Instructions to use OmniGen2/OmniGen2-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OmniGen2/OmniGen2-RL with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OmniGen2/OmniGen2-RL", 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
Add pipeline tag and link to paper
#2
by nielsr HF Staff - opened
Hi! I'm Niels from the community science team at Hugging Face.
I've opened this PR to add the any-to-any pipeline tag to your model card. This helps users discover OmniGen2 when filtering models by multimodal generation capabilities on the Hub.
I've also linked the repository to its corresponding paper page on Hugging Face: OmniGen2: Towards Instruction-Aligned Multimodal Generation.