madaan/minimal-text-diffusion
A minimal implementation of diffusion models for text generation
This project helps anyone generate new text samples by learning from an existing body of text. You provide a collection of text documents, and it produces a model that can generate similar-style text, going from random gibberish to coherent sentences. This is ideal for content creators, researchers, or anyone needing to generate varied text based on a specific style or topic.
410 stars. No commits in the last 6 months.
Use this if you need to generate new, original text content that mimics the style, vocabulary, and themes of a specific text corpus you already possess.
Not ideal if you need to generate images or structured data, or if you expect perfect grammatical correctness and factual accuracy without any post-processing.
Stars
410
Forks
38
Language
Python
License
MIT
Category
Last pushed
May 11, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/madaan/minimal-text-diffusion"
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...