Instructions to use Intel/ldm3d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Intel/ldm3d with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Intel/ldm3d", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Web Hosted Inference API Broken
If you view the main page (https://huggingface.co/Intel/ldm3d) and try the Hosted inference API on the right, it fails with the message:
module 'diffusers' has no attribute 'StableDiffusionLDM3DPipeline'
I'd like to try this but right now it's missing clear instructions on how to make it work.
Same for me.
The last version of diffusers is not aligned with main yet
You can install from souce (from main) and it should work!
Let us know if you still have issues
Could we update the readme with the steps to run from source?
You may install latest diffusers main branch from source:
pip install git+https://github.com/huggingface/diffusers
O sorry! I thought I answered already
Thank you @sammysun0711 :)
Yes this is the way
We also published a new ckpt if youre interested: https://huggingface.co/Intel/ldm3d-4c
Hi @sammysun0711 , @jwalton73 and @chrismatthieu
The demo is available here :https://huggingface.co/spaces/Intel/ldm3d
Its using a new checkpoint we published https://huggingface.co/Intel/ldm3d-pano
Enjoy!
@estellea thanks for your great update. I try out the space quickly and the result is quite amazing! :)