Instructions to use SD-Next/MicroDecoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SD-Next/MicroDecoder with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SD-Next/MicroDecoder", 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 microdecoder-mage.safetensors from SD-Next/MicroDecoder: direct link, hf CLI and curl.
- Browser
- Download file 10.2 MB
-
https://huggingface.co/SD-Next/MicroDecoder/resolve/main/microdecoder-mage.safetensors
- Command line
-
hf download hf://SD-Next/MicroDecoder/microdecoder-mage.safetensors
-
curl -L -o microdecoder-mage.safetensors https://huggingface.co/SD-Next/MicroDecoder/resolve/main/microdecoder-mage.safetensors
10.2 MB
- Xet hash:
- 23a813a37abbdc1fb9099e77803a768482cf1f43c2d5f7df42d6d4b1c3088bbe
- Size of remote file:
- 10.2 MB
- SHA256:
- baf5dcf5f24fa4cca453f81b54d5a9117147d0bdbb1babb5e8c12251f9f9e318
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.