Instructions to use akhaliq/MOSS-Image-SFT-4-steps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use akhaliq/MOSS-Image-SFT-4-steps 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") pipe.load_lora_weights("akhaliq/MOSS-Image-SFT-4-steps") 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
Download showcase/race_street.gif from akhaliq/MOSS-Image-SFT-4-steps: direct link, hf CLI and curl.
- Browser
- Download file 2.56 MB
-
https://huggingface.co/akhaliq/MOSS-Image-SFT-4-steps/resolve/main/showcase/race_street.gif
- Command line
-
hf download hf://akhaliq/MOSS-Image-SFT-4-steps/showcase/race_street.gif
-
curl -L -o race_street.gif https://huggingface.co/akhaliq/MOSS-Image-SFT-4-steps/resolve/main/showcase/race_street.gif
2.56 MB

- Xet hash:
- 8775b855088e89c31e6bc68338da82b4f9354408315910c0785b851e29e181b2
- Size of remote file:
- 2.56 MB
- SHA256:
- 7d680a641833eb4d25d671a62b29313a0aa87965db37bf3846b6b264a2a8726e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.