Any-to-Any
Transformers
Safetensors
nlduni
feature-extraction
custom_code
image-text-to-text
text-to-image
image-to-image
Instructions to use nvidia/NLD-Uni with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/NLD-Uni with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/NLD-Uni", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download inference.py from nvidia/NLD-Uni: direct link, hf CLI and curl.
- Browser
- Download file 980 Bytes
-
https://huggingface.co/nvidia/NLD-Uni/resolve/main/inference.py
- Command line
-
hf download hf://nvidia/NLD-Uni/inference.py
-
curl -L -o inference.py https://huggingface.co/nvidia/NLD-Uni/resolve/main/inference.py
980 Bytes
| """Examples: python inference.py /path/to/model --task t2i --prompt 'A red mug'.""" | |
| import argparse | |
| from pathlib import Path | |
| import torch | |
| from transformers import AutoModelForCausalLM | |
| parser=argparse.ArgumentParser() | |
| parser.add_argument('model') | |
| parser.add_argument('--task',choices=['t2i','edit','understand'],default='t2i') | |
| parser.add_argument('--prompt',required=True) | |
| parser.add_argument('--image') | |
| parser.add_argument('--output',default='output.png') | |
| parser.add_argument('--seed',type=int,default=42) | |
| args=parser.parse_args() | |
| model=AutoModelForCausalLM.from_pretrained(args.model,trust_remote_code=True,torch_dtype=torch.bfloat16).to('cuda').eval() | |
| if args.task=='t2i': | |
| model.text_to_image(args.prompt,seed=args.seed).save(args.output) | |
| elif args.task=='edit': | |
| if not args.image:parser.error('--image is required for editing') | |
| model.image_edit(args.image,args.prompt,seed=args.seed).save(args.output) | |
| else: | |
| print(model.generate(args.prompt,image=args.image)) | |