Instructions to use fal/MOSS-Image-SFT-flashpack with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use fal/MOSS-Image-SFT-flashpack with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("fal/MOSS-Image-SFT-flashpack", 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
Download flashpack_conversion.json from fal/MOSS-Image-SFT-flashpack: direct link, hf CLI and curl.
- Browser
- Download file 671 Bytes
-
https://huggingface.co/fal/MOSS-Image-SFT-flashpack/resolve/main/flashpack_conversion.json
- Command line
-
hf download hf://fal/MOSS-Image-SFT-flashpack/flashpack_conversion.json
-
curl -L -o flashpack_conversion.json https://huggingface.co/fal/MOSS-Image-SFT-flashpack/resolve/main/flashpack_conversion.json
671 Bytes
| { | |
| "epoch": 6, | |
| "source_repo": "OpenMOSS-Team/MOSS-Image-SFT", | |
| "source_revision": "daf706d2e1c7a6369c17b6d1658671aee6db1ebe", | |
| "dtype": "keep", | |
| "components": [ | |
| "text_encoder", | |
| "transformer", | |
| "vae" | |
| ], | |
| "components_only": null, | |
| "variant": null, | |
| "include_root": false, | |
| "ignore_names": [], | |
| "ignore_prefixes": [], | |
| "ignore_suffixes": [], | |
| "files": null, | |
| "pack_files": null, | |
| "pickle_key": null, | |
| "rename_prefixes": null, | |
| "include_names": null, | |
| "include_prefixes": null, | |
| "include_suffixes": null, | |
| "script_sha256": "129b4821dbc3cf7d01b5ce93e7672af1f90a057384df7ec89d2cf3eea4a9f3b5", | |
| "n_packs": 3, | |
| "total_pack_bytes": 27199665154 | |
| } |