Text-to-Image
Diffusers
Safetensors
MOSSImagePipeline
quantized
mecha
weight-only
int4
experimental
image
8-bit precision
Instructions to use Rin247/MOSS-Image-SFT-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Rin247/MOSS-Image-SFT-INT4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Rin247/MOSS-Image-SFT-INT4", 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 vae/quantization.json from Rin247/MOSS-Image-SFT-INT4: direct link, hf CLI and curl.
- Browser
- Download file 182 Bytes
-
https://huggingface.co/Rin247/MOSS-Image-SFT-INT4/resolve/main/vae/quantization.json
- Command line
-
hf download hf://Rin247/MOSS-Image-SFT-INT4/vae/quantization.json
-
curl -L -o quantization.json https://huggingface.co/Rin247/MOSS-Image-SFT-INT4/resolve/main/vae/quantization.json
182 Bytes
| { | |
| "format": "INT8", | |
| "scale": "per-tensor", | |
| "per_tensor_relative_error": 0.015259, | |
| "per_tensor_weights_lost": 0.021574, | |
| "matrices_measured": 4, | |
| "package_format": "INT4" | |
| } |