Instructions to use CompVis/ldm-celebahq-256 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use CompVis/ldm-celebahq-256 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("CompVis/ldm-celebahq-256", 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
Update vqvae/config.json
#5
by david20571015 - opened
LDMPipeline use scaling_factor to have unit variance and which is defaults to 0.18215.
But this model config was upload before this modification.
Therefore, scaling_factor should be set to 1 to prevent the image generation problem.