Spaces:
Running
on
Zero
Multiple Image Input support
With the amazing results of Image to 3d generations i can only imagine the amount of accuracy it can bring with multiple reference image support
Ideally a 3d generation should support up to 6 images ( for all angles )
For future if you can guide the 3d generation with ability to specify the view ( like top, front, side etc ) it would produce more accurate results
PS thanks for this amazing model we love it hopefully it gets the updates it deserve
yes it would be so so good,
i`ve got these concepts its such a pity it sometimes gets the ratios or some details i cant get in one picture for the back of the tank
This is exactly what i am talking about, at the end of the day accuracy in 3D models matter a lot especially when it comes to usability of a AI generated 3D model in a professional pipeline.
Hope the developers actually consider it and make this great tool awesome with these sort of features
@JeffreyXiang
thanks in advance
With the amazing results of Image to 3d generations i can only imagine the amount of accuracy it can bring with multiple reference image support
Ideally a 3d generation should support up to 6 images ( for all angles )
For future if you can guide the 3d generation with ability to specify the view ( like top, front, side etc ) it would produce more accurate results
PS thanks for this amazing model we love it hopefully it gets the updates it deserve
The issue with this is it would require another train of the model for the view selection (I think). This may be doable, but I'd make sure to wait for input from the creator.
@abjo THEY MADE IT