migs2021/migs
MIGS: Meta Image Generation from Scene Graphs (BMVC 2021)
This tool helps researchers and computer vision scientists generate realistic images from textual scene descriptions. You input a scene graph, which describes objects and their relationships (e.g., "a car is on a road next to a tree"), and it outputs a synthetic image matching that description. It's designed for those exploring synthetic data generation or visual understanding research.
No commits in the last 6 months.
Use this if you need to create diverse image datasets from structured text descriptions for computer vision model training or research, especially if you're working with specific domains like driving scenes or human-object interactions.
Not ideal if you need to generate images from free-form text descriptions without structured scene graph inputs, or if you're looking for a simple, off-the-shelf image generation tool without fine-tuning.
Stars
8
Forks
3
Language
Python
License
Apache-2.0
Category
Last pushed
May 12, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/migs2021/migs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Vchitect/VBench
[CVPR2024 Highlight] VBench - We Evaluate Video Generation
VectorSpaceLab/OmniGen
OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340
EndlessSora/focal-frequency-loss
[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis
JIA-Lab-research/DreamOmni2
This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing...
SkyworkAI/UniPic
Open-source SOTA multi-image editing model