Clarification Needed on the Models Behind Reported Results in the Paper · Issue #71 · baaivision/Emu3 · GitHub
More Web Proxy on the site http://driver.im/
You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Could you kindly specify whether the reported results are derived from distinct models tailored for each task—specifically Emu3-Chat for visual understanding and Emu3-Gen for image generation—or if they stem from Emu3-Stage1? The previous issue also mentions an unreleased unified model; does this play a role in the results discussed?
Thanks for your attention to this matter.
The text was updated successfully, but these errors were encountered:
Hi, thanks for your great work! @ryanzhangfan
Could you kindly specify whether the reported results are derived from distinct models tailored for each task—specifically Emu3-Chat for visual understanding and Emu3-Gen for image generation—or if they stem from Emu3-Stage1? The previous issue also mentions an unreleased unified model; does this play a role in the results discussed?
Thanks for your attention to this matter.
The text was updated successfully, but these errors were encountered: