jintae-00 (GitHub) · Visual Understanding
ReDesign
VLM-driven agent decomposes flat raster designs into editable JSON: text with typography, vector shapes, images, layer hierarchies, via five specialized tools (Qwen-Image-Layered, GroundingDINO, SAM 2). Accepted to ECCV 2026, 60 GitHub stars, CC BY 4.0 datasets.
Open the source ↗Similar Vision & Image releases
- Rembg
Daniel Gatis (danielgatis) · Background removal · Week 46, 2026
- InternLumina-U2
Shanghai AI Laboratory · Omni-Visual Diffusion LLM · Week 36, 2026
- MODUS
EPFL / Apple / U. Copenhagen / CUHK / U. Geneva / Lambda · Visual Understanding · Week 31, 2026
- NVIDIA Nemotron 3.5 Super VL
NVIDIA, via Amazon Web Services · Agentic VLM · Week 47, 2026
- Mirage
Cactus · On-device vision model · Week 46, 2026
- P-H3-Image
Pruna AI · Open image model · Week 46, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.