HKUNLP/reparam-discrete-diffusion
Reparameterized Discrete Diffusion Models for Text Generation
This project helps researchers and developers create new text generation models using advanced diffusion techniques. It takes an input sequence of tokens (like words or characters) and applies a diffusion process to generate novel, coherent text outputs. Users who are building or experimenting with next-generation text generation systems would benefit from this.
104 stars. No commits in the last 6 months.
Use this if you are developing or researching new methods for generating text and want to leverage discrete diffusion models to create more robust and diverse text outputs.
Not ideal if you are looking for an out-of-the-box, end-user application for text generation or if you are unfamiliar with deep learning model development and Python.
Stars
104
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 14, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/HKUNLP/reparam-discrete-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.