Instructions to use faverogian/Smithsonian128ControlNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use faverogian/Smithsonian128ControlNet with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("faverogian/Smithsonian128ControlNet", 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
metadata
language:
- en
license: apache-2.0
library_name: diffusers
tags:
- diffusion
datasets:
- huggan/smithsonian_butterflies_subset
Model Card for Smithsonian128UNet
A pre-trained ControlNet on the Smithsonain Butterflies 128x128 dataset (HuggingFace) using Canny images as conditioning.
Model Description
An EMA model saved at the conclusion of training (1000 epochs) of an unconditional diffusion model on the Smithsonian Butterflies 128x128 dataset. Trained using the Simple Diffusion paradigm
- Developed by: [Gian Favero]
- License: [Apache 2.0]
Model Sources [optional]
- Repository: [https://github.com/faverogian/simpleDiffusion]
- Paper [optional]: [https://arxiv.org/pdf/2301.11093]
How to Get Started with the Model
Full usage details can be found at the GitHub repository page.
Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type: 4x 16GB V100
- Hours used: 1 hour
- Compute Region: Canada