threestudio

threestudio copied to clipboard

[Hash3D] Accelerate threestudio for free

1

🎉 Hi guys and maintainers, we just release [Hash3D](https://github.com/Adamdad/hash3D) that aims to accelerate SDS for free. It is universal, so that any text23D or image23D code can benefit from our...

Adamdad

Problem with tinycudann

14

I am facing this after setting up the Docker project: ```python dreamer@9d615a31c0af:~/threestudio$ python launch.py --config configs/dreamfusion-if.yaml --train --gpu 0 system.prompt_processor.prompt="white flully dog :)" trainer.max_steps=10000 system.prompt_processor.spawn=false Traceback (most recent call last):...

notdanilo

How to export Mesh in GaussianDreamer? (Missing mandatory value: tag error)

5

## summary * GaussianDreamer installation was successful * Successfully created `point_cloud.ply` file under `outputs/gs-sds-mvdream/an_astronaut_wearing_a_blue_suit@20240329-022833/save`, and `last.ckpt` under `gs-sds-mvdream/an_astronaut_wearing_a_blue_suit@20240329-022833/ckpts` * Tried running `Mesh export` commands causes `Missing mandatory value: tag` error...

hayoung-jeremy

implementation of sv3d

1

is there any plan to embed sv3d into threestudio?

sekkit

A question about gradients [really confused]

1

While running **DreamFusion**, I wanted to delve deeper into the values of gradients, but I found that the following two values are different (though I merely decomposed it manually using...

ByChelsea

https://discuss.pytorch.org/t/saving-tensor-with-torch-save-uses-too-much-memory/46865/2 saving the text embedding as cache without .clone() will have the file size of whole tensor.

kamwoh

For example, when the batch_size = 2, the arrangement of text embeddings is [pos_b_1, pos_b_2, uncond_b_1, uncond_b_2, neg_1_b_1, neg_2_b_1, neg_1_b_2, neg_2_b_2], while the arrangement of $t$ is [t_b_1, t_b_2] *...

2y7c3

Audio to 3D (Question)

1

Hi, Thank you all for a great git! I want to try some new thing instead use the text prompt diffusion model to generate 3d I want to try the...

arielkantorovich

I have tried to run a couple of Image-to-3D methods, including Wonder3D, TripoSR, SV3D, etc. The output of these methods is all single .obj file without .mtl and textured_UV maps....

PROPHETE-pro

The current volsdf alpha value is computed as: alpha = torch.abs(dists.detach()) * volsdf_density(sdf, inv_std) I believe the actual formula should be: alpha = 1 - torch.exp(-dists * volsdf_density(sdf, inv_std) )...

lzqsd