threestudio

threestudio copied to clipboard

Increase the number of graphics cards. There is a memory shortage, CUDA out of memory。

1

this is OK。 python launch.py --config configs/prolificdreamer.yaml --train --gpu 0,1,2,3,4 system.prompt_processor.prompt="a blue car" this is a memory shortage. python launch.py --config configs/prolificdreamer.yaml --train --gpu 0,1,2,3,4,5 system.prompt_processor.prompt="a blue car" The other...

tmrjlu

token_merging error！How can i do it?

1

scipt： python launch.py --config configs/prolificdreamer.yaml --train --gpu 5,6 system.prompt_processor.prompt="a DSLR photo of a blue car" data.batch_size=1 data.width=256 data.height=256 system.guidance.token_merging=true TypeError: __init__() got an unexpected keyword argument 'token_merging'

tmrjlu

[DRAFT] Prolific Zero123

1

Makes Prolific Dreamer with Zero123, adds LoRA layers to Zero123. Not ready to publish yet.

voletiv

Google Colab Error

1

``` ╭───────────────────── Traceback (most recent call last) ──────────────────────╮ │ /content/threestudio/launch.py:180 in │ │ │ │ 177 │ │ 178 │ │ 179 if __name__ == "__main__": │ │ ❱ 180...

qtabdullah

Using prompt [RAW photo, (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3] and negative prompt [(overexposed, underexposed, out of focus, deformed iris, deformed pupils,...

DSaurus

Multiple errors, WSL2 Ubuntu

2

Hello, all sorts of issues here culminating in a "FileNotFoundError: Text embedding file .threestudio_cache/text_embeddings/380af1c90b3b8ac914fde9dd32b144db.pt for model DeepFloyd/IF-I-XL-v1.0 and prompt [a zoomed out DSLR photo of a baby bunny sitting on...

Ainaemaet

ImageDreamfusion accumulate grad, guidance_eval in sd,if

1

1. Accumulates grad in imagedreamfusion Fixes imagedreamfusion to accumulate grads from ref and guidance 2. Adds guidance_eval to stable_diffusion, deep_floyd Adds the ability to optionally evaluate guidance periodically, in stable_diffusion...

voletiv

Support utilization of volsdf density function in neus volume renderer. I have discovered that VolSDF is more stable than NeuS in sparse multi-view reconstruction tasks and 3D generation using VSD...

DSaurus

Thank you so much for this great work. I just made a 2D demo of Prolific Dreamer with VSD loss (SDS loss is also supported) [here](https://github.com/yuanzhi-zhu/prolific_dreamer2d) for those who are...

yuanzhi-zhu

About VSD loss in 2D playground

2

Could you give an example about how to use VSD loss in 2D img?

MontaEllis