360CVGroup/HiCo_T2I
Layout Conditioned Image Generation, NeurIPS2024
This tool helps graphic designers, marketers, and content creators generate detailed images from a conceptual layout. You provide a general layout (like a wireframe with regions for objects) and descriptive text for each element, and it produces a high-quality, fully rendered image that matches your specifications. It's ideal for anyone needing to visualize designs or create unique visual content based on structured spatial ideas.
No commits in the last 6 months.
Use this if you need to create images where the precise placement and composition of multiple objects are critical, based on a text description and a visual layout guide.
Not ideal if you only need to generate images from simple text prompts without specific control over object placement, or if you require real-time, instantaneous image generation.
Stars
65
Forks
3
Language
Python
License
—
Category
Last pushed
Sep 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/360CVGroup/HiCo_T2I"
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