33 lines
1.8 KiB
Markdown
33 lines
1.8 KiB
Markdown
# Yeri AI: working notes for image and video generation: lessons from real projects
|
|
|
|
This repository keeps my notes on [Yeri AI](https://yeri.ai), an online tool that turns prompts and photos into images and short clips. I keep the notes in a repo because prompts drift: a wording that worked last month may need a tweak after a model update, and the history makes that easy to see.
|
|
|
|
|
|
|
|
## Templates
|
|
|
|
Video templates and photo effects are the fastest way to get something social-ready; swap in your own photo and adjust the text. The prompt library is useful when you are stuck: copy a prompt, change the subject, keep the lighting and composition terms.
|
|
|
|
## Tips
|
|
|
|
- Generate four variations, pick one, then iterate on that one only.
|
|
- Keep a log of prompt, model and seed for every image you plan to reuse.
|
|
- Use the same reference image across a series to keep characters consistent.
|
|
|
|
## 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.
|
|
|
|
## Video
|
|
|
|
Text-to-video clips are short, so plan one idea per clip and cut several together afterwards. 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.
|
|
|
|
## Models
|
|
|
|
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. Model choice matters more than prompt length. Fast models are fine for exploring ideas; switch to a pro model only for the final render to save credits.
|
|
|
|
## Links
|
|
|
|
Try it here: https://yeri.ai
|
|
|
|
Corrections and new prompt ideas are welcome. |