L-YeZhu/BoundaryDiffusion
[NeurIPS2023] BoundaryDiffusion: A learning-free method for semantic control with Diffusion Models
This project offers a resource-friendly way to modify specific attributes in existing images, like changing a frown to a smile on a face or altering architectural features in a building. It takes an input image and, without needing extensive training, produces a new version of that image with the desired semantic edit. This is useful for graphic designers, content creators, or researchers who need to quickly and efficiently generate variations of images based on conceptual changes.
No commits in the last 6 months.
Use this if you need to semantically edit images (e.g., adjust facial expressions, alter building styles) using pre-trained diffusion models without complex fine-tuning or re-training.
Not ideal if you need to generate entirely new images from scratch or if your image editing task requires pixel-level precision rather than broad semantic changes.
Stars
40
Forks
2
Language
Python
License
MIT
Category
Last pushed
Nov 01, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/L-YeZhu/BoundaryDiffusion"
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