Text-to-Image
Cosmos
Diffusers
Safetensors
cosmos3_omni
nvidia
cosmos3
vllm-omni
sglang
sglang-diffusion
image-generation
Instructions to use nvidia/Cosmos3-Super-Text2Image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Cosmos
How to use nvidia/Cosmos3-Super-Text2Image 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
- Diffusers
How to use nvidia/Cosmos3-Super-Text2Image 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/Cosmos3-Super-Text2Image", 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
smaller version for experementing?
#15
by Manni1000 - opened
Hi, it would be cool if you could release a smaller version for experimenting. Most modern image models have scaled up by a lot, but when you just want to test new ideas, then scale can be an issue. I think it would be cool to have a 0.6B model or something like that, but with all the new modern ideas. I think it could help people explore new ideas fast :)
Late reply but there was an Cosmos 3 Edge 4B model originally announced. Nvidia has not given any updates so I assume it's still baking. It might get a Text2Image finetune but I am not sure. Should still be capable of T2I just fine though