Text-to-Image
Diffusers
English
Polish
quantization
torchao
diffusion-transformer
moss-image-sft
int8wo
Instructions to use WiktorMatuszek/MOSS-Image-SFT-INT8-WO-Core with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WiktorMatuszek/MOSS-Image-SFT-INT8-WO-Core with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("WiktorMatuszek/MOSS-Image-SFT-INT8-WO-Core", 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 assets/original_vs_quantized.png from WiktorMatuszek/MOSS-Image-SFT-INT8-WO-Core: direct link, hf CLI and curl.
- Browser
- Download file 840 kB
-
https://huggingface.co/WiktorMatuszek/MOSS-Image-SFT-INT8-WO-Core/resolve/main/assets/original_vs_quantized.png
- Command line
-
hf download hf://WiktorMatuszek/MOSS-Image-SFT-INT8-WO-Core/assets/original_vs_quantized.png
-
curl -L -o original_vs_quantized.png https://huggingface.co/WiktorMatuszek/MOSS-Image-SFT-INT8-WO-Core/resolve/main/assets/original_vs_quantized.png
840 kB

- Xet hash:
- 600c329b1cb95625df1c0a2e198be656924c7da5529f1cc8da38df35e8852485
- Size of remote file:
- 840 kB
- SHA256:
- a470bf24c175256f5106246c6e383fe98c29196a2f93589d340d6c91a2ebbaef
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.