lzyhha/VisualCloze
[ICCV 2025] VisualCloze: A universal image generation framework that can support a wide range of in-domain tasks and generalize to unseen ones. (🔥 🔥 🔥 Merged into offical pipelines of diffusers.)
VisualCloze is an image generation framework that helps creators produce a wide range of images, even for tasks it hasn't specifically been trained on. You provide example images and text descriptions, and it generates new images that fit your specified criteria. This tool is ideal for graphic designers, artists, marketers, or anyone needing to generate diverse visual content.
279 stars.
Use this if you need to generate images for various purposes and want a versatile tool that can adapt to new or unique creative demands by simply providing examples.
Not ideal if you require highly precise, photorealistic imagery for very specific real-world scenarios without any prior examples or creative prompts.
Stars
279
Forks
14
Language
Python
License
—
Category
Last pushed
Jan 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/lzyhha/VisualCloze"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
UCSC-VLAA/story-iter
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
PaddlePaddle/PaddleMIX
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks,...
keivalya/mini-vla
a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to...
adobe-research/custom-diffusion
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
byliutao/1Prompt1Story
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation...