davidhalladay/Frido
Research code for paper "Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis"
This project helps researchers generate realistic images from various inputs like text descriptions, scene layouts, or semantic labels. It takes structured inputs such as a sentence describing a scene or a spatial arrangement of objects, and produces a high-quality, complex image matching that description. It's designed for researchers working in computer vision and generative AI.
115 stars. No commits in the last 6 months.
Use this if you are a researcher focused on synthesizing complex scenes and evaluating different methods for text-to-image, layout-to-image, scene-graph-to-image, or label-to-image generation.
Not ideal if you need a simple, ready-to-use tool for image editing or generating basic images without deep technical involvement.
Stars
115
Forks
11
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Nov 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/davidhalladay/Frido"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OPTML-Group/Unlearn-Saliency
[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in...
Shilin-LU/VINE
[ICLR 2025] "Robust Watermarking Using Generative Priors Against Image Editing: From...
WindVChen/DiffAttack
An unrestricted attack based on diffusion models that can achieve both good transferability and...
koninik/DiffusionPen
Official PyTorch Implementation of "DiffusionPen: Towards Controlling the Style of Handwritten...
Wuyxin/DISC
(ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation