Instructions to use serizard1005/Cosmos3-nano-dummy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use serizard1005/Cosmos3-nano-dummy with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("serizard1005/Cosmos3-nano-dummy", 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
-
Update dummy Cosmos3-Nano weights (real shapes, random normal(0,0.02) init)
Verified signature0c78582 -
Add dummy Cosmos3-Nano weights (real shapes, zero-initialized)
Verified signaturee0f9c54