JointDreamer: Ensuring Geometry Consistency and Text Congruence in Text-to-3D Generation via Joint Score Distillation

Paper Project Code (Coming Soon) Gallery

Additional Examples

More text-to-3D generation results here. Check this page for the comparison in our experiments.

A DSLR photo of a pink Spiderman dancing ballet, Marvel character HD, highly detailed 3D model

a DSLR photo of a skiing penguin wearing a puffy jacket

A wide angle zoomed out DSLR photo of a red dragon dressed in a tuxedo and playing chess, 8K, HD, photorealistic

a zoomed out DSLR photo of a bear playing electric bass

A DSLR photo of a fox working on a jigsaw puzzle, 8K, HD, photorealistic

A zoomed out DSLR photo of a hippo biting through a watermelon, 8K, HD, photorealistic

A DSLR photo of the hasty White Rabbit wearing a waistcoat and carrying a pocket watch and umbrella, ‘Alice in Wonderland’

A DSLR photo of The girl in a yellow dress dancing under the moonlight, La La Land movie, 8K, HD, photorealistic

A DSLR photo of Kungfu panda eating a dumpling, movie style, 8K, HD, photorealistic

oung son Goku riding a piece of cloud, Anime style, more details, 8K, HD

A DSLR photo of Harley Quinn grips a baseball bat with both hands, the clown girl, movie style

A DSLR photo of a Maid with doll makeup holding an ax, full body

Cinderella standing next to pumpkin carriage, more details, 8K, HD

a zoomed out DSLR photo of a baby monkey riding on a pig

A DSLR photo of Queen Elizabeth riding a motorcycle, 8K, HD, photorealistic