Closed xizaoqu closed 2 months ago
Hi, really exciting work. I have questions about the reconstruction results in Fig.7. Do I need to append some text to reconstruct the origin image? Since if I only use the prompt "reconstruct it", the result is not that satisfying
If you want to reconstruct the original image, just using the decoder is enough. We will release the code about reconstruction soon.
Thanks, directly using the token before LLM makes the reconstruction better.
Hi, really exciting work. I have questions about the reconstruction results in Fig.7. Do I need to append some text to reconstruct the origin image? Since if I only use the prompt "reconstruct it", the result is not that satisfying
![image](https://github.com/jy0205/LaVIT/assets/45515569/769a7d92-3e53-4bbf-b37e-89caef856592)