Your code does not seem to work?

[yosun]

Trying to run each of your documented use cases but none of them seem to work. Could you please provide some working code?

multi-view to 3D

python eval_all.py does not seem to produce the multiview to 3d unlike what is advertised

text to 3D

python evaluation.py configs/infer.yaml 
       infer.ckpt_path=ckpts/lara.ckpt
       infer.save_folder=outputs/prompts/
       infer.dataset.generator_type=instant3d
       infer.dataset.prompts=["a car made out of sushi","a beautiful rainbow fish"]

your instantmesh implementation is not done, so an exception occurs

single view to 3D

python evaluation.py configs/infer.yaml 
       infer.ckpt_path=ckpts/lara.ckpt
       infer.save_folder=outputs/single-view/
       infer.dataset.generator_type="zero123plus-v1.1"
       infer.dataset.image_pathes=\["assets/examples/19_dalle3_stump1.png"\]

we used a 1024x1024 image for 19_dalle3_stump1.png and got this error index 3 is out of bounds for dimension 1 with size 3

[apchenstu]

multi-view to 3D please specify the video_frames and save_mesh labels if you would like to output mesh and video during the evaluation

text to 3D and single view to 3D Please pull and try again, sorry for the outdated readme and dataloader

[yosun]

just want to check if downloading gobjecverse is required for multiview to 3d inference only?

[apchenstu]

Yes, you can download other datasets like google_scancel_objects by specify gso here