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
4.25k stars 315 forks source link

Can you opensource the StyleGAN code when training Multi-scale VQ? #90

Open sunset-clouds opened 3 weeks ago

sunset-clouds commented 3 weeks ago

Without the GAN loss, we find the reconstructed images are over-smooth, will you opensource the StyleGAN code when training Multi-scale VQ?

sen-ye commented 2 weeks ago

You can refer to: https://github.com/FoundationVision/LlamaGen/blob/main/tokenizer/tokenizer_image/discriminator_stylegan.py