Instructions to use OpenMOSS-Team/MOSS-Image-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OpenMOSS-Team/MOSS-Image-SFT with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OpenMOSS-Team/MOSS-Image-SFT", 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
Official API
You are hereby greeted, OpenMOSS-Team / @Phospheneser .
MOSS-Image is a greatly appreciated model, especially under the Apache-2.0 license.
I tested it and the results are fantastic, and therefore, I would like to support you by using your official API.
However, I was not able to find an official API linked in the model card; are there plans to have an official API?
You are hereby bidden farewell.
Thank you so much for your kind words about MOSS-Image!
Great question about the API. We're actively working on it, and we expect to have official API access available hopefully next week. Once it's live, we'll update the README with the details!
Thanks again for reaching out and for your interest in supporting the project!