About testing Zero-shot generalizability

FoundationVision / VAR

[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

4.03k stars 302 forks source link

About testing Zero-shot generalizability #7

Closed Youngwoo-git closed 5 months ago

Youngwoo-git commented 6 months ago

Thank you for sharing the code!

Just noticed the empty script in train.py, would like to know by when I can get an access to the training code. Also, is there any plan of releasing code regarding zero-shot generalization such as Class-cond editing?

Thanks in advance!

keyu-tian commented 5 months ago

@Youngwoo-git yes i'm actively working on cleaning these codes. Both training codes and zero-shot demos wil be ok in this week. Stay tuned🍻!

keyu-tian commented 5 months ago

hi @Youngwoo-git, our training codes & scripts are released. More demos will be ready in the next few days. Feel free to drop an issue again if you run into any other problem.

Thanks, and have fun with VAR!