Instructions to use SJTU-DENG-Lab/LatentUM-Decoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SJTU-DENG-Lab/LatentUM-Decoder with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SJTU-DENG-Lab/LatentUM-Decoder", 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
Commit History
-
Add model card for LatentUM
Verified signatureHi! I'm Niels, part of the community science team at Hugging Face. I'm opening this PR to add a model card to your repository. This model card includes: - A link to the [original paper](https://huggingface.co/papers/2604.02097). - A link to the official Github repository. - Metadata for the `apache-2.0` license and the `image-to-image` pipeline tag. - Sample usage code snippets for image understanding and image generation as found in your README. Feel free to merge this if it looks good!554e32c
-
Upload folder using huggingface_hub
Verified signature0cc47ec -
initial commit
Verified signature184a265