maple-research-lab/SIM
Inference-only implementation of "One-Step Diffusion Distillation through Score Implicit Matching" [NIPS 2024]
This project helps generate high-quality images from text descriptions or unconditional prompts significantly faster than traditional methods. It takes a text prompt or no input for unconditional generation and produces a high-quality image. This would be used by content creators, graphic designers, and AI artists who need to quickly generate diverse images without sacrificing quality.
No commits in the last 6 months.
Use this if you need to rapidly create diverse, high-quality images from text prompts or for general image generation, without waiting for multiple processing steps.
Not ideal if you require fine-tuning a diffusion model for custom datasets or if your workflow specifically demands multi-step generation for incremental artistic control.
Stars
83
Forks
3
Language
Python
License
AGPL-3.0
Category
Last pushed
Nov 17, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/maple-research-lab/SIM"
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".
yulewang97/ERDiff
[NeurIPS 2023 Spotlight] Official Repo for "Extraction and Recovery of Dpatio-temporal Structure...
UNIC-Lab/RadioDiff
This is the code for the paper "RadioDiff: An Effective Generative Diffusion Model for...
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...