Ruizhi Shao

Hi, @blueangel1313. Would you mind briefly introducing what SHAP-E is and how you perform fine-tuning with ThreeStudio? Additionally, I'm curious to know if the fine-tuning process is similar to current...

Here are some 2D experiments. VSD guidance only  VSD + DU guidance, lambda_DU = 1.0  VSD + DU guidance, lambda_DU = 0.1 

It will be replaced by HIFa.

Hi, @generatorman. We are actively addressing this issue, and you can refer to [this pull request](https://github.com/threestudio-project/threestudio/pull/174) for more details. You can also consider reducing the `num_samples_per_ray` to `256` and downsampling...

I think loading the zero123 guidance model requires lots of RAM. To address this, you could consider modify `torch.load(..., map_location='cpu')` command to `torch.load(..., map_location='cuda:0)`, which could potentially alleviate the memory...

Hi, @yankeesong. Could you please share your data? I will try to help you figure out the issues.

@yankeesong Can you reconstruct your scene successfully with NeRFStudio?

Here are some issues I've found in the current implementation: Key problem: - The ```grid_prune``` in nerfacc will prune all samples if the scene is not initialized properly, resulting in...

Hi, @dunbar12138. ControlNet support both SDS and DU(dataset update proposed by instructnerf2nerf). In the DU setting, ControlNet needs to define a scheduler with a random timestep to execute multiple sampling...

It seems like your taichi version is higher, you can try to downgrade taichi to 0.6.39.