prolificdreamer

prolificdreamer copied to clipboard

The result doesn't look good in stage 1

6

The commands I run are as follows： ``` cd ./prolificdreamer-main CUDA_VISIBLE_DEVICES=0 python main.py --text "Albert Einstein is playing the guitar." --iters 25000 --lambda_entropy 100 --scale 7.5 --n_particles 1 --h 512...

MnKnight1

I'm curious if it makes sense to switch the VSD loss and LoRA loss in the paper (switch the following two red boxes). I feel like it is intuitively more...

ziye3001

[Question] Loss Factor to Weight LoRA Loss and VSD Loss

1

Thank you for your awesome research!!! I have been trying to implement prolific dreamer recently. Would you like to share more details about how to set factors for VSD loss...

jameskuma

Export mesh + texture

3

Thanks for your great work! My goal is to import highly detailed meshes and textures into 3D software like Blender, Unreal for rendering How do export mesh and textures (diffuse,...

SlimeVRX

I am interested in reviewing the 3D model generated by ProlificDreamer, please enlight me of how to get one of the file in fbx, obj, glb or other format.

codyddd

A question about the cost time of a training process

1

I used the default config to run bash run.sh 0 "A pineapple." It cost 9 hours on 4090. I wonder if it is normal?

2019211753

generate from single image version

1

hello did you also program a version of this that works with single image input instead of text ? how can i switch it ? thank you for your attention

shayansep

since the training takes sooo much time despite i've got 4090 rtx, is there any checkpoints for the training ?

shayansep