dome272/Paella
Official Implementation of Paella https://arxiv.org/abs/2211.07292v2
Operates on compressed, quantized latent spaces conditioned with CLIP embeddings to achieve high-fidelity image generation in under 10 steps and 500ms per image. Beyond text-to-image synthesis, supports latent space interpolation and image manipulations including inpainting, outpainting, and structural editing. Prioritizes accessibility with minimalistic codebases—training and sampling implementations fit under 140 lines—enabling rapid experimentation and community contribution.
748 stars. No commits in the last 6 months.
Stars
748
Forks
53
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 04, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/dome272/Paella"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
xie-lab-ml/Golden-Noise-for-Diffusion-Models
[ICCV2025] The code of our work "Golden Noise for Diffusion Models: A Learning Framework".
UNIC-Lab/RadioDiff
This is the code for the paper "RadioDiff: An Effective Generative Diffusion Model for...
yulewang97/ERDiff
[NeurIPS 2023 Spotlight] Official Repo for "Extraction and Recovery of Dpatio-temporal Structure...
pantheon5100/pid_diffusion
This repository is the official implementation of the paper: Physics Informed Distillation for...
zju-pi/diff-sampler
An open-source toolbox for fast sampling of diffusion models. Official implementations of our...