Instructions to use OpenTO/LDM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OpenTO/LDM with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OpenTO/LDM", 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
Commit History
-
Improve model card for Optimize Any Topology
Verified signatureThis PR updates the model card for the Optimize Any Topology (OAT) model. Key changes include: - Adding `pipeline_tag: text-to-image` to the metadata for better discoverability. - Adding `datasets: OpenTO/OpenTO` to the metadata, linking to the primary training dataset mentioned in the GitHub repository. - Replacing boilerplate text with a comprehensive model description based on the paper abstract. - Adding direct links to the paper and the GitHub repository. - Detailing the two-stage training process, the training data, and listing the available pre-trained checkpoints on Hugging Face. - Providing a BibTeX citation for the paper. - Removing placeholders and filling in relevant sections with information from the paper and GitHub README.70e0ea3
-
Upload CTOPUNet
Verified signature59aca1e -
initial commit
Verified signaturec65c376