InternScience/AdaptiveDiffusion
[NeurIPS'24] Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy
This project helps anyone working with AI image or video generation models to speed up their creative workflow. It takes an existing diffusion model (like those used for text-to-image or text-to-video) and, without needing new training, produces images or videos significantly faster. This means artists, marketers, or content creators can generate visual assets more quickly.
No commits in the last 6 months.
Use this if you need to accelerate the generation speed of existing diffusion models for images or videos without compromising output quality through retraining.
Not ideal if you are looking for a completely new diffusion model or need to fine-tune existing models with custom datasets.
Stars
73
Forks
6
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/InternScience/AdaptiveDiffusion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
FlorianFuerrutter/genQC
Generative Quantum Circuits
horseee/DeepCache
[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free
Gen-Verse/MMaDA
MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion,...
kuleshov-group/mdlm
[NeurIPS 2024] Simple and Effective Masked Diffusion Language Model
Shark-NLP/DiffuSeq
[ICLR'23] DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models