nupurkmr9/syncd
SynCD: Generating Multi-Image Synthetic Data for Text-to-Image Customization (ICCV 2025)
This tool helps creative professionals and artists generate new images of a specific object based on a text description. You provide a few reference images of an object, like an action figure, and a text prompt describing the desired scene. The system then outputs new, high-quality images of that object in different poses, lighting, and backgrounds, matching your text description. It's ideal for designers, marketers, and content creators looking to quickly produce varied visual content featuring a consistent subject.
154 stars.
Use this if you need to generate multiple creative variations of an existing object for marketing, design, or artistic projects using text prompts.
Not ideal if you require only simple object cropping or basic image manipulation, or if you don't have existing reference images of the object.
Stars
154
Forks
15
Language
Python
License
MIT
Category
Last pushed
Oct 16, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/nupurkmr9/syncd"
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