AniSora

less than 1 minute read

Got back from a short vacation and jump back into animation generation

Anisora is an image to video model. We can use Kontext to change image to Shinkai Makoto style and generate video from it. Examples are this picture Alt text Alt text

You May Also Enjoy

DeepSeek OCR

October 30 2025

Continue to dive into the OCR paper, which reaches silimar leve to SOTA dots.ocr

DeepSeek OCR - Background

October 29 2025

A deepseek paper about more Contexts Optical Compression than OCR, which could be the next big break through in VLM field. Great read from EZ encoder video