Instructions to use SeFi-Image/SeFi-Image-2B-Base-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SeFi-Image/SeFi-Image-2B-Base-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SeFi-Image/SeFi-Image-2B-Base-diffusers", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
| license: cc-by-nc-4.0 | |
| library_name: diffusers | |
| pipeline_tag: text-to-image | |
| gated: true | |
| tags: | |
| - sefi-image | |
| - semantic-first-diffusion | |
| - safetensors | |
| base_model: SeFi-Image/SeFi-Image-2B-Base | |
| # SeFi-Image Diffusers checkpoint | |
| This repository is a Diffusers-format conversion of [`SeFi-Image/SeFi-Image-2B-Base`](https://huggingface.co/SeFi-Image/SeFi-Image-2B-Base). The original checkpoint is not modified by the | |
| conversion. Refer to the source model card for model details, limitations, and responsible-use guidance. | |
| ```python | |
| import torch | |
| from diffusers import SeFiPipeline | |
| pipe = SeFiPipeline.from_pretrained( | |
| "SeFi-Image/SeFi-Image-2B-Base-diffusers", dtype=torch.bfloat16 | |
| ).to("cuda") | |
| image = pipe("A red apple on a wooden table.").images[0] | |
| image.save("sefi.png") | |
| ``` | |
| ## License | |
| The checkpoint is distributed under the Creative Commons Attribution-NonCommercial 4.0 International license | |
| (CC BY-NC 4.0). It is for non-commercial use only. | |