Instructions to use nvidia/Cosmos-1.0-Diffusion-7B-Text2World with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Cosmos
How to use nvidia/Cosmos-1.0-Diffusion-7B-Text2World with Cosmos:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- NeMo
How to use nvidia/Cosmos-1.0-Diffusion-7B-Text2World with NeMo:
# tag did not correspond to a valid NeMo domain.
- Diffusers
How to use nvidia/Cosmos-1.0-Diffusion-7B-Text2World with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nvidia/Cosmos-1.0-Diffusion-7B-Text2World", 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
Unable to use this model even after getting access
#5
by rinhg - opened
I am using it like this - self.pipeline = DiffusionPipeline.from_pretrained(
"nvidia/Cosmos-1.0-Diffusion-7B-Text2World",
but getting an error :
Initializing on device: cuda
Setup failed with error: 404 Client Error. (Request ID: Root=1-67849669-12b3fbe50a5da60c7a9b6f81;6478420e-dbc6-4a3b-adf5-ed88a0c6edb2)
Entry Not Found for url: https://huggingface.co/nvidia/Cosmos-1.0-Diffusion-7B-Text2World/resolve/main/model_index.json.
Does anyone know how to resolve this?