Instructions to use Prince3003/OmniGen2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Prince3003/OmniGen2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Prince3003/OmniGen2", 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
Download model_index.json from Prince3003/OmniGen2: direct link, hf CLI and curl.
- Browser
- Download file 462 Bytes
-
https://huggingface.co/Prince3003/OmniGen2/resolve/main/model_index.json
- Command line
-
hf download hf://Prince3003/OmniGen2/model_index.json
-
curl -L -o model_index.json https://huggingface.co/Prince3003/OmniGen2/resolve/main/model_index.json
462 Bytes
| { | |
| "_class_name": "OmniGen2Pipeline", | |
| "_diffusers_version": "0.33.1", | |
| "mllm": [ | |
| "transformers", | |
| "Qwen2_5_VLForConditionalGeneration" | |
| ], | |
| "processor": [ | |
| "transformers", | |
| "Qwen2_5_VLProcessor" | |
| ], | |
| "scheduler": [ | |
| "scheduling_flow_match_euler_discrete", | |
| "FlowMatchEulerDiscreteScheduler" | |
| ], | |
| "transformer": [ | |
| "transformer_omnigen2", | |
| "OmniGen2Transformer2DModel" | |
| ], | |
| "vae": [ | |
| "diffusers", | |
| "AutoencoderKL" | |
| ] | |
| } | |