Diffusers
ConsistencyModelPipeline
generative model
unconditional image generation
consistency-model
Instructions to use openai/diffusers-ct_bedroom256 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use openai/diffusers-ct_bedroom256 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("openai/diffusers-ct_bedroom256", 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
inference steps is just one.
#1
by j35t3r - opened
num_inference_steps=1
Are the images getting better if I take a higher number?
Generally yes, see the documentation for details: https://huggingface.co/docs/diffusers/api/pipelines/consistency_models#diffusers.ConsistencyModelPipeline.__call__.num_inference_steps