j-min/VPGen
Visual Programming for Text-to-Image Generation and Evaluation (NeurIPS 2023)
VPGen helps creators and designers generate images from text descriptions with more control. You provide a text prompt, and it first breaks down the scene into objects and their arrangement, then generates an image that precisely matches that layout. This is ideal for anyone needing to visualize specific object placements or compositions from a text idea.
No commits in the last 6 months.
Use this if you need fine-grained control over the composition and object placement in AI-generated images, rather than just a general aesthetic.
Not ideal if you're looking for a simple, one-step text-to-image tool without needing to inspect or influence intermediate layout steps.
Stars
57
Forks
3
Language
Jupyter Notebook
License
—
Category
Last pushed
Jul 25, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/j-min/VPGen"
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