search

FoundationVision / VAR

[NeurIPS 2024 Oral][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!
MIT License
4.28k stars 315 forks source link

About in-painting tasks #74

Open zhiyuanyou opened 4 months ago

zhiyuanyou commented 4 months ago

Hello,

Thanks for your great work.

I have found that the demo does not support in-painting tasks. So I wonder whether this repo contains the in-painting scripts ?

Thanks again.

Ferenas commented 2 months ago

Same question. I am curious about how to process inpainting task? Just simply set the masked regions as 0 and implement the teacher-force reconstruction?

zijinY commented 18 hours ago

Same question, Did you try successfully ? Thanks.