continual Learning with Diffusion Models
This tool helps researchers and engineers working with AI models to incrementally train image generation models. It allows you to feed in new batches of images and their descriptions or categories over time, and the system learns from them without 'forgetting' what it learned previously. The output is a highly capable image generation model that can create new images based on text prompts or class labels, even combining different concepts.
No commits in the last 6 months.
Use this if you need to continuously update your image generation models with new datasets or concepts without having to retrain from scratch every time, preserving previously learned knowledge.
Not ideal if you are looking for a simple, out-of-the-box solution for one-off image generation without the need for incremental learning or advanced model training customization.
Stars
9
Forks
—
Language
Python
License
—
Category
Last pushed
Oct 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Bharat-Runwal/Continual-Diffusers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
quantgirluk/aleatory
📦 Python library for Stochastic Processes Simulation and Visualisation
blei-lab/treeffuser
Treeffuser is an easy-to-use package for probabilistic prediction and probabilistic regression...
TuftsBCB/RegDiffusion
Diffusion model for gene regulatory network inference.
yuanchenyang/smalldiffusion
Simple and readable code for training and sampling from diffusion models
chairc/Integrated-Design-Diffusion-Model
IDDM (Industrial, landscape, animate, latent diffusion), support LDM, DDPM, DDIM, PLMS, webui...