search

PixArt-alpha / PixArt-sigma

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
https://pixart-alpha.github.io/PixArt-sigma-project/
GNU Affero General Public License v3.0
1.44k stars 67 forks source link

About VAE #106

Closed berryxue closed 6 days ago

berryxue commented 1 month ago

I want to fine-tune 1024 model, can I directly use VAE and text_encoder from https://huggingface.co/PixArt-alpha/PixArt-Sigma-XL-2-1024-MS/tree/main? Or must use these models from https://huggingface.co/PixArt-alpha/pixart_sigma_sdxlvae_T5_diffusers/tree/main?

ReyJ94 commented 1 week ago

you may be get your answers faster if you ask about finetuning questions from pixart discord server

lawrence-cj commented 1 week ago

Yes. You can directly use them. They are the same.