Instructions to use inclusionAI/Ming-Lite-Uni with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use inclusionAI/Ming-Lite-Uni with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("inclusionAI/Ming-Lite-Uni", 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
Add model card
#1
by nielsr HF Staff - opened
This PR adds a model card, making sure the model is easily findable on the hub. It:
- links to the paper (Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction).
- adds a library name (the model is compatible with the Transformers library, according to file information).
- adds a license (MIT)
- sets a relevant
pipeline_tag, meaning this model is now discoverable at https://huggingface.co/models?pipeline_tag=image-text-to-text - adds link to the code
I think it looks good, and I appreciate your contribution.
m1ngcheng changed pull request status to merged