> For the complete documentation index, see [llms.txt](https://docs.apiframe.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.apiframe.ai/ai-photos/best-input-images.md).

# Best Input Images

To get the best results, your input images should be:

* **High quality**: Use clear, well-lit images with good resolution (ideally 1024×1024 or higher)
* **Diverse in composition**: Include various poses, expressions, angles, and outfits
* **Consistent in subject**: Ensure all images feature the same person
* **Clean background**: Simpler backgrounds help the model focus on the subject
* **Well-cropped**: Center the subject and avoid unnecessary elements
* **Varied in framing**: Mix of close-ups, mid-shots, and full-body images
* **Consistent in style**: Similar lighting and color grading across images
* **Free of watermarks/text**: These can confuse the model
* **Adequate quantity**: 15-30 high-quality images typically work better than 100+ low-quality ones