Yeri AI image-to-video experiments: tips after a month

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. The goal is a short, honest reference: what each part of the tool is good at, and where it still needs a second pass.

Editing tools

Upscaling and enhancement fix soft or low-resolution sources before you animate them, which noticeably improves video results. The watermark remover and style changer cover most quick fixes that used to need a desktop editor.

Tips

• Use the same reference image across a series to keep characters consistent.
• Keep a log of prompt, model and seed for every image you plan to reuse.
• Check hands, text and logos at full size before publishing.

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.

Image prompts

Start with the subject, then the setting, then light and lens. For example: 'ceramic mug on a linen table, soft window light from the left, 50mm, shallow depth of field'. Short, concrete nouns beat long lists of adjectives. 'Rainy Tokyo alley at night, neon reflections' works better than ten style words.

Use cases

Typical uses: product photos for small shops, YouTube thumbnails, ad creatives, concept art, and short promo clips. Marketers, e-commerce sellers, designers and video creators are the people who get the most out of it.

Links

Try it here: https://yeri.ai

I update this file when a workflow changes.