Instructions to use SimpleTuner/cosmos3-component-generation-layers-bf16-super with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SimpleTuner/cosmos3-component-generation-layers-bf16-super with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SimpleTuner/cosmos3-component-generation-layers-bf16-super", 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
| # Cosmos3 Generator Component | |
| This repository contains the Cosmos3 generation-path transformer weights used by SimpleTuner. The in-transformer reasoner weights are omitted; use the matching reasoner component for K/V entries. | |