How Endlss works
Select an image. See what's similar. Select again. Every image leads somewhere new — across five dimensions of discovery.
Visual Similarity
Powered by CLIP embeddings, Endlss finds images that look, feel, and resonate like the one you're viewing. Not keyword matching — true visual understanding.
Colour Exploration
Every image is analysed for its dominant colour palette. Explore by colour to find images that share your favourite tones and moods.
Smart Tags
AI-generated and community-curated tags let you explore by subject, style, and theme. Vote on tags to improve discovery for everyone.
Prompt Similarity
For AI-generated images, explore by the prompts that created them. Find images born from similar creative ideas.
Collections
Build named collections of your favourite discoveries. Organise by theme, mood, or project — then share them with anyone via a link.
Share & Discover
Every path through Endlss is unique. Share your discoveries, follow other explorers, and see what the community is finding.
Frequently asked questions
- How does visual similarity work?
- Endlss uses CLIP (Contrastive Language-Image Pretraining) to generate 512-dimensional embeddings for each image. Images with similar visual content, style, or subject are close in this embedding space, enabling nearest-neighbour similarity search.
- Is Endlss free to use?
- Yes. Browsing, exploring, and discovering images is completely free. Optional subscriptions unlock additional features like larger collections and priority uploads.
- Can I upload my own images?
- Absolutely. Signed-in users can upload images and videos through the inbox. Your content goes through our pipeline for tagging, colour extraction, and embedding — then it becomes discoverable by the community.