diff --git a/README.md b/README.md
new file mode 100644
index 0000000..2efd3d8
--- /dev/null
+++ b/README.md
@@ -0,0 +1,33 @@
+# Yeri AI cheat sheet: images, edits and clips: what actually works
+
+This repository keeps my notes on [Yeri AI](https://yeri.ai), an online tool that turns prompts and photos into images and short clips. Writing things down here stops me from re-discovering the same settings every time I start a new project.
+
+![Yeri AI example](example.jpg)
+
+## Editing tools
+
+Upscaling and enhancement fix soft or low-resolution sources before you animate them, which noticeably improves video results. The image expander (outpainting) is handy for turning a square photo into a 16:9 banner without cropping the subject.
+
+## Tips
+
+- Use the same reference image across a series to keep characters consistent.
+- Check hands, text and logos at full size before publishing.
+- Generate four variations, pick one, then iterate on that one only.
+
+## Use cases
+
+Marketers, e-commerce sellers, designers and video creators are the people who get the most out of it. Typical uses: product photos for small shops, YouTube thumbnails, ad creatives, concept art, and short promo clips.
+
+## Video
+
+Text-to-video clips are short, so plan one idea per clip and cut several together afterwards. I generate a clean still first, then animate it. That gives much more control than describing everything in one video prompt.
+
+## Models
+
+I usually draft on a lighter model, keep the seed and prompt, then re-render the best two or three on a higher-quality model. Yeri AI lets you choose the model per job. Seedream is my pick for detailed product shots, Nano Banana for fast drafts and multi-reference edits, and GPT Image when the picture has to contain readable text.
+
+## Links
+
+Website: https://yeri.ai
+
+Corrections and new prompt ideas are welcome.
\ No newline at end of file