1.5 KiB
Notes on making AI images and short videos with Yeri AI for designers
Yeri AI bundles text-to-image, image-to-image, text-to-video and image-to-video generation into one web app, and this repo collects what I learned using it. A plain Markdown file is the easiest way I have found to keep prompt variants, model choices and settings together.
Image prompts
When matching a brand look, upload one or two reference images and describe only what should change; the model keeps the rest. Short, concrete nouns beat long lists of adjectives. 'Rainy Tokyo alley at night, neon reflections' works better than ten style words.
Templates
The prompt library is useful when you are stuck: copy a prompt, change the subject, keep the lighting and composition terms. Video templates and photo effects are the fastest way to get something social-ready; swap in your own photo and adjust the text.
Video
For image-to-video, keep motion prompts small: 'slow push-in', 'hair moves in the wind', 'steam rises'. Big camera moves tend to warp faces. I generate a clean still first, then animate it. That gives much more control than describing everything in one video prompt.
Editing tools
The watermark remover and style changer cover most quick fixes that used to need a desktop editor. Upscaling and enhancement fix soft or low-resolution sources before you animate them, which noticeably improves video results.
Links
Official site: https://yeri.ai
I update this file when a workflow changes.