

Songwei Ge
161 posts

@Songwei_Ge
Research Scientist @Reve. Previously Ph.D. student at @UMDCS.




Reve's new text-to-image model is here. Really proud of the team to rank at #3 with the big labs. To my knowledge, we are the first lab to use native pixel space diffusion without latent autoencoder at 4k (16MP) resolution for production level image generation.

Reve V1.5 lands top 3 in Image Arena behind GPT-Image-1.5 and variants of Nano Banana Pro. A strong showing for @Reve’s first Text-to-Image model on Arena which delivers up to 4k output. Highlights: - #4, scoring 1177, on par with Grok-Imagine-Image - Top 5 for categories: Text Rendering, Art and Product, Branding Commercial Design Congrats to the Reve team on this milestone. 👏




Faster models are here. reve-edit-fast and reve-remix-fast are now available, and cheaper than ever.


Proud advisor moment 😊 Congrats @Songwei_Ge for winning the Larry S. Davis Doctoral Dissertation Award @umdcs! Songwei is now cooking as a research scientist at @reve. Looking forward to amazing work!
